We address the challenge of task-oriented navigation in unstructured and unknown environments, where robots must incrementally build and reason on rich, metric-semantic maps in real time. Since tasks may require clarification or re-specification, it is necessary for the information in the map to be rich enough to enable generalization across a wide range of tasks. To effectively execute tasks specified in natural language, we propose a hierarchical representation built on language-embedded Gaussian splatting that enables both sparse semantic planning that lends itself to online operation and dense geometric representation for collision-free navigation. We validate the effectiveness of our method through real-world robot experiments conducted in both cluttered indoor and kilometer-scale outdoor environments, with a competitive ratio of about 60% against privileged baselines. Experiment videos and more details can be found on our project page: https://atlasnav.github.io
We present a low-cost data generation pipeline that integrates physics-based simulation, human demonstrations, and model-based planning to efficiently generate large-scale, high-quality datasets for contact-rich robotic manipulation tasks. Starting with a small number of embodiment-flexible human demonstrations collected in a virtual reality simulation environment, the pipeline refines these demonstrations using optimization-based kinematic retargeting and trajectory optimization to adapt them across various robot embodiments and physical parameters. This process yields a diverse, physically consistent dataset that enables cross-embodiment data transfer, and offers the potential to reuse legacy datasets collected under different hardware configurations or physical parameters. We validate the pipeline's effectiveness by training diffusion policies from the generated datasets for challenging contact-rich manipulation tasks across multiple robot embodiments, including a floating Allegro hand and bimanual robot arms. The trained policies are deployed zero-shot on hardware for bimanual iiwa arms, achieving high success rates with minimal human input. Project website: https://lujieyang.github.io/physicsgen/.
In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the kinds of constraints that can be practically used to form so-called diffusion bridges. We develop a mechanism for combining multiple such constraints so that the resulting multiply-constrained model remains a manual bridge that respects all constraints. We also develop a mechanism for training a diffusion model that respects such multiple constraints while also adapting it to match a data distribution. We develop and extend theory demonstrating the mathematical validity of our mechanisms. Additionally, we demonstrate our mechanism in constrained generative modeling tasks, highlighting a particular high-value application in modeling trajectory initializations for path planning and control in autonomous vehicles.
Multi-agent path planning is a critical challenge in robotics, requiring agents to navigate complex environments while avoiding collisions and optimizing travel efficiency. This work addresses the limitations of existing approaches by combining Gaussian belief propagation with path integration and introducing a novel tracking factor to ensure strict adherence to global paths. The proposed method is tested with two different global path-planning approaches: rapidly exploring random trees and a structured planner, which leverages predefined lane structures to improve coordination. A simulation environment was developed to validate the proposed method across diverse scenarios, each posing unique challenges in navigation and communication. Simulation results demonstrate that the tracking factor reduces path deviation by 28% in single-agent and 16% in multi-agent scenarios, highlighting its effectiveness in improving multi-agent coordination, especially when combined with structured global planning.
Stable and robust robotic grasping is essential for current and future robot applications. In recent works, the use of large datasets and supervised learning has enhanced speed and precision in antipodal grasping. However, these methods struggle with perception and calibration errors due to large planning horizons. To obtain more robust and reactive grasping motions, leveraging reinforcement learning combined with tactile sensing is a promising direction. Yet, there is no systematic evaluation of how the complexity of force-based tactile sensing affects the learning behavior for grasping tasks. This paper compares various tactile and environmental setups using two model-free reinforcement learning approaches for antipodal grasping. Our findings suggest that under imperfect visual perception, various tactile features improve learning outcomes, while complex tactile inputs complicate training.
Text-rich Graph Knowledge Bases (TG-KBs) have become increasingly crucial for answering queries by providing textual and structural knowledge. However, current retrieval methods often retrieve these two types of knowledge in isolation without considering their mutual reinforcement and some hybrid methods even bypass structural retrieval entirely after neighboring aggregation. To fill in this gap, we propose a Mixture of Structural-and-Textual Retrieval (MoR) to retrieve these two types of knowledge via a Planning-Reasoning-Organizing framework. In the Planning stage, MoR generates textual planning graphs delineating the logic for answering queries. Following planning graphs, in the Reasoning stage, MoR interweaves structural traversal and textual matching to obtain candidates from TG-KBs. In the Organizing stage, MoR further reranks fetched candidates based on their structural trajectory. Extensive experiments demonstrate the superiority of MoR in harmonizing structural and textual retrieval with insights, including uneven retrieving performance across different query logics and the benefits of integrating structural trajectories for candidate reranking. Our code is available at https://github.com/Yoega/MoR.
In multi-robot exploration, a team of mobile robot is tasked with efficiently mapping an unknown environments. While most exploration planners assume omnidirectional sensors like LiDAR, this is impractical for small robots such as drones, where lightweight, directional sensors like cameras may be the only option due to payload constraints. These sensors have a constrained field-of-view (FoV), which adds complexity to the exploration problem, requiring not only optimal robot positioning but also sensor orientation during movement. In this work, we propose MARVEL, a neural framework that leverages graph attention networks, together with novel frontiers and orientation features fusion technique, to develop a collaborative, decentralized policy using multi-agent reinforcement learning (MARL) for robots with constrained FoV. To handle the large action space of viewpoints planning, we further introduce a novel information-driven action pruning strategy. MARVEL improves multi-robot coordination and decision-making in challenging large-scale indoor environments, while adapting to various team sizes and sensor configurations (i.e., FoV and sensor range) without additional training. Our extensive evaluation shows that MARVEL's learned policies exhibit effective coordinated behaviors, outperforming state-of-the-art exploration planners across multiple metrics. We experimentally demonstrate MARVEL's generalizability in large-scale environments, of up to 90m by 90m, and validate its practical applicability through successful deployment on a team of real drone hardware.
Unmanned aerial vehicles (UAVs) are increasingly employed to perform high-risk tasks that require minimal human intervention. However, UAVs face escalating cybersecurity threats, particularly from GNSS spoofing attacks. While previous studies have extensively investigated the impacts of GNSS spoofing on UAVs, few have focused on its effects on specific tasks. Moreover, the influence of UAV motion states on the assessment of network security risks is often overlooked. To address these gaps, we first provide a detailed evaluation of how motion states affect the effectiveness of network attacks. We demonstrate that nonlinear motion states not only enhance the effectiveness of position spoofing in GNSS spoofing attacks but also reduce the probability of speed-related attack detection. Building upon this, we propose a state-triggered backdoor attack method (SSD) to deceive GNSS systems and assess its risk to trajectory planning tasks. Extensive validation of SSD's effectiveness and stealthiness is conducted. Experimental results show that, with appropriately tuned hyperparameters, SSD significantly increases positioning errors and the risk of task failure, while maintaining 100% stealth across three state-of-the-art detectors.
Reinforcement learning (RL) is a powerful approach for robot learning. However, model-free RL (MFRL) requires a large number of environment interactions to learn successful control policies. This is due to the noisy RL training updates and the complexity of robotic systems, which typically involve highly non-linear dynamics and noisy sensor signals. In contrast, model-based RL (MBRL) not only trains a policy but simultaneously learns a world model that captures the environment's dynamics and rewards. The world model can either be used for planning, for data collection, or to provide first-order policy gradients for training. Leveraging a world model significantly improves sample efficiency compared to model-free RL. However, training a world model alongside the policy increases the computational complexity, leading to longer training times that are often intractable for complex real-world scenarios. In this work, we propose a new method for accelerating model-based RL using state-space world models. Our approach leverages state-space models (SSMs) to parallelize the training of the dynamics model, which is typically the main computational bottleneck. Additionally, we propose an architecture that provides privileged information to the world model during training, which is particularly relevant for partially observable environments. We evaluate our method in several real-world agile quadrotor flight tasks, involving complex dynamics, for both fully and partially observable environments. We demonstrate a significant speedup, reducing the world model training time by up to 10 times, and the overall MBRL training time by up to 4 times. This benefit comes without compromising performance, as our method achieves similar sample efficiency and task rewards to state-of-the-art MBRL methods.
Accurate regional climate forecast calls for high-resolution downscaling of Global Climate Models (GCMs). This work presents a deep-learning-based multi-model evaluation and downscaling framework ranking 32 Coupled Model Intercomparison Project Phase 6 (CMIP6) models using a Deep Learning-TOPSIS (DL-TOPSIS) mechanism and so refines outputs using advanced deep-learning models. Using nine performance criteria, five K\"oppen-Geiger climate zones -- Tropical, Arid, Temperate, Continental, and Polar -- are investigated over four seasons. While TaiESM1 and CMCC-CM2-SR5 show notable biases, ranking results show that NorESM2-LM, GISS-E2-1-G, and HadGEM3-GC31-LL outperform other models. Four models contribute to downscaling the top-ranked GCMs to 0.1$^{\circ}$ resolution: Vision Transformer (ViT), Geospatial Spatiotemporal Transformer with Attention and Imbalance-Aware Network (GeoSTANet), CNN-LSTM, and CNN-Long Short-Term Memory (ConvLSTM). Effectively capturing temperature extremes (TXx, TNn), GeoSTANet achieves the highest accuracy (Root Mean Square Error (RMSE) = 1.57$^{\circ}$C, Kling-Gupta Efficiency (KGE) = 0.89, Nash-Sutcliffe Efficiency (NSE) = 0.85, Correlation ($r$) = 0.92), so reducing RMSE by 20\% over ConvLSTM. CNN-LSTM and ConvLSTM do well in Continental and Temperate zones; ViT finds fine-scale temperature fluctuations difficult. These results confirm that multi-criteria ranking improves GCM selection for regional climate studies and transformer-based downscaling exceeds conventional deep-learning methods. This framework offers a scalable method to enhance high-resolution climate projections, benefiting impact assessments and adaptation plans.
In autonomous driving, dynamic environment and corner cases pose significant challenges to the robustness of ego vehicle's decision-making. To address these challenges, commencing with the representation of state-action mapping in the end-to-end autonomous driving paradigm, we introduce a novel pipeline, VDT-Auto. Leveraging the advancement of the state understanding of Visual Language Model (VLM), incorporating with diffusion Transformer-based action generation, our VDT-Auto parses the environment geometrically and contextually for the conditioning of the diffusion process. Geometrically, we use a bird's-eye view (BEV) encoder to extract feature grids from the surrounding images. Contextually, the structured output of our fine-tuned VLM is processed into textual embeddings and noisy paths. During our diffusion process, the added noise for the forward process is sampled from the noisy path output of the fine-tuned VLM, while the extracted BEV feature grids and embedded texts condition the reverse process of our diffusion Transformers. Our VDT-Auto achieved 0.52m on average L2 errors and 21% on average collision rate in the nuScenes open-loop planning evaluation. Moreover, the real-world demonstration exhibited prominent generalizability of our VDT-Auto. The code and dataset will be released after acceptance.
Navigation Among Movable Obstacles (NAMO) poses a challenge for traditional path-planning methods when obstacles block the path, requiring push actions to reach the goal. We propose a framework that enables movability-aware planning to overcome this challenge without relying on explicit obstacle placement. Our framework integrates a global Semantic Visibility Graph and a local Model Predictive Path Integral (SVG-MPPI) approach to efficiently sample rollouts, taking into account the continuous range of obstacle movability. A physics engine is adopted to simulate the interaction result of the rollouts with the environment, and generate trajectories that minimize contact force. In qualitative and quantitative experiments, SVG-MPPI outperforms the existing paradigm that uses only binary movability for planning, achieving higher success rates with reduced cumulative contact forces. Our code is available at: https://github.com/tud-amr/SVG-MPPI
Environmental sustainability in Systems-of-Systems (SoS) is an emerging field that seeks to integrate technological solutions to promote the efficient management of natural resources. While systematic reviews address sustainability in the context of Smart Cities (a category of SoS), a systematic study synthesizing the existing knowledge on environmental sustainability applied to SoS in general does not exist. Although literature includes other types of sustainability, such as financial and social, this study focuses on environmental sustainability, analyzing how SoS contribute to sustainable practices such as carbon emission reduction, energy efficiency, and biodiversity conservation. We conducted a Systematic Mapping Study to identify the application domains of SoS in sustainability, the challenges faced, and research opportunities. We planned and executed a research protocol including an automated search over four scientific databases. Of 926 studies retrieved, we selected, analyzed, and reported the results of 39 relevant studies. Our findings reveal that most studies focus on Smart Cities and Smart Grids, while applications such as sustainable agriculture and wildfire prevention are less explored. We identified challenges such as system interoperability, scalability, and data governance. Finally, we propose future research directions for SoS and environmental sustainability.
Trajectory planning is vital for autonomous driving, ensuring safe and efficient navigation in complex environments. While recent learning-based methods, particularly reinforcement learning (RL), have shown promise in specific scenarios, RL planners struggle with training inefficiencies and managing large-scale, real-world driving scenarios. In this paper, we introduce \textbf{CarPlanner}, a \textbf{C}onsistent \textbf{a}uto-\textbf{r}egressive \textbf{Planner} that uses RL to generate multi-modal trajectories. The auto-regressive structure enables efficient large-scale RL training, while the incorporation of consistency ensures stable policy learning by maintaining coherent temporal consistency across time steps. Moreover, CarPlanner employs a generation-selection framework with an expert-guided reward function and an invariant-view module, simplifying RL training and enhancing policy performance. Extensive analysis demonstrates that our proposed RL framework effectively addresses the challenges of training efficiency and performance enhancement, positioning CarPlanner as a promising solution for trajectory planning in autonomous driving. To the best of our knowledge, we are the first to demonstrate that the RL-based planner can surpass both IL- and rule-based state-of-the-arts (SOTAs) on the challenging large-scale real-world dataset nuPlan. Our proposed CarPlanner surpasses RL-, IL-, and rule-based SOTA approaches within this demanding dataset.
Building an agent that can mimic human behavior patterns to accomplish various open-world tasks is a long-term goal. To enable agents to effectively learn behavioral patterns across diverse tasks, a key challenge lies in modeling the intricate relationships among observations, actions, and language. To this end, we propose Optimus-2, a novel Minecraft agent that incorporates a Multimodal Large Language Model (MLLM) for high-level planning, alongside a Goal-Observation-Action Conditioned Policy (GOAP) for low-level control. GOAP contains (1) an Action-guided Behavior Encoder that models causal relationships between observations and actions at each timestep, then dynamically interacts with the historical observation-action sequence, consolidating it into fixed-length behavior tokens, and (2) an MLLM that aligns behavior tokens with open-ended language instructions to predict actions auto-regressively. Moreover, we introduce a high-quality Minecraft Goal-Observation-Action (MGOA)} dataset, which contains 25,000 videos across 8 atomic tasks, providing about 30M goal-observation-action pairs. The automated construction method, along with the MGOA dataset, can contribute to the community's efforts to train Minecraft agents. Extensive experimental results demonstrate that Optimus-2 exhibits superior performance across atomic tasks, long-horizon tasks, and open-ended instruction tasks in Minecraft.
Deep Reinforcement Learning (DRL) has demonstrated potential in addressing robotic local planning problems, yet its efficacy remains constrained in highly unstructured and dynamic environments. To address these challenges, this study proposes the ColorDynamic framework. First, an end-to-end DRL formulation is established, which maps raw sensor data directly to control commands, thereby ensuring compatibility with unstructured environments. Under this formulation, a novel network, Transqer, is introduced. The Transqer enables online DRL learning from temporal transitions, substantially enhancing decision-making in dynamic scenarios. To facilitate scalable training of Transqer with diverse data, an efficient simulation platform E-Sparrow, along with a data augmentation technique leveraging symmetric invariance, are developed. Comparative evaluations against state-of-the-art methods, alongside assessments of generalizability, scalability, and real-time performance, were conducted to validate the effectiveness of ColorDynamic. Results indicate that our approach achieves a success rate exceeding 90% while exhibiting real-time capacity (1.2-1.3 ms per planning). Additionally, ablation studies were performed to corroborate the contributions of individual components. Building on this, the OkayPlan-ColorDynamic (OPCD) navigation system is presented, with simulated and real-world experiments demonstrating its superiority and applicability in complex scenarios. The codebase and experimental demonstrations have been open-sourced on our website to facilitate reproducibility and further research.
This work focuses on understanding the minimum eradication time for the controlled Susceptible-Infectious-Recovered (SIR) model in the time-homogeneous setting, where the infection and recovery rates are constant. The eradication time is defined as the earliest time the infectious population drops below a given threshold and remains below it. For time-homogeneous models, the eradication time is well-defined due to the predictable dynamics of the infectious population, and optimal control strategies can be systematically studied. We utilize Physics-Informed Neural Networks (PINNs) to solve the partial differential equation (PDE) governing the eradication time and derive the corresponding optimal vaccination control. The PINN framework enables a mesh-free solution to the PDE by embedding the dynamics directly into the loss function of a deep neural network. We use a variable scaling method to ensure stable training of PINN and mathematically analyze that this method is effective in our setting. This approach provides an efficient computational alternative to traditional numerical methods, allowing for an approximation of the eradication time and the optimal control strategy. Through numerical experiments, we validate the effectiveness of the proposed method in computing the minimum eradication time and achieving optimal control. This work offers a novel application of PINNs to epidemic modeling, bridging mathematical theory and computational practice for time-homogeneous SIR models.
Despite diverse mobility needs worldwide, existing mapping tools fail to address the varied experiences of different mobility device users. This paper presents a large-scale online survey exploring how five mobility groups -- users of canes, walkers, mobility scooters, manual wheelchairs, and motorized wheelchairs -- perceive sidewalk barriers. Using 52 sidewalk barrier images, respondents evaluated their confidence in navigating each scenario. Our findings (N=190) reveal variations in barrier perceptions across groups, while also identifying shared concerns. To further demonstrate the value of this data, we showcase its use in two custom prototypes: a visual analytics tool and a personalized routing tool. Our survey findings and open dataset advance work in accessibility-focused maps, routing algorithms, and urban planning.
The tractor-trailer vehicle (robot) consists of a drivable tractor and one or more non-drivable trailers connected via hitches. Compared to typical car-like robots, the addition of trailers provides greater transportation capability. However, this also complicates motion planning due to the robot's complex kinematics, high-dimensional state space, and deformable structure. To efficiently plan safe, time-optimal trajectories that adhere to the kinematic constraints of the robot and address the challenges posed by its unique features, this paper introduces a lightweight, compact, and high-order smooth trajectory representation for tractor-trailer robots. Based on it, we design an efficiently solvable spatio-temporal trajectory optimization problem. To deal with deformable structures, which leads to difficulties in collision avoidance, we fully leverage the collision-free regions of the environment, directly applying deformations to trajectories in continuous space. This approach not requires constructing safe regions from the environment using convex approximations through collision-free seed points before each optimization, avoiding the loss of the solution space, thus reducing the dependency of the optimization on initial values. Moreover, a multi-terminal fast path search algorithm is proposed to generate the initial values for optimization. Extensive simulation experiments demonstrate that our approach achieves several-fold improvements in efficiency compared to existing algorithms, while also ensuring lower curvature and trajectory duration. Real-world experiments involving the transportation, loading and unloading of goods in both indoor and outdoor scenarios further validate the effectiveness of our method. The source code is accessible at https://github.com/ZJU-FAST-Lab/tracailer/.
Traffic flow forecasting is a critical spatio-temporal data mining task with wide-ranging applications in intelligent route planning and dynamic traffic management. Recent advancements in deep learning, particularly through Graph Neural Networks (GNNs), have significantly enhanced the accuracy of these forecasts by capturing complex spatio-temporal dynamics. However, the scalability of GNNs remains a challenge due to their exponential growth in model complexity with increasing nodes in the graph. Existing methods to address this issue, including sparsification, decomposition, and kernel-based approaches, either do not fully resolve the complexity issue or risk compromising predictive accuracy. This paper introduces GraphSparseNet (GSNet), a novel framework designed to improve both the scalability and accuracy of GNN-based traffic forecasting models. GraphSparseNet is comprised of two core modules: the Feature Extractor and the Relational Compressor. These modules operate with linear time and space complexity, thereby reducing the overall computational complexity of the model to a linear scale. Our extensive experiments on multiple real-world datasets demonstrate that GraphSparseNet not only significantly reduces training time by 3.51x compared to state-of-the-art linear models but also maintains high predictive performance.
Accurate Subseasonal-to-Seasonal (S2S) climate forecasting is pivotal for decision-making including agriculture planning and disaster preparedness but is known to be challenging due to its chaotic nature. Although recent data-driven models have shown promising results, their performance is limited by inadequate consideration of geometric inductive biases. Usually, they treat the spherical weather data as planar images, resulting in an inaccurate representation of locations and spatial relations. In this work, we propose the geometric-inspired Circular Transformer (CirT) to model the cyclic characteristic of the graticule, consisting of two key designs: (1) Decomposing the weather data by latitude into circular patches that serve as input tokens to the Transformer; (2) Leveraging Fourier transform in self-attention to capture the global information and model the spatial periodicity. Extensive experiments on the Earth Reanalysis 5 (ERA5) reanalysis dataset demonstrate our model yields a significant improvement over the advanced data-driven models, including PanguWeather and GraphCast, as well as skillful ECMWF systems. Additionally, we empirically show the effectiveness of our model designs and high-quality prediction over spatial and temporal dimensions.
In cooperative multi-agent reinforcement learning (MARL), well-designed communication protocols can effectively facilitate consensus among agents, thereby enhancing task performance. Moreover, in large-scale multi-agent systems commonly found in real-world applications, effective communication plays an even more critical role due to the escalated challenge of partial observability compared to smaller-scale setups. In this work, we endeavor to develop a scalable communication protocol for MARL. Unlike previous methods that focus on selecting optimal pairwise communication links-a task that becomes increasingly complex as the number of agents grows-we adopt a global perspective on communication topology design. Specifically, we propose utilizing the exponential topology to enable rapid information dissemination among agents by leveraging its small-diameter and small-size properties. This approach leads to a scalable communication protocol, named ExpoComm. To fully unlock the potential of exponential graphs as communication topologies, we employ memory-based message processors and auxiliary tasks to ground messages, ensuring that they reflect global information and benefit decision-making. Extensive experiments on large-scale cooperative benchmarks, including MAgent and Infrastructure Management Planning, demonstrate the superior performance and robust zero-shot transferability of ExpoComm compared to existing communication strategies. The code is publicly available at https://github.com/LXXXXR/ExpoComm.
Snake robots enable mobility through extreme terrains and confined environments in terrestrial and space applications. However, robust perception and localization for snake robots remain an open challenge due to the proximity of the sensor payload to the ground coupled with a limited field of view. To address this issue, we propose Blind-motion with Intermittently Scheduled Scans (BLISS) which combines proprioception-only mobility with intermittent scans to be resilient against both localization failures and collision risks. BLISS is formulated as an integrated Task and Motion Planning (TAMP) problem that leads to a Chance-Constrained Hybrid Partially Observable Markov Decision Process (CC-HPOMDP), known to be computationally intractable due to the curse of history. Our novelty lies in reformulating CC-HPOMDP as a tractable, convex Mixed Integer Linear Program. This allows us to solve BLISS-TAMP significantly faster and jointly derive optimal task-motion plans. Simulations and hardware experiments on the EELS snake robot show our method achieves over an order of magnitude computational improvement compared to state-of-the-art POMDP planners and $>$ 50\% better navigation time optimality versus classical two-stage planners.
This work presents a motion planning framework for robotic manipulators that computes collision-free paths directly in image space. The generated paths can then be tracked using vision-based control, eliminating the need for an explicit robot model or proprioceptive sensing. At the core of our approach is the construction of a roadmap entirely in image space. To achieve this, we explicitly define sampling, nearest-neighbor selection, and collision checking based on visual features rather than geometric models. We first collect a set of image-space samples by moving the robot within its workspace, capturing keypoints along its body at different configurations. These samples serve as nodes in the roadmap, which we construct using either learned or predefined distance metrics. At runtime, the roadmap generates collision-free paths directly in image space, removing the need for a robot model or joint encoders. We validate our approach through an experimental study in which a robotic arm follows planned paths using an adaptive vision-based control scheme to avoid obstacles. The results show that paths generated with the learned-distance roadmap achieved 100% success in control convergence, whereas the predefined image-space distance roadmap enabled faster transient responses but had a lower success rate in convergence.
Many real-world eligibility problems, ranging from medical diagnosis to tax planning, can be mapped to decision problems expressed in natural language, wherein a model must make a binary choice based on user features. Large-scale domains such as legal codes or frequently updated funding opportunities render human annotation (e.g., web forms or decision trees) impractical, highlighting the need for agents that can automatically assist in decision-making. Since relevant information is often only known to the user, it is crucial that these agents ask the right questions. As agents determine when to terminate a conversation, they face a trade-off between accuracy and the number of questions asked, a key metric for both user experience and cost. To evaluate this task, we propose BeNYfits, a new benchmark for determining user eligibility for multiple overlapping social benefits opportunities through interactive decision-making. Our experiments show that current language models struggle with frequent hallucinations, with GPT-4o scoring only 35.7 F1 using a ReAct-style chain-of-thought. To address this, we introduce ProADA, a novel approach that leverages program synthesis to assist in decision-making by mapping dialog planning to a code generation problem and using gaps in structured data to determine the best next action. Our agent, ProADA, improves the F1 score to 55.6 while maintaining nearly the same number of dialog turns.
This work studies the planning problem for robotic systems under both quantifiable and unquantifiable uncertainty. The objective is to enable the robotic systems to optimally fulfill high-level tasks specified by Linear Temporal Logic (LTL) formulas. To capture both types of uncertainty in a unified modelling framework, we utilise Markov Decision Processes with Set-valued Transitions (MDPSTs). We introduce a novel solution technique for the optimal robust strategy synthesis of MDPSTs with LTL specifications. To improve efficiency, our work leverages limit-deterministic B\"uchi automata (LDBAs) as the automaton representation for LTL to take advantage of their efficient constructions. To tackle the inherent nondeterminism in MDPSTs, which presents a significant challenge for reducing the LTL planning problem to a reachability problem, we introduce the concept of a Winning Region (WR) for MDPSTs. Additionally, we propose an algorithm for computing the WR over the product of the MDPST and the LDBA. Finally, a robust value iteration algorithm is invoked to solve the reachability problem. We validate the effectiveness of our approach through a case study involving a mobile robot operating in the hexagonal world, demonstrating promising efficiency gains.
Many robotic applications, such as sanding, polishing, wiping and sensor scanning, require a manipulator to dexterously cover a surface using its end-effector. In this paper, we provide an efficient and effective coverage path planning approach that leverages a manipulator's redundancy and task tolerances to minimize costs in joint space. We formulate the problem as a Generalized Traveling Salesman Problem and hierarchically streamline the graph size. Our strategy is to identify guide paths that roughly cover the surface and accelerate the computation by solving a sequence of smaller problems. We demonstrate the effectiveness of our method through a simulation experiment and an illustrative demonstration using a physical robot.
Diffusion models can be used as a motion planner by sampling from a distribution of possible futures. However, the samples may not satisfy hard constraints that exist only implicitly in the training data, e.g., avoiding falls or not colliding with a wall. We propose learned viability filters that efficiently predict the future success of any given plan, i.e., diffusion sample, and thereby enforce an implicit future-success constraint. Multiple viability filters can also be composed together. We demonstrate the approach on detailed footstep planning for challenging 3D human locomotion tasks, showing the effectiveness of viability filters in performing online planning and control for box-climbing, step-over walls, and obstacle avoidance. We further show that using viability filters is significantly faster than guidance-based diffusion prediction.
Intraoral scans are widely used in digital dentistry for tasks such as dental restoration, treatment planning, and orthodontic procedures. These scans contain detailed topological information, but manual annotation of these scans remains a time-consuming task. Deep learning-based methods have been developed to automate tasks such as tooth segmentation. A typical intraoral scan contains over 200,000 mesh cells, making direct processing computationally expensive. Models are often trained on downsampled versions, typically with 10,000 or 16,000 cells. Previous studies suggest that downsampling may degrade segmentation accuracy, but the extent of this degradation remains unclear. Understanding the extent of degradation is crucial for deploying ML models on edge devices. This study evaluates the extent of performance degradation with decreasing resolution. We train a deep learning model (PointMLP) on intraoral scans decimated to 16K, 10K, 8K, 6K, 4K, and 2K mesh cells. Models trained at lower resolutions are tested on high-resolution scans to assess performance. Our goal is to identify a resolution that balances computational efficiency and segmentation accuracy.
Autonomous robotic inspection missions require balancing multiple conflicting objectives while navigating near costly obstacles. Current multi-objective path planning (MOPP) methods struggle to adapt to evolving risks like localization errors, weather, battery state, and communication issues. This letter presents an Adaptive Risk-aware and Energy-efficient NAvigation (ARENA) MOPP approach for UAVs in complex 3D environments. Our method enables online trajectory adaptation by optimizing safety, time, and energy using 4D NURBS representation and a genetic-based algorithm to generate the Pareto front. A novel risk-aware voting algorithm ensures adaptivity. Simulations and real-world tests demonstrate the planner's ability to produce diverse, optimized trajectories covering 95% or more of the range defined by single-objective benchmarks and its ability to estimate power consumption with a mean error representing 14% of the full power range. The ARENA framework enhances UAV autonomy and reliability in critical, evolving 3D missions.
Wilderness search and rescue operations are often carried out over vast landscapes. The search efforts, however, must be undertaken in minimum time to maximize the chance of survival of the victim. Whilst the advent of cheap multicopters in recent years has changed the way search operations are handled, it has not solved the challenges of the massive areas at hand. The problem therefore is not one of complete coverage, but one of maximizing the information gathered in the limited time available. In this work we propose that a combination of a recurrent autoencoder and deep reinforcement learning is a more efficient solution to the search problem than previous pure deep reinforcement learning or optimisation approaches. The autoencoder training paradigm efficiently maximizes the information throughput of the encoder into its latent space representation which deep reinforcement learning is primed to leverage. Without the overhead of independently solving the problem that the recurrent autoencoder is designed for, it is more efficient in learning the control task. We further implement three additional architectures for a comprehensive comparison of the main proposed architecture. Similarly, we apply both soft actor-critic and proximal policy optimisation to provide an insight into the performance of both in a highly non-linear and complex application with a large observation Results show that the proposed architecture is vastly superior to the benchmarks, with soft actor-critic achieving the best performance. This model further outperformed work from the literature whilst having below a fifth of the total learnable parameters and training in a quarter of the time.
Industrial robots are widely used in diverse manufacturing environments. Nonetheless, how to enable robots to automatically plan trajectories for changing tasks presents a considerable challenge. Further complexities arise when robots operate within work cells alongside machines, humans, or other robots. This paper introduces a multi-level hybrid robot motion planning method combining a task space Reinforcement Learning-based Learning from Demonstration (RL-LfD) agent and a joint-space based Deep Reinforcement Learning (DRL) based agent. A higher level agent learns to switch between the two agents to enable feasible and smooth motion. The feasibility is computed by incorporating reachability, joint limits, manipulability, and collision risks of the robot in the given environment. Therefore, the derived hybrid motion planning policy generates a feasible trajectory that adheres to task constraints. The effectiveness of the method is validated through sim ulated robotic scenarios and in a real-world setup.
Multiagent Reinforcement Learning (MARL) poses significant challenges due to the exponential growth of state and action spaces and the non-stationary nature of multiagent environments. This results in notable sample inefficiency and hinders generalization across diverse tasks. The complexity is further pronounced in relational settings, where domain knowledge is crucial but often underutilized by existing MARL algorithms. To overcome these hurdles, we propose integrating relational planners as centralized controllers with efficient state abstractions and reinforcement learning. This approach proves to be sample-efficient and facilitates effective task transfer and generalization.
Medical imaging spans diverse tasks and modalities which play a pivotal role in disease diagnosis, treatment planning, and monitoring. This study presents a novel exploration, being the first to systematically evaluate segmentation, registration, and classification tasks across multiple imaging modalities. Integrating both classical and deep learning (DL) approaches in addressing brain MRI tissue segmentation, lung CT image registration, and skin lesion classification from dermoscopic images, we demonstrate the complementary strengths of these methodologies in diverse applications. For brain tissue segmentation, 3D DL models outperformed 2D and patch-based models, specifically nnU-Net achieving Dice of 0.9397, with 3D U-Net models on ResNet34 backbone, offering competitive results with Dice 0.8946. Multi-Atlas methods provided robust alternatives for cases where DL methods are not feasible, achieving average Dice of 0.7267. In lung CT registration, classical Elastix-based methods outperformed DL models, achieving a minimum Target Registration Error (TRE) of 6.68 mm, highlighting the effectiveness of parameter tuning. HighResNet performed best among DL models with a TRE of 7.40 mm. For skin lesion classification, ensembles of DL models like InceptionResNetV2 and ResNet50 excelled, achieving up to 90.44%, and 93.62% accuracies for binary and multiclass classification respectively. Also, adopting One-vs-All method, DL attained accuracies of 94.64% (mel vs. others), 95.35% (bcc vs. others), and 96.93% (scc vs. others), while ML models specifically Multi-Layer Perceptron (MLP) on handcrafted features offered interpretable alternatives with 85.04% accuracy using SMOTE for class imbalance correction on the multi-class task and 83.27% on the binary-class task. Links to source code are available on request.
Great Britain aims to meet growing electricity demand and achieve a fully decarbonised grid by 2035, targeting 70 GW of solar photovoltaic (PV) capacity. However, grid constraints and connection delays hinder solar integration. To address these integration challenges, various connection reform processes and policies are being developed [1]. This study supports the connection reforms with a model that estimates regional PV capacity at the NUTS 3 level, explaining 89% of the variation in capacity, with a mean absolute error of 20 MW and a national mean absolute percentage error of 5.4%. Artificial surfaces and agricultural areas are identified as key factors in deployment. The model has three primary applications: disaggregating national PV capacity into regional capacity, benchmarking regional PV deployment between different regions, and forecasting future PV capacity distribution. These applications support grid operators in generation monitoring and strategic grid planning by identifying regions where capacity is likely to be concentrated. This can address grid connection delays, plan network expansions, and resolve land-use conflicts.
Shifting towards renewable energy sources and reducing carbon emissions necessitate sophisticated energy system planning, optimization, and extension. Energy systems optimization models (ESOMs) often form the basis for political and operational decision-making. ESOMs are frequently formulated as linear (LPs) and mixed-integer linear (MIP) problems. MIPs allow continuous and discrete decision variables. Consequently, they are substantially more expressive than LPs but also more challenging to solve. The ever-growing size and complexity of ESOMs take a toll on the computational time of state-of-the-art commercial solvers. Indeed, for large-scale ESOMs, solving the LP relaxation -- the basis of modern MIP solution algorithms -- can be very costly. These time requirements can render ESOM MIPs impractical for real-world applications. This article considers a set of large-scale decarbonization-focused unit commitment models with expansion decisions based on the REMix framework (up to 83 million variables and 900,000 discrete decision variables). For these particular instances, the solution to the LP relaxation and the MIP optimum lie close. Based on this observation, we investigate the application of relaxation-enforced neighborhood search (RENS), machine learning guided rounding, and a fix-and-propagate (FP) heuristic as a standalone solution method. Our approach generated feasible solutions 20 to 100 times faster than GUROBI, achieving comparable solution quality with primal-dual gaps as low as 1% and up to 35%. This enabled us to solve numerous scenarios without lowering the quality of our models. For some instances that GUROBI could not solve within two days, our \FP method provided feasible solutions in under one hour.
Recent studies have shown that Transformers can perform in-context reinforcement learning (RL) by imitating existing RL algorithms, enabling sample-efficient adaptation to unseen tasks without parameter updates. However, these models also inherit the suboptimal behaviors of the RL algorithms they imitate. This issue primarily arises due to the gradual update rule employed by those algorithms. Model-based planning offers a promising solution to this limitation by allowing the models to simulate potential outcomes before taking action, providing an additional mechanism to deviate from the suboptimal behavior. Rather than learning a separate dynamics model, we propose Distillation for In-Context Planning (DICP), an in-context model-based RL framework where Transformers simultaneously learn environment dynamics and improve policy in-context. We evaluate DICP across a range of discrete and continuous environments, including Darkroom variants and Meta-World. Our results show that DICP achieves state-of-the-art performance while requiring significantly fewer environment interactions than baselines, which include both model-free counterparts and existing meta-RL methods.
Background: Deep learning (DL)-based organ segmentation is increasingly used in radiotherapy, yet voxel-wise DL uncertainty maps are rarely presented to clinicians. Purpose: This study assessed how DL-generated uncertainty maps impact radiation oncologists during manual correction of prostate radiotherapy DL segmentations. Methods: Two nnUNet models were trained by 10-fold cross-validation on 434 MRI-only prostate cancer cases to segment the prostate and rectum. Each model was evaluated on 35 independent cases. Voxel-wise uncertainty was calculated using the SoftMax standard deviation (n=10) and visualized as a color-coded map. Four oncologists performed segmentation in two steps: Step 1: Rated segmentation quality and confidence using Likert scales and edited DL segmentations without uncertainty maps. Step 2 ($\geq 4$ weeks later): Repeated step 1, but with uncertainty maps available. Segmentation time was recorded for both steps, and oncologists provided qualitative free-text feedback. Histogram analysis compared voxel edits across uncertainty levels. Results: DL segmentations showed high agreement with oncologist edits. Quality ratings varied: rectum segmentation ratings slightly decreased overall in step 2, while prostate ratings differed among oncologists. Confidence ratings also varied. Three oncologists reduced segmentation time with uncertainty maps, saving 1-2 minutes per case. Histogram analysis showed 50% fewer edits for step 2 in low-uncertainty areas. Conclusions: Presenting DL segmentation uncertainty information to radiation oncologists influences their decision-making, quality perception, and confidence in the DL segmentations. Low-uncertainty regions were edited less frequently, indicating increased trust in DL predictions. Uncertainty maps improve efficiency by reducing segmentation time and can be a valuable clinical tool, enhancing radiotherapy planning efficiency.
General parameters are highly desirable in the natural sciences - e.g., chemical reaction conditions that enable high yields across a range of related transformations. This has a significant practical impact since those general parameters can be transferred to related tasks without the need for laborious and time-intensive re-optimization. While Bayesian optimization (BO) is widely applied to find optimal parameter sets for specific tasks, it has remained underused in experiment planning towards such general optima. In this work, we consider the real-world problem of condition optimization for chemical reactions to study how performing generality-oriented BO can accelerate the identification of general optima, and whether these optima also translate to unseen examples. This is achieved through a careful formulation of the problem as an optimization over curried functions, as well as systematic evaluations of generality-oriented strategies for optimization tasks on real-world experimental data. We find that for generality-oriented optimization, simple myopic optimization strategies that decouple parameter and task selection perform comparably to more complex ones, and that effective optimization is merely determined by an effective exploration of both parameter and task space.
In multi-robot system (MRS) applications, efficient task assignment is essential not only for coordinating agents and ensuring mission success but also for maintaining overall system security. In this work, we first propose an optimization-based distributed task assignment algorithm that dynamically assigns mandatory security-critical tasks and optional tasks among teams. Leveraging an inexact Alternating Direction Method of Multipliers (ADMM)-based approach, we decompose the task assignment problem into separable and non-separable subproblems. The non-separable subproblems are transformed into an inexact ADMM update by projected gradient descent, which can be performed through several communication steps within the team. In the second part of this paper, we formulate a comprehensive framework that enables MRS under plan-deviation attacks to handle online tasks without compromising security. The process begins with a security analysis that determines whether an online task can be executed securely by a robot and, if so, the required time and location for the robot to rejoin the team. Next, the proposed task assignment algorithm is used to allocate security-related tasks and verified online tasks. Finally, task fulfillment is managed using a Control Lyapunov Function (CLF)-based controller, while security enforcement is ensured through a Control Barrier Function (CBF)-based security filter. Through simulations, we demonstrate that the proposed framework allows MRS to effectively respond to unplanned online tasks while maintaining security guarantees.
Autonomous parking has become a critical application in automatic driving research and development. Parking operations often suffer from limited space and complex environments, requiring accurate perception and precise maneuvering. Traditional rule-based parking algorithms struggle to adapt to diverse and unpredictable conditions, while learning-based algorithms lack consistent and stable performance in various scenarios. Therefore, a hybrid approach is necessary that combines the stability of rule-based methods and the generalizability of learning-based methods. Recently, reinforcement learning (RL) based policy has shown robust capability in planning tasks. However, the simulation-to-reality (sim-to-real) transfer gap seriously blocks the real-world deployment. To address these problems, we employ a hybrid policy, consisting of a rule-based Reeds-Shepp (RS) planner and a learning-based reinforcement learning (RL) planner. A real-time LiDAR-based Occupancy Grid Map (OGM) representation is adopted to bridge the sim-to-real gap, leading the hybrid policy can be applied to real-world systems seamlessly. We conducted extensive experiments both in the simulation environment and real-world scenarios, and the result demonstrates that the proposed method outperforms pure rule-based and learning-based methods. The real-world experiment further validates the feasibility and efficiency of the proposed method.
Glioma, the prevalent primary brain tumor, exhibits diverse aggressiveness levels and prognoses. Precise classification of glioma is paramount for treatment planning and predicting prognosis. This study aims to develop an algorithm to fuse the MRI images from T1, T2, T1ce, and fluid-attenuated inversion recovery (FLAIR) sequences to enhance the efficacy of glioma subclass classification as no tumor, necrotic core, peritumoral edema, and enhancing tumor. The MRI images from BraTS datasets were used in this work. The images were pre-processed using max-min normalization to ensure consistency in pixel intensity values across different images. The segmentation of the necrotic core, peritumoral edema, and enhancing tumor was performed on 2D and 3D images separately using UNET architecture. Further, the segmented regions from multimodal MRI images were fused using the weighted averaging technique. Integrating 2D and 3D segmented outputs enhances classification accuracy by capturing detailed features like tumor shape, boundaries, and intensity distribution in slices, while also providing a comprehensive view of spatial extent, shape, texture, and localization within the brain volume. The fused images were used as input to the pre-trained ResNet50 model for glioma subclass classification. The network is trained on 80% and validated on 20% of the data. The proposed method achieved a classification of accuracy of 99.25%, precision of 99.30%, recall of 99.10, F1 score of 99.19%, Intersection Over Union of 84.49%, and specificity of 99.76, which showed a significantly higher performance than existing techniques. These findings emphasize the significance of glioma segmentation and classification in aiding accurate diagnosis.
Object-Centric Motion Generation (OCMG) plays a key role in a variety of industrial applications$\unicode{x2014}$such as robotic spray painting and welding$\unicode{x2014}$requiring efficient, scalable, and generalizable algorithms to plan multiple long-horizon trajectories over free-form 3D objects. However, existing solutions rely on specialized heuristics, expensive optimization routines, or restrictive geometry assumptions that limit their adaptability to real-world scenarios. In this work, we introduce a novel, fully data-driven framework that tackles OCMG directly from 3D point clouds, learning to generalize expert path patterns across free-form surfaces. We propose MaskPlanner, a deep learning method that predicts local path segments for a given object while simultaneously inferring "path masks" to group these segments into distinct paths. This design induces the network to capture both local geometric patterns and global task requirements in a single forward pass. Extensive experimentation on a realistic robotic spray painting scenario shows that our approach attains near-complete coverage (above 99%) for unseen objects, while it remains task-agnostic and does not explicitly optimize for paint deposition. Moreover, our real-world validation on a 6-DoF specialized painting robot demonstrates that the generated trajectories are directly executable and yield expert-level painting quality. Our findings crucially highlight the potential of the proposed learning method for OCMG to reduce engineering overhead and seamlessly adapt to several industrial use cases.
Local and federal agencies are rapidly adopting AI systems to augment or automate critical decisions, efficiently use resources, and improve public service delivery. AI systems are being used to support tasks associated with urban planning, security, surveillance, energy and critical infrastructure, and support decisions that directly affect citizens and their ability to access essential services. Local governments act as the governance tier closest to citizens and must play a critical role in upholding democratic values and building community trust especially as it relates to smart city initiatives that seek to transform public services through the adoption of AI. Community-centered and participatory approaches have been central for ensuring the appropriate adoption of technology; however, AI innovation introduces new challenges in this context because participatory AI design methods require more robust formulation and face higher standards for implementation in the public sector compared to the private sector. This requires us to reassess traditional methods used in this space as well as develop new resources and methods. This workshop will explore emerging practices in participatory algorithm design - or the use of public participation and community engagement - in the scoping, design, adoption, and implementation of public sector algorithms.
AI systems have rapidly advanced, diversified, and proliferated, but our knowledge of people's perceptions of mind and morality in them is limited, despite its importance for outcomes such as whether people trust AIs and how they assign responsibility for AI-caused harms. In a preregistered online study, 975 participants rated 26 AI and non-AI entities. Overall, AIs were perceived to have low-to-moderate agency (e.g., planning, acting), between inanimate objects and ants, and low experience (e.g., sensing, feeling). For example, ChatGPT was rated only as capable of feeling pleasure and pain as a rock. The analogous moral faculties, moral agency (doing right or wrong) and moral patiency (being treated rightly or wrongly) were higher and more varied, particularly moral agency: The highest-rated AI, a Tesla Full Self-Driving car, was rated as morally responsible for harm as a chimpanzee. We discuss how design choices can help manage perceptions, particularly in high-stakes moral contexts.
The digitization of healthcare presents numerous challenges, including the complexity of biological systems, vast data generation, and the need for personalized treatment plans. Traditional computational methods often fall short, leading to delayed and sometimes ineffective diagnoses and treatments. Quantum Computing (QC) and Quantum Machine Learning (QML) offer transformative advancements with the potential to revolutionize medicine. This paper summarizes areas where QC promises unprecedented computational power, enabling faster, more accurate diagnostics, personalized treatments, and enhanced drug discovery processes. However, integrating quantum technologies into precision medicine also presents challenges, including errors in algorithms and high costs. We show that mathematically-based techniques for specifying, developing, and verifying software (formal methods) can enhance the reliability and correctness of QC. By providing a rigorous mathematical framework, formal methods help to specify, develop, and verify systems with high precision. In genomic data analysis, formal specification languages can precisely (1) define the behavior and properties of quantum algorithms designed to identify genetic markers associated with diseases. Model checking tools can systematically explore all possible states of the algorithm to (2) ensure it behaves correctly under all conditions, while theorem proving techniques provide mathematical (3) proof that the algorithm meets its specified properties, ensuring accuracy and reliability. Additionally, formal optimization techniques can (4) enhance the efficiency and performance of quantum algorithms by reducing resource usage, such as the number of qubits and gate operations. Therefore, we posit that formal methods can significantly contribute to enabling QC to realize its full potential as a game changer in precision medicine.
Existing tracheal tumor resection methods often lack the precision required for effective airway clearance, and robotic advancements offer new potential for autonomous resection. We present a vision-guided, autonomous approach for palliative resection of tracheal tumors. This system models the tracheal surface with a fifth-degree polynomial to plan tool trajectories, while a custom Faster R-CNN segmentation pipeline identifies the trachea and tumor boundaries. The electrocautery tool angle is optimized using handheld surgical demonstrations, and trajectories are planned to maintain a 1 mm safety clearance from the tracheal surface. We validated the workflow successfully in five consecutive experiments on ex-vivo animal tissue models, successfully clearing the airway obstruction without trachea perforation in all cases (with more than 90% volumetric tumor removal). These results support the feasibility of an autonomous resection platform, paving the way for future developments in minimally-invasive autonomous resection.
Existing approaches to reward inference from behavior typically assume that humans provide demonstrations according to specific models of behavior. However, humans often indicate their goals through a wide range of behaviors, from actions that are suboptimal due to poor planning or execution to behaviors which are intended to communicate goals rather than achieve them. We propose that supervised learning offers a unified framework to infer reward functions from any class of behavior, and show that such an approach is asymptotically Bayes-optimal under mild assumptions. Experiments on simulated robotic manipulation tasks show that our method can efficiently infer rewards from a wide variety of arbitrarily suboptimal demonstrations.
In this paper we present ToMCAT (Theory-of-Mind for Cooperative Agents in Teams), a new framework for generating ToM-conditioned trajectories. It combines a meta-learning mechanism, that performs ToM reasoning over teammates' underlying goals and future behavior, with a multiagent denoising-diffusion model, that generates plans for an agent and its teammates conditioned on both the agent's goals and its teammates' characteristics, as computed via ToM. We implemented an online planning system that dynamically samples new trajectories (replans) from the diffusion model whenever it detects a divergence between a previously generated plan and the current state of the world. We conducted several experiments using ToMCAT in a simulated cooking domain. Our results highlight the importance of the dynamic replanning mechanism in reducing the usage of resources without sacrificing team performance. We also show that recent observations about the world and teammates' behavior collected by an agent over the course of an episode combined with ToM inferences are crucial to generate team-aware plans for dynamic adaptation to teammates, especially when no prior information is provided about them.
Assessing wireless coverage is a fundamental task for public network operators and private deployments, whose goal is to guarantee quality of service across the network while minimizing material waste and energy consumption. These maps are usually built through ray tracing techniques and/or channel measurements that can be consequently translated into network Key Performance Indicators (KPIs), such as capacity or throughput. However, next generation networks (e.g., 6G) typically involve beyond communication resources, towards services that require data transmission, but also processing (local and remote) to perform complex decision making in real time, with the best balance between performance, energy consumption, material waste, and privacy. In this paper, we introduce the novel concept of areas of effectiveness, which goes beyond the legacy notion of coverage, towards one that takes into account capability of the network of offering edge Artificial Intelligence (AI)-related computation. We will show that radio coverage is a poor indicator of real system performance, depending on the application and the computing capabilities of network and devices. This opens new challenges in network planning, but also resource orchestration during operation to achieve the specific goal of communication.
Interferometric Synthetic Aperture Radar (InSAR) technology uses satellite radar to detect surface deformation patterns and monitor earthquake impacts on buildings. While vital for emergency response planning, extracting multi-class building damage classifications from InSAR data faces challenges: overlapping damage signatures with environmental noise, computational complexity in multi-class scenarios, and the need for rapid regional-scale processing. Our novel multi-class variational causal Bayesian inference framework with quadratic variational bounds provides rigorous approximations while ensuring efficiency. By integrating InSAR observations with USGS ground failure models and building fragility functions, our approach separates building damage signals while maintaining computational efficiency through strategic pruning. Evaluation across five major earthquakes (Haiti 2021, Puerto Rico 2020, Zagreb 2020, Italy 2016, Ridgecrest 2019) shows improved damage classification accuracy (AUC: 0.94-0.96), achieving up to 35.7% improvement over existing methods. Our approach maintains high accuracy (AUC > 0.93) across all damage categories while reducing computational overhead by over 40% without requiring extensive ground truth data.
This study investigates the dynamics and controllability of a Purcell three-link microswimmer equipped with passive elastic torsional coils at its joints. By controlling the spontaneous curvature, we analyse the swimmers motion using both linear and weakly nonlinear approaches. Linear analysis reveals steady harmonic solutions for small-amplitude controls but does not predict any net displacement, whereas weakly nonlinear analysis predicts translation along the orientation of the central link. Using geometric control theory, we prove that the system is small time locally controllable near equilibrium and derive displacement estimates for periodic piecewise constant controls, which are validated through numerical simulations. These findings indicate that oscillatory controls can enable motion in all directions near equilibrium. This work offers foundational insights into the controllability of elastic microswimmers, paving the way for advanced motion planning and control strategies.
Electric Location-Routing models (ELRP) can contribute to the effective planning of electric vehicles (EVs) fleets and charging infrastructure within EV logistic networks because it simultaneously combines routing and location decisions to find optimal solutions to the network design. This study introduces ELRP models that incorporate nonlinear charging process, multiple charging station types and develop new improved formulations to the problem. Existing ELRP models commonly assume a linear charging process and employ a node-based formulation for tracking EV energy and time consumption. In contrast, we propose novel formulations offering alternative approaches for modeling EV energy, time consumption, and nonlinear charging. Through extensive computational experiments, our analysis demonstrates the effectiveness of the new formulations, reducing the average gap from 29.1% to 11.9%, yielding improved solutions for 28 out of 74 instances compared to the node-based formulation. Moreover, our findings provide valuable insights into the strategic implications of nonlinear charging in ELRP decision-making, offering new perspectives for planning charging infrastructure in EV logistic networks.
Medical image segmentation is crucial for clinical diagnosis and treatment planning, particularly for complex anatomical structures like vessels. In this work, we propose VesselSAM, a modified version of the Segmentation Anything Model (SAM), specifically designed for aortic vessel segmentation. VesselSAM incorporates AtrousLoRA, a novel module that combines Atrous Attention with Low-Rank Adaptation (LoRA), to improve segmentation performance. Atrous Attention enables the model to capture multi-scale contextual information, preserving both fine local details and broader global context. At the same time, LoRA facilitates efficient fine-tuning of the frozen SAM image encoder, reducing the number of trainable parameters and ensuring computational efficiency. We evaluate VesselSAM on two challenging datasets: the Aortic Vessel Tree (AVT) dataset and the Type-B Aortic Dissection (TBAD) dataset. VesselSAM achieves state-of-the-art performance with DSC scores of 93.50\%, 93.25\%, 93.02\%, and 93.26\% across multiple medical centers. Our results demonstrate that VesselSAM delivers high segmentation accuracy while significantly reducing computational overhead compared to existing large-scale models. This development paves the way for enhanced AI-based aortic vessel segmentation in clinical environments. The code and models will be released at https://github.com/Adnan-CAS/AtrousLora.
Planning a safe and feasible trajectory for autonomous vehicles in real-time by fully utilizing perceptual information in complex urban environments is challenging. In this paper, we propose a spatio-temporal trajectory planning method based on graph optimization. It efficiently extracts the multi-modal information of the perception module by constructing a semantic spatio-temporal map through separation processing of static and dynamic obstacles, and then quickly generates feasible trajectories via sparse graph optimization based on a semantic spatio-temporal hypergraph. Extensive experiments have proven that the proposed method can effectively handle complex urban public road scenarios and perform in real time. We will also release our codes to accommodate benchmarking for the research community
Local alignment between medical images and text is essential for accurate diagnosis, though it remains challenging due to the absence of natural local pairings and the limitations of rigid region recognition methods. Traditional approaches rely on hard boundaries, which introduce uncertainty, whereas medical imaging demands flexible soft region recognition to handle irregular structures. To overcome these challenges, we propose the Progressive Local Alignment Network (PLAN), which designs a novel contrastive learning-based approach for local alignment to establish meaningful word-pixel relationships and introduces a progressive learning strategy to iteratively refine these relationships, enhancing alignment precision and robustness. By combining these techniques, PLAN effectively improves soft region recognition while suppressing noise interference. Extensive experiments on multiple medical datasets demonstrate that PLAN surpasses state-of-the-art methods in phrase grounding, image-text retrieval, object detection, and zero-shot classification, setting a new benchmark for medical image-text alignment.
Current robots face challenges in manipulation tasks that require a long sequence of prehensile and non-prehensile skills. This involves handling contact-rich interactions and chaining multiple skills while considering their long-term consequences. This paper presents a framework that leverages imitation learning to distill a planning algorithm, capable of solving long-horizon problems but requiring extensive computation time, into a policy for efficient action inference. We introduce $\texttt{Skill-RRT}$, an extension of the rapidly-exploring random tree (RRT) that incorporates skill applicability checks and intermediate object pose sampling for efficient long-horizon planning. To enable skill chaining, we propose $\textit{connectors}$, goal-conditioned policies that transition between skills while minimizing object disturbance. Using lazy planning, connectors are selectively trained on relevant transitions, reducing the cost of training. High-quality demonstrations are generated with $\texttt{Skill-RRT}$ and refined by a noise-based replay mechanism to ensure robust policy performance. The distilled policy, trained entirely in simulation, zero-shot transfer to the real world, and achieves over 80% success rates across three challenging manipulation tasks. In simulation, our approach outperforms the state-of-the-art skill-based reinforcement learning method, $\texttt{MAPLE}$, and $\texttt{Skill-RRT}$.
An emerging phenomenon, digital legacy management explores the management of digital data individuals accumulate throughout their lifetime. With the integration of digital systems and data into people's daily lives, it becomes crucial to understand the intricacies of managing data to eventually form one's digital legacy. This can be understood by investigating the significance of behavioral predictors in shaping digital legacy management. The objective of this study is to explore how behavioral predictors influence the intentions of individuals in South Africa towards managing their digital legacy. This entailed: Investigating the impact of attitude, subjective norms, and perceived behavioral control on these intentions. Exploring the perceived usefulness of digital legacy management systems. Understanding the implications of response cost and task-technology fit on individuals' inclinations towards digital legacy planning. Data were collected (n = 203 valid responses) from South African residents using an online survey and analyzed using partial least squares structural equation analysis (PLS-SEM). Results indicate that attitudes, peer opinions, personal resources, and skills are significant positive influences on digital legacy management intention. Recognizing and understanding these behavioral predictors is key when developing region-specific and culturally sensitive digital legacy management tools, awareness campaigns, and policies. Furthermore, it could pave the way for more tailored strategies, ensuring effective transfer of post-mortem data, reducing potential conflicts, and providing clarity when dealing with post-mortem data.
End-to-end autonomous driving with its holistic optimization capabilities, has gained increasing traction in academia and industry. Vectorized representations, which preserve instance-level topological information while reducing computational overhead, have emerged as a promising paradigm. While existing vectorized query-based frameworks often overlook the inherent spatial correlations among intra-instance points, resulting in geometrically inconsistent outputs (e.g., fragmented HD map elements or oscillatory trajectories). To address these limitations, we propose InVDriver, a novel vectorized query-based system that systematically models intra-instance spatial dependencies through masked self-attention layers, thereby enhancing planning accuracy and trajectory smoothness. Across all core modules, i.e., perception, prediction, and planning, InVDriver incorporates masked self-attention mechanisms that restrict attention to intra-instance point interactions, enabling coordinated refinement of structural elements while suppressing irrelevant inter-instance noise. Experimental results on the nuScenes benchmark demonstrate that InVDriver achieves state-of-the-art performance, surpassing prior methods in both accuracy and safety, while maintaining high computational efficiency. Our work validates that explicit modeling of intra-instance geometric coherence is critical for advancing vectorized autonomous driving systems, bridging the gap between theoretical advantages of end-to-end frameworks and practical deployment requirements.
Identifying statistical patterns characterizing human trajectories is crucial for public health, traffic engineering, city planning, and epidemic modeling. Recent developments in global positioning systems and mobile phone networks have enabled the collection of substantial information on human movement. Analyses of these data have revealed various power laws in the temporal and spatial statistical patterns of human mobility. For example, jump size and waiting time distributions follow power laws. Zipf's law was also established for the frequency of visits to each location and rank. Relationship $S(t)\sim t^\mu$ exists between time t and the number of sites visited up to that time t. Recently, a universal law of visitation for human mobility was established. Specifically, the number of people per unit area $\rho(r,f)$, who reside at distance r from a particular location and visit that location f times in a given period, is inversely proportional to the square of rf, i.e., $\rho(r,f) \propto (rf)^{-2}$ holds. The exploration and preferential return (EPR) model and its improved versions have been proposed to reproduce the above scaling laws. However, some rules that follow the power law are preinstalled in the EPR model. We propose a simple walking model to generate movements toward and away from a target via a single mechanism by relaxing the concept of approaching a target. Our model can reproduce the abovementioned power laws and some of the rules used in the EPR model are generated. These results provide a new perspective on why or how the scaling laws observed in human mobility behavior arise.
Safe navigation is essential for autonomous systems operating in hazardous environments. Traditional planning methods excel at long-horizon tasks but rely on a predefined graph with fixed distance metrics. In contrast, safe Reinforcement Learning (RL) can learn complex behaviors without relying on manual heuristics but fails to solve long-horizon tasks, particularly in goal-conditioned and multi-agent scenarios. In this paper, we introduce a novel method that integrates the strengths of both planning and safe RL. Our method leverages goal-conditioned RL and safe RL to learn a goal-conditioned policy for navigation while concurrently estimating cumulative distance and safety levels using learned value functions via an automated self-training algorithm. By constructing a graph with states from the replay buffer, our method prunes unsafe edges and generates a waypoint-based plan that the agent follows until reaching its goal, effectively balancing faster and safer routes over extended distances. Utilizing this unified high-level graph and a shared low-level goal-conditioned safe RL policy, we extend this approach to address the multi-agent safe navigation problem. In particular, we leverage Conflict-Based Search (CBS) to create waypoint-based plans for multiple agents allowing for their safe navigation over extended horizons. This integration enhances the scalability of goal-conditioned safe RL in multi-agent scenarios, enabling efficient coordination among agents. Extensive benchmarking against state-of-the-art baselines demonstrates the effectiveness of our method in achieving distance goals safely for multiple agents in complex and hazardous environments. Our code will be released to support future research.
This thesis concerns the use of reinforcement learning to train neural networks to aid in the design of public transit networks. The Transit Network Design Problem (TNDP) is an optimization problem of considerable practical importance. Given a city with an existing road network and travel demands, the goal is to find a set of transit routes - each of which is a path through the graph - that collectively satisfy all demands, while minimizing a cost function that may depend both on passenger satisfaction and operating costs. The existing literature on this problem mainly considers metaheuristic optimization algorithms, such as genetic algorithms and ant-colony optimization. By contrast, we begin by taking a reinforcement learning approach, formulating the construction of a set of transit routes as a Markov Decision Process (MDP) and training a neural net policy to act as the agent in this MDP. We then show that, beyond using this policy to plan a transit network directly, it can be combined with existing metaheuristic algorithms, both to initialize the solution and to suggest promising moves at each step of a search through solution space. We find that such hybrid algorithms, which use a neural policy trained via reinforcement learning as a core component within a classical metaheuristic framework, can plan transit networks that are superior to those planned by either the neural policy or the metaheuristic algorithm. We demonstrate the utility of our approach by using it to redesign the transit network for the city of Laval, Quebec, and show that in simulation, the resulting transit network provides better service at lower cost than the existing transit network.
The past few years have witnessed a rapid growth of the deployment of automated vehicles (AVs). Clearly, AVs and human-driven vehicles (HVs) will co-exist for many years, and AVs will have to operate around HVs, pedestrians, cyclists, and more, calling for fundamental breakthroughs in AI designed for mixed traffic to achieve mixed autonomy. Thus motivated, we study heterogeneous decision making by AVs and HVs in a mixed traffic environment, aiming to capture the interactions between human and machine decision-making and develop an AI foundation that enables vehicles to operate safely and efficiently. There are a number of challenges to achieve mixed autonomy, including 1) humans drivers make driving decisions with bounded rationality, and it remains open to develop accurate models for HVs' decision making; and 2) uncertainty-aware planning plays a critical role for AVs to take safety maneuvers in response to the human behavior. In this paper, we introduce a formulation of AV-HV interaction, where the HV makes decisions with bounded rationality and the AV employs uncertainty-aware planning based on the prediction on HV's future actions. We conduct a comprehensive analysis on AV and HV's learning regret to answer the questions: 1) {How does the learning performance depend on HV's bounded rationality and AV's planning}; 2) {How do different decision making strategies impact the overall learning performance}? Our findings reveal some intriguing phenomena, such as Goodhart's Law in AV's learning performance and compounding effects in HV's decision making process. By examining the dynamics of the regrets, we gain insights into the interplay between human and machine decision making.
Adverse childhood experiences (ACEs) have been linked to a wide range of negative health outcomes in adulthood. However, few studies have investigated what specific combinations of ACEs most substantially impact mental health. In this article, we provide the protocol for our observational study of the effects of combinations of ACEs on adult depression. We use data from the 2023 Behavioral Risk Factor Surveillance System (BRFSS) to assess these effects. We will evaluate the replicability of our findings by splitting the sample into two discrete subpopulations of individuals. We employ data turnover for this analysis, enabling a single team of statisticians and domain experts to collaboratively evaluate the strength of evidence, and also integrating both qualitative and quantitative insights from exploratory data analysis. We outline our analysis plan using this method and conclude with a brief discussion of several specifics for our study.
Motion planning for locomotion systems typically requires translating high-level rigid-body tasks into low-level joint trajectories-a process that is straightforward for car-like robots with fixed, unbounded actuation inputs but more challenging for systems like snake robots, where the mapping depends on the current configuration and is constrained by joint limits. In this paper, we focus on generating continuous families of optimal gaits-collections of gaits parameterized by step size or steering rate-to enhance controllability and maneuverability. We uncover the underlying geometric structure of these optimal gait families and propose methods for constructing them using both global and local search strategies, where the local method and the global method compensate each other. The global search approach is robust to nonsmooth behavior, albeit yielding reduced-order solutions, while the local search provides higher accuracy but can be unstable near nonsmooth regions. To demonstrate our framework, we generate optimal gait families for viscous and perfect-fluid three-link swimmers. This work lays a foundation for integrating low-level joint controllers with higher-level motion planners in complex locomotion systems.
Medical imaging is essential in modern radiotherapy, supporting diagnosis, treatment planning, and monitoring. Synthetic imaging, particularly synthetic computed tomography (sCT), is gaining traction in radiotherapy. The SynthRAD2025 dataset and Grand Challenge promote advancements in sCT generation by providing a benchmarking platform for algorithms using cone-beam CT (CBCT) and magnetic resonance imaging (MRI). The dataset includes 2362 cases: 890 MRI-CT and 1472 CBCT-CT pairs from head-and-neck, thoracic, and abdominal cancer patients treated at five European university medical centers (UMC Groningen, UMC Utrecht, Radboud UMC, LMU University Hospital Munich, and University Hospital of Cologne). Data were acquired with diverse scanners and protocols. Pre-processing, including rigid and deformable image registration, ensures high-quality, modality-aligned images. Extensive quality assurance validates image consistency and usability. All imaging data is provided in MetaImage (.mha) format, ensuring compatibility with medical image processing tools. Metadata, including acquisition parameters and registration details, is available in structured CSV files. To maintain dataset integrity, SynthRAD2025 is divided into training (65%), validation (10%), and test (25%) sets. The dataset is accessible at https://doi.org/10.5281/zenodo.14918089 under the SynthRAD2025 collection. This dataset supports benchmarking and the development of synthetic imaging techniques for radiotherapy applications. Use cases include sCT generation for MRI-only and MR-guided photon/proton therapy, CBCT-based dose calculations, and adaptive radiotherapy workflows. By integrating diverse acquisition settings, SynthRAD2025 fosters robust, generalizable image synthesis algorithms, advancing personalized cancer care and adaptive radiotherapy.
The UltraViolet EXplorer (UVEX) is a wide-field ultraviolet space telescope selected as a NASA Medium-Class Explorer (MIDEX) mission for launch in 2030. UVEX will undertake deep, cadenced surveys of the entire sky to probe low mass galaxies and explore the ultraviolet (UV) time-domain sky, and it will carry the first rapidly deployable UV spectroscopic capability for a broad range of science applications. One of UVEX's prime objectives is to follow up gravitational wave (GW) binary neutron star mergers as targets of opportunity (ToOs), rapidly scanning across their localization regions to search for their kilonova (KN) counterparts. Early-time multiband ultraviolet light curves of KNe are key to explaining the interplay between jet and ejecta in binary neutron star mergers. Owing to high Galactic extinction in the ultraviolet and the variation of GW distance estimates over the sky, the sensitivity to kilonovae can vary significantly across the GW localization and even across the footprint of a single image given UVEX's large field of view. Good ToO observing strategies to trade off between area and depth are neither simple nor obvious. We present an optimal strategy for GW follow-up with UVEX in which exposure time is adjusted dynamically for each field individually to maximize the overall probability of detection. We model the scheduling problem using the expressive and powerful mathematical framework of mixed integer linear programming (MILP), and employ a state-of-the-art MILP solver to automatically generate observing plan timelines that achieve high probabilities of kilonova detection. We have implemented this strategy in an open-source astronomical scheduling software package called the Multi-Mission Multi-Messenger Observation Planning Toolkit (M4OPT), on GitHub at https://github.com/m4opt/m4opt.
Subhalo abundance matching (SHAM) is widely used for connecting galaxies to dark matter haloes. In SHAM, galaxies and (sub-)haloes are sorted according to their mass (or mass proxy) and matched by their rank order. In this work, we show that SHAM is the solution of the optimal transport (OT) problem on empirical distributions (samples or catalogues) for any metric transport cost function. In the limit of large number of samples, it converges to the solution of the OT problem between continuous distributions. We propose SHAM-OT: a formulation of abundance matching where the halo-galaxy relation is obtained as the optimal transport plan between galaxy and halo mass functions. By working directly on these (discretized) functions, SHAM-OT eliminates the need for sampling or sorting and is solved using efficient OT algorithms at negligible compute and memory cost. Scatter in the galaxy-halo relation can be naturally incorporated through regularization of the transport plan. SHAM-OT can easily be generalized to multiple marginal distributions. We validate our method using analytical tests with varying cosmology and luminosity function parameters, and on simulated halo catalogues. The efficiency of SHAM-OT makes it particularly advantageous for Bayesian inference that requires marginalization over stellar mass or luminosity function uncertainties.
Humans naturally integrate vision and haptics for robust object perception during manipulation. The loss of either modality significantly degrades performance. Inspired by this multisensory integration, prior object pose estimation research has attempted to combine visual and haptic/tactile feedback. Although these works demonstrate improvements in controlled environments or synthetic datasets, they often underperform vision-only approaches in real-world settings due to poor generalization across diverse grippers, sensor layouts, or sim-to-real environments. Furthermore, they typically estimate the object pose for each frame independently, resulting in less coherent tracking over sequences in real-world deployments. To address these limitations, we introduce a novel unified haptic representation that effectively handles multiple gripper embodiments. Building on this representation, we introduce a new visuo-haptic transformer-based object pose tracker that seamlessly integrates visual and haptic input. We validate our framework in our dataset and the Feelsight dataset, demonstrating significant performance improvement on challenging sequences. Notably, our method achieves superior generalization and robustness across novel embodiments, objects, and sensor types (both taxel-based and vision-based tactile sensors). In real-world experiments, we demonstrate that our approach outperforms state-of-the-art visual trackers by a large margin. We further show that we can achieve precise manipulation tasks by incorporating our real-time object tracking result into motion plans, underscoring the advantages of visuo-haptic perception. Our model and dataset will be made open source upon acceptance of the paper. Project website: https://lhy.xyz/projects/v-hop/
Search and rescue (SAR) missions require reliable search methods to locate survivors, especially in challenging or inaccessible environments. This is why introducing unmanned aerial vehicles (UAVs) can be of great help to enhance the efficiency of SAR missions while simultaneously increasing the safety of everyone involved in the mission. Motivated by this, we design and experiment with autonomous UAV search for humans in a Mediterranean karst environment. The UAVs are directed using Heat equation-driven area coverage (HEDAC) ergodic control method according to known probability density and detection function. The implemented sensing framework consists of a probabilistic search model, motion control system, and computer vision object detection. It enables calculation of the probability of the target being detected in the SAR mission, and this paper focuses on experimental validation of proposed probabilistic framework and UAV control. The uniform probability density to ensure the even probability of finding the targets in the desired search area is achieved by assigning suitably thought-out tasks to 78 volunteers. The detection model is based on YOLO and trained with a previously collected ortho-photo image database. The experimental search is carefully planned and conducted, while as many parameters as possible are recorded. The thorough analysis consists of the motion control system, object detection, and the search validation. The assessment of the detection and search performance provides strong indication that the designed detection model in the UAV control algorithm is aligned with real-world results.
This paper analyzes the time-dependent relationship between the mean and variance of travel time on a single corridor under rush hour like congestion patterns. To model this phenomenon, we apply the LWR ((Lighthill & Whitham, 1955), (Richards, 1956)) theory on a homogenous freeway with a discontinuous bottleneck at its downstream end, assuming a uni-modal demand profile with a stochastic peak. We establish conditions for typical counterclockwise hysteresis loops under these assumptions. It is demonstrated that shapes of the fundamental diagram which always produce a counterclockwise loop can be interpreted as an indication of aggressive driving behavior, while deviations may occur under defensive driving. This classification enables a detailed explanation of the qualitative physical mechanisms behind this pattern, as well as an analysis of the causes for quantitatively limited deviations. Some of the mathematical properties of the LWR model identified in our analysis have not yet been addressed in the literature and we critically examine the extent to which these reflect actual traffic flow behavior. Our considerations are supported by numerical experiments. The obtained results aim to improve the fundamental understanding of the physical causes of this hysteresis pattern and to facilitate its better estimation in traffic planning and control.
The integration of Digital Twins with Extended Reality technologies, such as Virtual Reality and Augmented Reality, is transforming industries by enabling more immersive, interactive experiences and enhancing real time decision making. User centered evaluations are crucial for aligning XR enhanced DT systems with user expectations, enhancing acceptance and utility in real world settings. This paper proposes a user centric evaluation method for XR enhanced DT applications to assess usability, cognitive load, and user experience. By employing a range of assessment tools, including questionnaires and observational studies across various use cases, such as virtual tourism, city planning, and industrial maintenance, this method provides a structured approach to capturing the users perspective.
Next-generation touristic services will rely on the advanced mobile networks' high bandwidth and low latency and the Multi-access Edge Computing (MEC) paradigm to provide fully immersive mobile experiences. As an integral part of travel planning systems, recommendation algorithms devise personalized tour itineraries for individual users considering the popularity of a city's Points of Interest (POIs) as well as the tourist preferences and constraints. However, in the context of next-generation touristic services, recommendation algorithms should also consider the applications (e.g., social network, mobile video streaming, mobile augmented reality) the tourist will consume in the POIs and the quality in which the MEC infrastructure will deliver such applications. In this paper, we address the joint problem of recommending personalized tour itineraries for tourists and efficiently allocating MEC resources for advanced touristic applications. We formulate an optimization problem that maximizes the itinerary of individual tourists while optimizing the resource allocation at the network edge. We then propose an exact algorithm that quickly solves the problem optimally, considering instances of realistic size. Using a real-world location-based photo-sharing database, we conduct and present an exploratory analysis to understand preferences and users' visiting patterns. Using this understanding, we propose a methodology to identify user interest in applications. Finally, we evaluate our algorithm using this dataset. Results show that our algorithm outperforms a modified version of a state-of-the-art solution for personalized tour itinerary recommendation, demonstrating gains up to 11% for resource allocation efficiency and 40% for user experience. In addition, our algorithm performs similarly to the modified state-of-the-art solution regarding traditional itinerary recommendation metrics.
Recently, a first-of-its-kind operating system for programmable quantum network nodes was developed, called QNodeOS. Here, we present an extension of QNodeOS called Qoala, which introduces (1) a unified program format for hybrid interactive classical-quantum programs, providing a well-defined target for compilers, and (2) a runtime representation of a program that allows joint scheduling of the hybrid classical-quantum program, multitasking, and asynchronous program execution. Based on concrete design considerations, we put forward the architecture of Qoala, including the program structure and execution mechanism. We implement Qoala in the form of a modular and extendible simulator that is validated against real-world quantum network hardware (available online). However, Qoala is not meant to be purely a simulator, and implementation is planned on real hardware. We evaluate Qoala's effectiveness and performance sensitivity to latencies and network schedules using an extensive simulation study. Qoala provides a framework that opens the door for future computer science research into quantum network applications, including scheduling algorithms and compilation strategies that can now readily be explored using the framework and tools provided.
This study investigates the network characteristics of high-frequency (HF) and low-frequency (LF) travelers in urban public transport systems by analyzing 20 million smart card records from Beijing's transit network. A novel methodology integrates advanced data preprocessing, clustering techniques, and complex network analysis to differentiate HF and LF passenger behaviors and their impacts on network structure, robustness, and efficiency. The primary challenge is accurately segmenting and modeling the behaviors of diverse passenger groups within a large-scale, noisy dataset while maintaining computational efficiency and scalability. HF networks, representing the top 25% of travelers by usage frequency, exhibit high connectivity with an average clustering coefficient of 0.72 and greater node degree centrality. However, they have lower robustness, with efficiency declining by 35% under targeted disruptions and longer average path lengths of 6.2 during peak hours. In contrast, LF networks, which include 75% of travelers, are more dispersed yet resilient, with efficiency declining by only 10% under similar disruptions and stronger intracommunity connectivity. Temporal analysis reveals that HF passengers significantly contribute to peak-hour congestion, with 57.4% of HF trips occurring between 6:00 and 10:00 AM, while LF passengers show a broader temporal distribution, helping to mitigate congestion hotspots. Understanding these travel patterns is crucial for optimizing public transit systems. The findings suggest targeted strategies such as enhancing robustness in HF networks by diversifying key routes and improving accessibility in LF-dominated areas. This research provides a scalable framework for analyzing smart card data and offers actionable insights for optimizing transit networks, improving congestion management, and advancing sustainable urban mobility planning.
The increasing complexity and scale of modern telecommunications networks demand intelligent automation to enhance efficiency, adaptability, and resilience. Agentic AI has emerged as a key paradigm for intelligent communications and networking, enabling AI-driven agents to perceive, reason, decide, and act within dynamic networking environments. However, effective decision-making in telecom applications, such as network planning, management, and resource allocation, requires integrating retrieval mechanisms that support multi-hop reasoning, historical cross-referencing, and compliance with evolving 3GPP standards. This article presents a forward-looking perspective on generative information retrieval-inspired intelligent communications and networking, emphasizing the role of knowledge acquisition, processing, and retrieval in agentic AI for telecom systems. We first provide a comprehensive review of generative information retrieval strategies, including traditional retrieval, hybrid retrieval, semantic retrieval, knowledge-based retrieval, and agentic contextual retrieval. We then analyze their advantages, limitations, and suitability for various networking scenarios. Next, we present a survey about their applications in communications and networking. Additionally, we introduce an agentic contextual retrieval framework to enhance telecom-specific planning by integrating multi-source retrieval, structured reasoning, and self-reflective validation. Experimental results demonstrate that our framework significantly improves answer accuracy, explanation consistency, and retrieval efficiency compared to traditional and semantic retrieval methods. Finally, we outline future research directions.
We study random matrices with independent subgaussian columns. Assuming each column has a fixed Euclidean norm, we establish conditions under which such matrices act as near-isometries when restricted to a given subset of their domain. We show that, with high probability, the maximum distortion caused by such a matrix is proportional to the Gaussian complexity of the subset, scaled by the subgaussian norm of the matrix columns. This linear dependence on the subgaussian norm is a new phenomenon, as random matrices with independent rows or independent entries typically exhibit superlinear dependence. As a consequence, normalizing the columns of random sparse matrices leads to stronger embedding guarantees.
E-scooters are becoming a popular means of urban transportation. However, this increased popularity brings challenges, such as road accidents and conflicts when sharing space with traditional transport modes. An in-depth understanding of e-scooter rider behaviour is crucial for ensuring rider safety, guiding infrastructure planning, and enforcing traffic rules. This study investigated the rider behaviour through a naturalistic study with 23 participants equipped with a bike computer, eye-tracking glasses and cameras. They followed a pre-determined route, enabling multi-modal data collection. We analysed and compared gaze movements, speed, and video feeds across three transport infrastructure types: a pedestrian-shared path, a cycle lane and a roadway. Our findings reveal unique challenges e-scooter riders face, including difficulty keeping up with cyclists and motor vehicles due to speed limits on shared e-scooters, risks in signalling turns due to control lose, and limited acceptance in mixed-use spaces. The cycle lane showed the highest average speed, the least speed change points, and the least head movements, supporting its suitability as dedicated infrastructure for e-scooters. These findings are facilitated through multimodal sensing and analysing the e-scooter riders' ego-centric view, which show the efficacy of our method in discovering the behavioural dynamics of the riders in the wild. Our study highlights the critical need to align infrastructure with user behaviour to improve safety and emphasises the importance of targeted safety measures and regulations, especially when e-scooter riders share spaces with pedestrians or motor vehicles. The dataset and analysis code are available at https://github.com/HiruniNuwanthika/Electric-Scooter-Riders-Multi-Modal-Data-Analysis.git.
Recent advances in multimodal Human-Robot Interaction (HRI) datasets emphasize the integration of speech and gestures, allowing robots to absorb explicit knowledge and tacit understanding. However, existing datasets primarily focus on elementary tasks like object pointing and pushing, limiting their applicability to complex domains. They prioritize simpler human command data but place less emphasis on training robots to correctly interpret tasks and respond appropriately. To address these gaps, we present the NatSGLD dataset, which was collected using a Wizard of Oz (WoZ) method, where participants interacted with a robot they believed to be autonomous. NatSGLD records humans' multimodal commands (speech and gestures), each paired with a demonstration trajectory and a Linear Temporal Logic (LTL) formula that provides a ground-truth interpretation of the commanded tasks. This dataset serves as a foundational resource for research at the intersection of HRI and machine learning. By providing multimodal inputs and detailed annotations, NatSGLD enables exploration in areas such as multimodal instruction following, plan recognition, and human-advisable reinforcement learning from demonstrations. We release the dataset and code under the MIT License at https://www.snehesh.com/natsgld/ to support future HRI research.
Solving complex long-horizon robotic manipulation problems requires sophisticated high-level planning capabilities, the ability to reason about the physical world, and reactively choose appropriate motor skills. Vision-language models (VLMs) pretrained on Internet data could in principle offer a framework for tackling such problems. However, in their current form, VLMs lack both the nuanced understanding of intricate physics required for robotic manipulation and the ability to reason over long horizons to address error compounding issues. In this paper, we introduce a novel test-time computation framework that enhances VLMs' physical reasoning capabilities for multi-stage manipulation tasks. At its core, our approach iteratively improves a pretrained VLM with a "reflection" mechanism - it uses a generative model to imagine future world states, leverages these predictions to guide action selection, and critically reflects on potential suboptimalities to refine its reasoning. Experimental results demonstrate that our method significantly outperforms several state-of-the-art commercial VLMs as well as other post-training approaches such as Monte Carlo Tree Search (MCTS). Videos are available at https://reflect-vlm.github.io.
Centralized electronic health record repositories are critical for advancing disease surveillance, public health research, and evidence-based policymaking. However, developing countries face persistent challenges in achieving this due to fragmented healthcare data sources, inconsistent record-keeping practices, and the absence of standardized patient identifiers, limiting reliable record linkage, compromise data interoperability, and limit scalability-obstacles exacerbated by infrastructural constraints and privacy concerns. To address these barriers, this study proposes a scalable, privacy-preserving clinical data warehouse, NCDW, designed for heterogeneous EHR integration in resource-limited settings and tested with 1.16 million clinical records. The framework incorporates a wrapper-based data acquisition layer for secure, automated ingestion of multisource health data and introduces a soundex algorithm to resolve patient identity mismatches in the absence of unique IDs. A modular data mart is designed for disease-specific analytics, demonstrated through a dengue fever case study in Bangladesh, integrating clinical, demographic, and environmental data for outbreak prediction and resource planning. Quantitative assessment of the data mart underscores its utility in strengthening national decision-support systems, highlighting the model's adaptability for infectious disease management. Comparative evaluation of database technologies reveals NoSQL outperforms relational SQL by 40-69% in complex query processing, while system load estimates validate the architecture's capacity to manage 19 million daily records (34TB over 5 years). The framework can be adapted to various healthcare settings across developing nations by modifying the ingestion layer to accommodate standards like ICD-11 and HL7 FHIR, facilitating interoperability for managing infectious diseases (i.e., COVID, tuberculosis).
Planning with options -- a sequence of primitive actions -- has been shown effective in reinforcement learning within complex environments. Previous studies have focused on planning with predefined options or learned options through expert demonstration data. Inspired by MuZero, which learns superhuman heuristics without any human knowledge, we propose a novel approach, named OptionZero. OptionZero incorporates an option network into MuZero, providing autonomous discovery of options through self-play games. Furthermore, we modify the dynamics network to provide environment transitions when using options, allowing searching deeper under the same simulation constraints. Empirical experiments conducted in 26 Atari games demonstrate that OptionZero outperforms MuZero, achieving a 131.58% improvement in mean human-normalized score. Our behavior analysis shows that OptionZero not only learns options but also acquires strategic skills tailored to different game characteristics. Our findings show promising directions for discovering and using options in planning. Our code is available at https://rlg.iis.sinica.edu.tw/papers/optionzero.
Vehicle-to-everything technologies (V2X) have become an ideal paradigm to extend the perception range and see through the occlusion. Exiting efforts focus on single-frame cooperative perception, however, how to capture the temporal cue between frames with V2X to facilitate the prediction task even the planning task is still underexplored. In this paper, we introduce the Co-MTP, a general cooperative trajectory prediction framework with multi-temporal fusion for autonomous driving, which leverages the V2X system to fully capture the interaction among agents in both history and future domains to benefit the planning. In the history domain, V2X can complement the incomplete history trajectory in single-vehicle perception, and we design a heterogeneous graph transformer to learn the fusion of the history feature from multiple agents and capture the history interaction. Moreover, the goal of prediction is to support future planning. Thus, in the future domain, V2X can provide the prediction results of surrounding objects, and we further extend the graph transformer to capture the future interaction among the ego planning and the other vehicles' intentions and obtain the final future scenario state under a certain planning action. We evaluate the Co-MTP framework on the real-world dataset V2X-Seq, and the results show that Co-MTP achieves state-of-the-art performance and that both history and future fusion can greatly benefit prediction.
Heart failure is one of the leading causes of death worldwide, with millons of deaths each year, according to data from the World Health Organization (WHO) and other public health agencies. While significant progress has been made in the field of heart failure, leading to improved survival rates and improvement of ejection fraction, there remains substantial unmet needs, due to the complexity and multifactorial characteristics. Therefore, we propose a composable strategy framework for assessment and treatment optimization in heart failure. This framework simulates the doctor-patient consultation process and leverages multi-modal algorithms to analyze a range of data, including video, physical examination, text results as well as medical history. By integrating these various data sources, our framework offers a more holistic evaluation and optimized treatment plan for patients. Our results demonstrate that this multi-modal approach outperforms single-modal artificial intelligence (AI) algorithms in terms of accuracy in heart failure (HF) prognosis prediction. Through this method, we can further evaluate the impact of various pathological indicators on HF prognosis,providing a more comprehensive evaluation.
We consider multi-robot systems under recurring tasks formalized as linear temporal logic (LTL) specifications. To solve the planning problem efficiently, we propose a bottom-up approach combining offline plan synthesis with online coordination, dynamically adjusting plans via real-time communication. To address action delays, we introduce a synchronization mechanism ensuring coordinated task execution, leading to a multi-agent coordination and synchronization framework that is adaptable to a wide range of multi-robot applications. The software package is developed in Python and ROS2 for broad deployment. We validate our findings through lab experiments involving nine robots showing enhanced adaptability compared to previous methods. Additionally, we conduct simulations with up to ninety agents to demonstrate the reduced computational complexity and the scalability features of our work.
China plans to launch a probe (Tianwen-2) around 2025, mainly for exploring the near-Earth asteroid 2016 HO3 . The mission involves close-range exploration, landing, and mining operations that require three-dimensional modeling of the asteroid, which requires prior knowledge of its material composition and uniformity. This information is crucial in progressive or ground exploration processes. Our research focuses on high-precision intelligent inversion of complex physical properties of asteroids based on spectral data, providing support for further analysis of aster oid materials, density, and structure. We have developed a platform for asteroid spectral classification, albedo estimation, and composition analysis, which includes three types of neural networks based on Transformer attention mechanism: One for spectral classification, achieving a four-class classification accuracy of 97.28% and an eleven-class classification accuracy of 95.69%; second one for albedo estimation, with an average absolute error of 0.0308 in S-type asteroid albedo estimation, and the third one for composition analysis, with a predicted spectral angular distance of only 0.0340 and a root mean square error of 0.1759 for the abundance of end members. These results indicate that our network can provide high-precision asteroid spectral classification, albedo estimation, and composition analysis results. In addition, we utilized the platform to analyze and provide results for six asteroids.
Unmanned Aerial Vehicles (UAVs) in Wireless Power Transfer (WPT)-assisted Internet of Things (IoT) systems face the following challenges: limited resources and suboptimal trajectory planning. Reinforcement learning-based trajectory planning schemes face issues of low search efficiency and learning instability when optimizing large-scale systems. To address these issues, we present an Attention-based UAV Trajectory Optimization (AUTO) framework based on the graph transformer, which consists of an Attention Trajectory Optimization Model (ATOM) and a Trajectory lEarNing Method based on Actor-critic (TENMA). In ATOM, a graph encoder is used to calculate the self-attention characteristics of all IoTDs, and a trajectory decoder is developed to optimize the number and trajectories of UAVs. TENMA then trains the ATOM using an improved Actor-Critic method, in which the real reward of the system is applied as the baseline to reduce variances in the critic network. This method is suitable for high-quality and large-scale multi-UAV trajectory planning. Finally, we develop numerous experiments, including a hardware experiment in the field case, to verify the feasibility and efficiency of the AUTO framework.
We investigate the small regularization limit of entropic optimal transport when the cost function is the Euclidean distance in dimensions $d > 1$, and the marginal measures are absolutely continuous with respect to the Lebesgue measure. Our results establish that the limiting optimal transport plan is supported on transport rays. Furthermore, within each transport ray, the limiting transport plan uniquely minimizes a relative entropy functional with respect to specific reference measures supported on the rays. This provides a complete and unique characterization of the limiting transport plan. While similar results have been obtained for $d = 1$ in \cite{Marino} and for discrete measures in \cite{peyr\'e2020computationaloptimaltransport}, this work resolves the previously open case in higher dimensions $d>1.$
As the number of electric vehicles (EVs) continues to grow, the demand for charging stations is also increasing, leading to challenges such as long wait times and insufficient infrastructure. High-precision forecasting of EV charging demand is crucial for efficient station management, to address some of these challenges. This paper presents an approach to predict the charging demand at 15-minute intervals for the day ahead using a multivariate long short-term memory (LSTM) network with an attention mechanism. Additionally, the model leverages explainable AI techniques to evaluate the influence of various factors on the predictions, including weather conditions, day of the week, month, and any holiday. SHapley Additive exPlanations (SHAP) are used to quantify the contribution of each feature to the final forecast, providing deeper insights into how these factors affect prediction accuracy. As a result, the framework offers enhanced decision-making for infrastructure planning. The efficacy of the proposed method is demonstrated by simulations using the test data collected from the EV charging stations at California State University, Long Beach.
As the developed world replaces Defined Benefit (DB) pension plans with Defined Contribution (DC) plans, there is a need to develop decumulation strategies for DC plan holders. Optimal decumulation can be viewed as a problem in optimal stochastic control. Formulation as a control problem requires specification of an objective function, which in turn requires a definition of reward and risk. An intuitive specification of reward is the total withdrawals over the retirement period. Most retirees view risk as the possibility of running out of savings. This paper investigates several possible left tail risk measures, in conjunction with DC plan decumulation. The risk measures studied include (i) expected shortfall (ii) linear shortfall and (iii) probability of shortfall. We establish that, under certain assumptions, the set of optimal controls associated with all expected reward and expected shortfall Pareto efficient frontier curves is identical to the set of optimal controls for all expected reward and linear shortfall Pareto efficient frontier curves. Optimal efficient frontiers are determined computationally for each risk measure, based on a parametric market model. Robustness of these strategies is determined by testing the strategies out-of-sample using block bootstrapping of historical data.
Each year, nearly 13,000 eviction orders are issued in Cook County, Illinois. While most of these orders have an enforcement deadline, a portion does not. The Cook County Sheriff's Office (CCSO) is responsible for enforcing these orders, which involves selecting the orders to prioritize and planning daily enforcement routes. This task presents a challenge: balancing "equity" (i.e., prioritizing orders that have been waiting longer) with "efficiency" (i.e., maximizing the number of orders served). Although the current CCSO policy is highly efficient, a significant fraction of eviction orders miss their deadline. Motivated by the CCSO's operations, we study a model of eviction enforcement planning and propose a policy that dynamically prioritizes orders based on their type (deadline or no deadline), location, and waiting time. Our approach employs a budgeted prize-collecting vehicle routing problem (VRP) for daily planning, where the "prizes" are determined by solving a stochastic control problem. This stochastic control problem, which relies on the VRP for determining feasible actions at each decision point, is high-dimensional due to its spatial nature, leading to the curse of dimensionality. We overcome this challenge by building on recent advances in high-dimensional stochastic control using deep neural networks. We compare the performance of our proposed policy with two practical benchmark policies, including one that mimics the current CCSO policy, using data from CCSO. Similar to the CCSO policy, our proposed policy leads to efficient resource utilization, but it also reduces the percentage of orders that miss their deadline by 72.38% without degrading the overall service effort for either type of orders. In a counterfactual study, we show that increasing the service capacity or extending the enforcement deadline further reduces the fraction of orders missing their deadline.
Objective: Spatiotemporal optimization in radiation therapy involves determining the optimal number of dose delivery fractions (temporal) and the optimal dose per fraction (spatial). Traditional approaches focus on maximizing the biologically effective dose (BED) to the target while constraining BED to organs-at-risk (OAR), which may lead to insufficient BED for complete tumor cell kill. This work proposes a formulation that ensures adequate BED delivery to the target while minimizing BED to the OAR. Approach: A spatiotemporal optimization model is developed that incorporates an inequality constraint to guarantee sufficient BED for tumor cell kill while minimizing BED to the OAR. The model accounts for tumor proliferation dynamics, including lag time (delay before proliferation begins) and doubling time (time for tumor volume to double), to optimize dose fractionation. Results: The performance of our formulation is evaluated for varying lag and doubling times. The results show that mean BED to the target consistently meets the minimum requirement for tumor cell kill. Additionally, the mean BED to OAR varies based on tumor proliferation dynamics. In the prostate case with lag time of 7 days and doubling time of 2 days, it is observed that mean BED delivered to femoral head is lowest at around 20 fractions, making this an optimal choice. While in the head-and-neck case, mean BED to OAR decreases as the number of fractions increases, suggesting that a higher number of fractions is optimal. Significance: A spatiotemporal optimization model is presented that minimizes BED to the OAR while ensuring sufficient BED for tumor cell kill. By incorporating tumor lag and doubling time, the approach identifies optimal number of fractions. This model can be extended to support hyperfractionation or accelerated fractionation strategies, offering a versatile tool for clinical treatment planning.
Purpose: LATTICE, a form of spatially fractionated radiation therapy that delivers high-dose peaks and low-dose valleys within the target, has been clinically utilized for treating bulky tumors. However, its application to small-to-medium-sized target remains challenging due to beam size limitations. To address this challenge, this work proposes a novel proton LATTICE (pLATTICE) modality using minibeams, namely minibeam-pLATTICE, that extends LATTICE approach for small-to-medium targets. Methods: Three minibeam-pLATTICE methods are introduced. (1) M0: a fixed minibeam orientation for all beam angles; (2) M1: alternated minibeam orientations, for consecutive beam angles; (3) M2: multiple minibeam orientations for each beam angle. For each minibeam-pLATTICE method, an optimization problem is formulated to optimize dose uniformity in target peaks and valleys, as well as dose-volume-histogram-based objectives. This problem is solved using iterative convex relaxation and alternating direction method of multipliers. Results: Three minibeam-pLATTICE methods are validated to demonstrate the feasibility of minibeam-pLATTICE for head-and-neck cases. The advantages of this modality over conventional beam (CONV) pLATTICE are evaluated by comparing peak-to-valley dose ratio (PVDR) and dose delivered to organs at risk (OAR). All three minibeam-pLATTICE modalities achieved improved plan quality compared to CONV, with M2 yielding the best results. For example, in terms of PVDR, M2=5.89, compared to CONV=4.13, M0=4.87 and M1=4.7. Conclusion: A novel minibeam-pLATTICE modality is proposed that generates lattice dose patterns for small-to-medium targets, which are not achievable with conventional pLATTICE due to beam size limitations.
Background: Multi-collimator proton minibeam radiation therapy (MC-pMBRT) has recently emerged as a versatile technique for dose shaping, enabling peak-valley dose patterns in organs-at-risk (OAR) while maintaining a uniform dose distribution in tumor. MC-pMBRT leverages a set of generic multi-slit collimators (MSC) with varying center-to-center distances. However, the current method for minibeam aperture optimization (MAO), i.e., the selection of MSC per beam angle, is manual and heuristic, resulting in computational inefficiencies and no guarantee of optimality. This work introduces a novel mixed integer programming (MIP) approach to MAO for optimizing MC-pMBRT plan quality. Methods: The proposed MIP approach jointly optimizes dose distributions, peak-to-valley dose ratio (PVDR), and selects the optimal set of MSC per beam angle. The optimization problem includes decision variables for MSC selection per beam angle and spot weights. The proposed MIP approach is a two-step process: Step1: the binary variables are optimally determined to select MSC for each beam angle; Step 2: the continuous variables are solved to determine the spot weights. Both steps utilize iterative convex relaxation and the alternating direction method of multipliers to solve the problems. Results: The proposed MIP method for MAO (MIP-MAO) was validated against the conventional heuristic method (CONV) for MC-pMBRT treatment planning. Results indicate that MIP-MAO enhances the conformity index (CI) for the target and improves PVDR for OAR. For instance, in a head-and-neck case, CI improved from 0.61 (CONV) to 0.70 (MIP-MAO); in an abdomen case, CI improved from 0.78 (CONV) to 0.83 (MIP-MAO). Additionally, MIP-MAO reduced mean doses in the body and OAR. Conclusions: A novel MIP approach for MAO in MC-pMBRT is presented, showing demonstrated improvements in plan quality and PVDR compared to the heuristic method.
Epilepsy is a neurological disorder characterized by seizures and epileptic events intertwined with religious and personal beliefs since prehistoric times. This review paper explores the historical context and challenges in defining epilepsy. The formal definition was established twenty years ago, and the multifaceted causes of this neurological disorder. It aims to pave the way for personalised therapeutic strategies, research advancements, and informed public health planning to enhance the lives of those affected by this complex neurological condition. In addition, this review paper focuses on the mechanisms and etiologies of epileptogenesis, categorizing them by mechanisms and the underlying causes of the disorder. The review paper provides a brief overview of the current state of the art in the diagnosis, diagnosis, treatment, and treatment of epileptiform seizures.
This paper presents a motion-coupled mapping algorithm for contour mapping of hybrid rice canopies, specifically designed for Agricultural Unmanned Ground Vehicles (Agri-UGV) navigating complex and unknown rice fields. Precise canopy mapping is essential for Agri-UGVs to plan efficient routes and avoid protected zones. The motion control of Agri-UGVs, tasked with impurity removal and other operations, depends heavily on accurate estimation of rice canopy height and structure. To achieve this, the proposed algorithm integrates real-time RGB-D sensor data with kinematic and inertial measurements, enabling efficient mapping and proprioceptive localization. The algorithm produces grid-based elevation maps that reflect the probabilistic distribution of canopy contours, accounting for motion-induced uncertainties. It is implemented on a high-clearance Agri-UGV platform and tested in various environments, including both controlled and dynamic rice field settings. This approach significantly enhances the mapping accuracy and operational reliability of Agri-UGVs, contributing to more efficient autonomous agricultural operations.
Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods for these tasks either perform task-level verification without considering constraints or apply inference-time algorithms without adapting to instance-level complexity. To address these limitations, we propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents. Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms--Best of N, Tree-of-Thought, and REBASE. In PlanGEN framework, the selection agent optimizes algorithm choice based on instance complexity, ensuring better adaptability to complex planning problems. Experimental results demonstrate significant improvements over the strongest baseline across multiple benchmarks, achieving state-of-the-art results on NATURAL PLAN ($\sim$8%$\uparrow$), OlympiadBench ($\sim$4%$\uparrow$), DocFinQA ($\sim$7%$\uparrow$), and GPQA ($\sim$1%$\uparrow$). Our key finding highlights that constraint-guided iterative verification improves inference-time algorithms, and adaptive selection further boosts performance on complex planning and reasoning problems.
We consider the problem of exact recovery of a $k$-sparse binary vector from generalized linear measurements (such as logistic regression). We analyze the linear estimation algorithm (Plan, Vershynin, Yudovina, 2017), and also show information theoretic lower bounds on the number of required measurements. As a consequence of our results, for noisy one bit quantized linear measurements ($\mathsf{1bCSbinary}$), we obtain a sample complexity of $O((k+\sigma^2)\log{n})$, where $\sigma^2$ is the noise variance. This is shown to be optimal due to the information theoretic lower bound. We also obtain tight sample complexity characterization for logistic regression. Since $\mathsf{1bCSbinary}$ is a strictly harder problem than noisy linear measurements ($\mathsf{SparseLinearReg}$) because of added quantization, the same sample complexity is achievable for $\mathsf{SparseLinearReg}$. While this sample complexity can be obtained via the popular lasso algorithm, linear estimation is computationally more efficient. Our lower bound holds for any set of measurements for $\mathsf{SparseLinearReg}$, (similar bound was known for Gaussian measurement matrices) and is closely matched by the maximum-likelihood upper bound. For $\mathsf{SparseLinearReg}$, it was conjectured in Gamarnik and Zadik, 2017 that there is a statistical-computational gap and the number of measurements should be at least $(2k+\sigma^2)\log{n}$ for efficient algorithms to exist. It is worth noting that our results imply that there is no such statistical-computational gap for $\mathsf{1bCSbinary}$ and logistic regression.
In this paper, we propose a model-based contact-aware motion planner for autonomous navigation of neuroendovascular tools in acute ischemic stroke. The planner is designed to find the optimal control strategy for telescopic pre-bent catheterization tools such as guidewire and catheters, currently used for neuroendovascular procedures. A kinematic model for the telescoping tools and their interaction with the surrounding anatomy is derived to predict tools steering. By leveraging geometrical knowledge of the anatomy, obtained from pre-operative segmented 3D images, and the mechanics of the telescoping tools, the planner finds paths to the target enabled by interacting with the surroundings. We propose an actuation platform for insertion and rotation of the telescopic tools and present experimental results for the navigation from the base of the descending aorta to the LCCA. We demonstrate that, by leveraging the pre-operative plan, we can consistently navigate the LCCA with 100% success of over 50 independent trials. We also study the robustness of the planner towards motion of the aorta and errors in the initial positioning of the robotic tools. The proposed plan can successfully reach the LCCA for rotations of the aorta of up to 10{\deg}, and displacement of up to 10mm, on the coronal plane.
Planning paths that maximize information gain for robotic platforms has wide-ranging applications and significant potential impact. To effectively adapt to real-time data collection, informative path planning must be computed online and be responsive to new observations. In this work, we present IA-TIGRIS, an incremental and adaptive sampling-based informative path planner that can be run efficiently with onboard computation. Our approach leverages past planning efforts through incremental refinement while continuously adapting to updated world beliefs. We additionally present detailed implementation and optimization insights to facilitate real-world deployment, along with an array of reward functions tailored to specific missions and behaviors. Extensive simulation results demonstrate IA-TIGRIS generates higher-quality paths compared to baseline methods. We validate our planner on two distinct hardware platforms: a hexarotor UAV and a fixed-wing UAV, each having unique motion models and configuration spaces. Our results show up to a 41% improvement in information gain compared to baseline methods, suggesting significant potential for deployment in real-world applications.
This paper explores the solutions for minimizing renewable energy (RE) curtailment in the Texas Electric Reliability Council of Texas (ERCOT) grid. By utilizing current and future planning data from ERCOT and the System Advisor Model from the National Renewable Energy Laboratory, we examine how future renewable energy (RE) initiatives, combined with utility-scale energy storage, can reduce CO2 emissions while reshaping Texas's energy mix. The study projects the energy landscape from 2023 to 2033, considering the planned phase-out of fossil fuel plants and the integration of new wind/solar projects. By comparing emissions under different load scenarios, with and without storage, we demonstrate storage's role in optimizing RE utilization. The findings of this paper provide actionable guidance for energy stakeholders, underscoring the need to expand wind and solar projects with strategic storage solutions to maximize Texas's RE capacity and substantially reduce CO2 emissions.
The increasing impact of human-induced climate change and unplanned urban constructions has increased flooding incidents in recent years. Accurate identification of flooded areas is crucial for effective disaster management and urban planning. While few works have utilized convolutional neural networks and transformer-based semantic segmentation techniques for identifying flooded areas from aerial footage, recent developments in graph neural networks have created improvement opportunities. This paper proposes an innovative approach, the Graph Attention Convolutional U-NET (GAC-UNET) model, based on graph neural networks for automated identification of flooded areas. The model incorporates a graph attention mechanism and Chebyshev layers into the U-Net architecture. Furthermore, this paper explores the applicability of transfer learning and model reprogramming to enhance the accuracy of flood area segmentation models. Empirical results demonstrate that the proposed GAC-UNET model, outperforms other approaches with 91\% mAP, 94\% dice score, and 89\% IoU, providing valuable insights for informed decision-making and better planning of future infrastructures in flood-prone areas.
The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be, unchecked AI agency poses significant risks to public safety and security, ranging from misuse by malicious actors to a potentially irreversible loss of human control. We discuss how these risks arise from current AI training methods. Indeed, various scenarios and experiments have demonstrated the possibility of AI agents engaging in deception or pursuing goals that were not specified by human operators and that conflict with human interests, such as self-preservation. Following the precautionary principle, we see a strong need for safer, yet still useful, alternatives to the current agency-driven trajectory. Accordingly, we propose as a core building block for further advances the development of a non-agentic AI system that is trustworthy and safe by design, which we call Scientist AI. This system is designed to explain the world from observations, as opposed to taking actions in it to imitate or please humans. It comprises a world model that generates theories to explain data and a question-answering inference machine. Both components operate with an explicit notion of uncertainty to mitigate the risks of overconfident predictions. In light of these considerations, a Scientist AI could be used to assist human researchers in accelerating scientific progress, including in AI safety. In particular, our system can be employed as a guardrail against AI agents that might be created despite the risks involved. Ultimately, focusing on non-agentic AI may enable the benefits of AI innovation while avoiding the risks associated with the current trajectory. We hope these arguments will motivate researchers, developers, and policymakers to favor this safer path.
To evaluate end-to-end autonomous driving systems, a simulation environment based on Novel View Synthesis (NVS) techniques is essential, which synthesizes photo-realistic images and point clouds from previously recorded sequences under new vehicle poses, particularly in cross-lane scenarios. Therefore, the development of a multi-lane dataset and benchmark is necessary. While recent synthetic scene-based NVS datasets have been prepared for cross-lane benchmarking, they still lack the realism of captured images and point clouds. To further assess the performance of existing methods based on NeRF and 3DGS, we present the first multi-lane dataset registering parallel scans specifically for novel driving view synthesis dataset derived from real-world scans, comprising 25 groups of associated sequences, including 16,000 front-view images, 64,000 surround-view images, and 16,000 LiDAR frames. All frames are labeled to differentiate moving objects from static elements. Using this dataset, we evaluate the performance of existing approaches in various testing scenarios at different lanes and distances. Additionally, our method provides the solution for solving and assessing the quality of multi-sensor poses for multi-modal data alignment for curating such a dataset in real-world. We plan to continually add new sequences to test the generalization of existing methods across different scenarios. The dataset is released publicly at the project page: https://nizqleo.github.io/paralane-dataset/.
Humanoid robots have great potential for real-world applications due to their ability to operate in environments built for humans, but their deployment is hindered by the challenge of controlling their underlying high-dimensional nonlinear hybrid dynamics. While reduced-order models like the Hybrid Linear Inverted Pendulum (HLIP) are simple and computationally efficient, they lose whole-body expressiveness. Meanwhile, recent advances in Contact-Implicit Model Predictive Control (CI-MPC) enable robots to plan through multiple hybrid contact modes, but remain vulnerable to local minima and require significant tuning. We propose a control framework that combines the strengths of HLIP and CI-MPC. The reduced-order model generates a nominal gait, while CI-MPC manages the whole-body dynamics and modifies the contact schedule as needed. We demonstrate the effectiveness of this approach in simulation with a novel 24 degree-of-freedom humanoid robot: Achilles. Our proposed framework achieves rough terrain walking, disturbance recovery, robustness under model and state uncertainty, and allows the robot to interact with obstacles in the environment, all while running online in real-time at 50 Hz.
Great novels create immersive worlds with rich character arcs, well-structured plots, and nuanced writing styles. However, current novel generation methods often rely on brief, simplistic story outlines and generate details using plain, generic language. To bridge this gap, we introduce the task of Pastiche Novel Generation, which requires the generated novels to imitate the distinctive features of the original work, including understanding character profiles, predicting plausible plot developments, and writing concrete details using vivid, expressive language. To achieve this, we propose WriterAgent, a novel generation system designed to master the core aspects of literary pastiche. WriterAgent is trained through a curriculum learning paradigm, progressing from low-level stylistic mastery to high-level narrative coherence. Its key tasks include language style learning, character modeling, plot planning, and stylish writing, ensuring comprehensive narrative control. To support this, WriterAgent leverages the WriterLoRA framework, an extension of LoRA with hierarchical and cumulative task-specific modules, each specializing in a different narrative aspect. We evaluate WriterAgent on multilingual classics like Harry Potter and Dream of the Red Chamber, demonstrating its superiority over baselines in capturing the target author's settings, character dynamics, and writing style to produce coherent, faithful narratives.
Probabilistic collision detection (PCD) is essential in motion planning for robots operating in unstructured environments, where considering sensing uncertainty helps prevent damage. Existing PCD methods mainly used simplified geometric models and addressed only position estimation errors. This paper presents an enhanced PCD method with two key advancements: (a) using superquadrics for more accurate shape approximation and (b) accounting for both position and orientation estimation errors to improve robustness under sensing uncertainty. Our method first computes an enlarged surface for each object that encapsulates its observed rotated copies, thereby addressing the orientation estimation errors. Then, the collision probability under the position estimation errors is formulated as a chance-constraint problem that is solved with a tight upper bound. Both the two steps leverage the recently developed normal parameterization of superquadric surfaces. Results show that our PCD method is twice as close to the Monte-Carlo sampled baseline as the best existing PCD method and reduces path length by 30% and planning time by 37%, respectively. A Real2Sim pipeline further validates the importance of considering orientation estimation errors, showing that the collision probability of executing the planned path in simulation is only 2%, compared to 9% and 29% when considering only position estimation errors or none at all.
Predicting seizure freedom is essential for tailoring epilepsy treatment. But accurate prediction remains challenging with traditional methods, especially with diverse patient populations. This study developed a deep learning-based graph neural network (GNN) model to predict seizure freedom from stereo electroencephalography (sEEG) data in patients with refractory epilepsy. We utilized high-quality sEEG data from 15 pediatric patients to train a deep learning model that can accurately predict seizure freedom outcomes and advance understanding of brain connectivity at the seizure onset zone. Our model integrates local and global connectivity using graph convolutions with multi-scale attention mechanisms to capture connections between difficult-to-study regions such as the thalamus and motor regions. The model achieved an accuracy of 92.4% in binary class analysis, 86.6% in patient-wise analysis, and 81.4% in multi-class analysis. Node and edge-level feature analysis highlighted the anterior cingulate and frontal pole regions as key contributors to seizure freedom outcomes. The nodes identified by our model were also more likely to coincide with seizure onset zones. Our findings underscore the potential of new connectivity-based deep learning models such as GNNs for enhancing the prediction of seizure freedom, predicting seizure onset zones, connectivity analysis of the brain during seizure, as well as informing AI-assisted personalized epilepsy treatment planning.
Join order optimization is critical in achieving good query performance. Despite decades of research and practice, modern query optimizers could still generate inferior join plans that are orders of magnitude slower than optimal. Existing research on robust query processing often lacks theoretical guarantees on join-order robustness while sacrificing query performance. In this paper, we rediscover the recent Predicate Transfer technique from a robustness point of view. We introduce two new algorithms, LargestRoot and SafeSubjoin, and then propose Robust Predicate Transfer (RPT) that is provably robust against arbitrary join orders of an acyclic query. We integrated Robust Predicate Transfer with DuckDB, a state-of-the-art analytical database, and evaluated against all the queries in TPC-H, JOB, and TPC-DS benchmarks. Our experimental results show that RPT improves join-order robustness by orders of magnitude compared to the baseline. With RPT, the largest ratio between the maximum and minimum execution time out of random join orders for a single acyclic query is only 1.6x (the ratio is close to 1 for most evaluated queries). Meanwhile, applying RPT also improves the end-to-end query performance by 1.5x (per-query geometric mean). We hope that this work sheds light on solving the practical join ordering problem.
Graph algorithms, such as shortest path finding, play a crucial role in enabling essential applications and services like infrastructure planning and navigation, making their correctness important. However, thoroughly testing graph algorithm implementations poses several challenges, including their vast input space (i.e., arbitrary graphs). Moreover, through our preliminary study, we find that just a few automatically generated graphs (less than 10) could be enough to cover the code of many graph algorithm implementations, rendering the code coverage-guided fuzzing approach -- one of the state-of-the-art search algorithms -- less efficient than expected. To tackle these challenges, we introduce GraphFuzz, the first automated feedback-guided fuzzing framework for graph algorithm implementations. Our key innovation lies in identifying lightweight and algorithm-specific feedback signals to combine with or completely replace the code coverage feedback to enhance the diversity of the test corpus, thereby speeding up the bug-finding process. This novel idea also allows GraphFuzz to effectively work in both black-box (i.e., no code coverage instrumentation/collection is required) and grey-box setups. GraphFuzz applies differential testing to detect both crash-triggering bugs and logic bugs. Our evaluation demonstrates the effectiveness of GraphFuzz. The tool has successfully discovered 12 previously unknown bugs, including 6 logic bugs, in 9 graph algorithm implementations in two popular graph libraries, NetworkX and iGraph. All of them have been confirmed and and 11 bugs have been rectified by the libraries' maintainers.
Effective resource management and environmental planning in regions with high climatic variability, such as Chile, demand advanced predictive tools. This study addresses this challenge by employing an innovative and computationally efficient hybrid methodology that integrates machine learning (ML) methods for time series forecasting with established statistical techniques. The spatiotemporal data undergo decomposition using time-dependent Empirical Orthogonal Functions (EOFs), denoted as \(\phi_{k}(t)\), and their corresponding spatial coefficients, \(\alpha_{k}(s)\), to reduce dimensionality. Wavelet analysis provides high-resolution time and frequency information from the \(\phi_{k}(t)\) functions, while neural networks forecast these functions within a medium-range horizon \(h\). By utilizing various ML models, particularly a Wavelet - ANN hybrid model, we forecast \(\phi_{k}(t+h)\) up to a time horizon \(h\), and subsequently reconstruct the spatiotemporal data using these extended EOFs. This methodology is applied to a grid of climate data covering the territory of Chile. It transitions from a high-dimensional multivariate spatiotemporal data forecasting problem to a low-dimensional univariate forecasting problem. Additionally, cluster analysis with Dynamic Time Warping for defining similarities between rainfall time series, along with spatial coherence and predictability assessments, has been instrumental in identifying geographic areas where model performance is enhanced. This approach also elucidates the reasons behind poor forecast performance in regions or clusters with low spatial coherence and predictability. By utilizing cluster medoids, the forecasting process becomes more practical and efficient. This compound approach significantly reduces computational complexity while generating forecasts of reasonable accuracy and utility.
Diffusion models excel at creating images and videos thanks to their multimodal generative capabilities. These same capabilities have made diffusion models increasingly popular in robotics research, where they are used for generating robot motion. However, the stochastic nature of diffusion models is fundamentally at odds with the precise dynamical equations describing the feasible motion of robots. Hence, generating dynamically admissible robot trajectories is a challenge for diffusion models. To alleviate this issue, we introduce DDAT: Diffusion policies for Dynamically Admissible Trajectories to generate provably admissible trajectories of black-box robotic systems using diffusion models. A sequence of states is a dynamically admissible trajectory if each state of the sequence belongs to the reachable set of its predecessor by the robot's equations of motion. To generate such trajectories, our diffusion policies project their predictions onto a dynamically admissible manifold during both training and inference to align the objective of the denoiser neural network with the dynamical admissibility constraint. The auto-regressive nature of these projections along with the black-box nature of robot dynamics render these projections immensely challenging. We thus enforce admissibility by iteratively sampling a polytopic under-approximation of the reachable set of a state onto which we project its predicted successor, before iterating this process with the projected successor. By producing accurate trajectories, this projection eliminates the need for diffusion models to continually replan, enabling one-shot long-horizon trajectory planning. We demonstrate that our framework generates higher quality dynamically admissible robot trajectories through extensive simulations on a quadcopter and various MuJoCo environments, along with real-world experiments on a Unitree GO1 and GO2.
Autonomous wire harness assembly requires robots to manipulate complex branched cables with high precision and reliability. A key challenge in automating this process is predicting how these flexible and branched structures behave under manipulation. Without accurate predictions, it is difficult for robots to reliably plan or execute assembly operations. While existing research has made progress in modeling single-threaded Deformable Linear Objects (DLOs), extending these approaches to Branched Deformable Linear Objects (BDLOs) presents fundamental challenges. The junction points in BDLOs create complex force interactions and strain propagation patterns that cannot be adequately captured by simply connecting multiple single-DLO models. To address these challenges, this paper presents Differentiable discrete branched Elastic rods for modeling Furcated DLOs in real-Time (DEFT), a novel framework that combines a differentiable physics-based model with a learning framework to: 1) accurately model BDLO dynamics, including dynamic propagation at junction points and grasping in the middle of a BDLO, 2) achieve efficient computation for real-time inference, and 3) enable planning to demonstrate dexterous BDLO manipulation. A comprehensive series of real-world experiments demonstrates DEFT's efficacy in terms of accuracy, computational speed, and generalizability compared to state-of-the-art alternatives. Project page:https://roahmlab.github.io/DEFT/.
A common problem when using model predictive control (MPC) in practice is the satisfaction of safety specifications beyond the prediction horizon. While theoretical works have shown that safety can be guaranteed by enforcing a suitable terminal set constraint or a sufficiently long prediction horizon, these techniques are difficult to apply and thus are rarely used by practitioners, especially in the case of general nonlinear dynamics. To solve this problem, we impose a tradeoff between exact recursive feasibility, computational tractability, and applicability to ''black-box'' dynamics by learning an approximate discrete-time control barrier function and incorporating it into a variational inference MPC (VIMPC), a sampling-based MPC paradigm. To handle the resulting state constraints, we further propose a new sampling strategy that greatly reduces the variance of the estimated optimal control, improving the sample efficiency, and enabling real-time planning on a CPU. The resulting Neural Shield-VIMPC (NS-VIMPC) controller yields substantial safety improvements compared to existing sampling-based MPC controllers, even under badly designed cost functions. We validate our approach in both simulation and real-world hardware experiments.
Over the last decade, the use of machine learning (ML) approaches in medicinal applications has increased manifold. Most of these approaches are based on deep learning, which aims to learn representations from grid data (like medical images). However, reinforcement learning (RL) applications in medicine are relatively less explored. Medical applications often involve a sequence of subtasks that form a diagnostic pipeline, and RL is uniquely suited to optimize over such sequential decision-making tasks. Ultrasound (US) image analysis is a quintessential example of such a sequential decision-making task, where the raw signal captured by the US transducer undergoes a series of signal processing and image post-processing steps, generally leading to a diagnostic suggestion. The application of RL in US remains limited. Deep Reinforcement Learning (DRL), that combines deep learning and RL, holds great promise in optimizing these pipelines by enabling intelligent and sequential decision-making. This review paper surveys the applications of RL in US over the last decade. We provide a succinct overview of the theoretic framework of RL and its application in US image processing and review existing work in each aspect of the image analysis pipeline. A comprehensive search of Scopus filtered on relevance yielded 14 papers most relevant to this topic. These papers were further categorized based on their target applications image classification, image segmentation, image enhancement, video summarization, and auto navigation and path planning. We also examined the type of RL approach used in each publication. Finally, we discuss key areas in healthcare where DRL approaches in US could be used for sequential decision-making. We analyze the opportunities, challenges, and limitations, providing insights into the future potential of DRL in US image analysis.
A long-standing goal in AI is to build agents that can solve a variety of tasks across different environments, including previously unseen ones. Two dominant approaches tackle this challenge: (i) reinforcement learning (RL), which learns policies through trial and error, and (ii) optimal control, which plans actions using a learned or known dynamics model. However, their relative strengths and weaknesses remain underexplored in the setting where agents must learn from offline trajectories without reward annotations. In this work, we systematically analyze the performance of different RL and control-based methods under datasets of varying quality. On the RL side, we consider goal-conditioned and zero-shot approaches. On the control side, we train a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and use it for planning. We study how dataset properties-such as data diversity, trajectory quality, and environment variability-affect the performance of these approaches. Our results show that model-free RL excels when abundant, high-quality data is available, while model-based planning excels in generalization to novel environment layouts, trajectory stitching, and data-efficiency. Notably, planning with a latent dynamics model emerges as a promising approach for zero-shot generalization from suboptimal data.
The performance of legged locomotion is closely tied to the accuracy and comprehensiveness of state observations. Blind policies, which rely solely on proprioception, are considered highly robust due to the reliability of proprioceptive observations. However, these policies significantly limit locomotion speed and often require collisions with the terrain to adapt. In contrast, Vision policies allows the robot to plan motions in advance and respond proactively to unstructured terrains with an online perception module. However, perception is often compromised by noisy real-world environments, potential sensor failures, and the limitations of current simulations in presenting dynamic or deformable terrains. Humanoid robots, with high degrees of freedom and inherently unstable morphology, are particularly susceptible to misguidance from deficient perception, which can result in falls or termination on challenging dynamic terrains. To leverage the advantages of both vision and blind policies, we propose VB-Com, a composite framework that enables humanoid robots to determine when to rely on the vision policy and when to switch to the blind policy under perceptual deficiency. We demonstrate that VB-Com effectively enables humanoid robots to traverse challenging terrains and obstacles despite perception deficiencies caused by dynamic terrains or perceptual noise.
Foundation models are becoming increasingly effective in the medical domain, offering pre-trained models on large datasets that can be readily adapted for downstream tasks. Despite progress, fetal ultrasound images remain a challenging domain for foundation models due to their inherent complexity, often requiring substantial additional training and facing limitations due to the scarcity of paired multimodal data. To overcome these challenges, here we introduce FetalCLIP, a vision-language foundation model capable of generating universal representation of fetal ultrasound images. FetalCLIP was pre-trained using a multimodal learning approach on a diverse dataset of 210,035 fetal ultrasound images paired with text. This represents the largest paired dataset of its kind used for foundation model development to date. This unique training approach allows FetalCLIP to effectively learn the intricate anatomical features present in fetal ultrasound images, resulting in robust representations that can be used for a variety of downstream applications. In extensive benchmarking across a range of key fetal ultrasound applications, including classification, gestational age estimation, congenital heart defect (CHD) detection, and fetal structure segmentation, FetalCLIP outperformed all baselines while demonstrating remarkable generalizability and strong performance even with limited labeled data. We plan to release the FetalCLIP model publicly for the benefit of the broader scientific community.
NASA's Cooperative Autonomous Distributed Robotic Exploration (CADRE) mission, slated for flight to the Moon's Reiner Gamma region in 2025/2026, is designed to demonstrate multi-agent autonomous exploration of the Lunar surface and sub-surface. A team of three robots and a base station will autonomously explore a region near the lander, collecting the data required for 3D reconstruction of the surface with no human input; and then autonomously perform distributed sensing with multi-static ground penetrating radars (GPR), driving in formation while performing coordinated radar soundings to create a map of the subsurface. At the core of CADRE's software architecture is a novel autonomous, distributed planning, scheduling, and execution (PS&E) system. The system coordinates the robots' activities, planning and executing tasks that require multiple robots' participation while ensuring that each individual robot's thermal and power resources stay within prescribed bounds, and respecting ground-prescribed sleep-wake cycles. The system uses a centralized-planning, distributed-execution paradigm, and a leader election mechanism ensures robustness to failures of individual agents. In this paper, we describe the architecture of CADRE's PS&E system; discuss its design rationale; and report on verification and validation (V&V) testing of the system on CADRE's hardware in preparation for deployment on the Moon.
Coastal regions are particularly vulnerable to the impacts of rising sea levels and extreme weather events. Accurate real-time forecasting of hydrodynamic processes in these areas is essential for infrastructure planning and climate adaptation. In this study, we present the Multiple-Input Temporal Operator Network (MITONet), a novel autoregressive neural emulator that employs dimensionality reduction to efficiently approximate high-dimensional numerical solvers for complex, nonlinear problems that are governed by time-dependent, parameterized partial differential equations. Although MITONet is applicable to a wide range of problems, we showcase its capabilities by forecasting regional tide-driven dynamics described by the two-dimensional shallow-water equations, while incorporating initial conditions, boundary conditions, and a varying domain parameter. We demonstrate MITONet's performance in a real-world application, highlighting its ability to make accurate predictions by extrapolating both in time and parametric space.
Large Multimodal Models (LMMs) have demonstrated strong performance in English, but their effectiveness in Japanese remains limited due to the lack of high-quality training data. Current Japanese LMMs often rely on translated English datasets, restricting their ability to capture Japan-specific cultural knowledge. To address this, we explore the potential of Japanese PDF data as a training resource, an area that remains largely underutilized. We introduce a fully automated pipeline that leverages pretrained models to extract image-text pairs from PDFs through layout analysis, OCR, and vision-language pairing, removing the need for manual annotation. Additionally, we construct instruction data from extracted image-text pairs to enrich the training data. To evaluate the effectiveness of PDF-derived data, we train Japanese LMMs and assess their performance on the Japanese LMM Benchmark. Our results demonstrate substantial improvements, with performance gains ranging from 3.9% to 13.8% on Heron-Bench. Further analysis highlights the impact of PDF-derived data on various factors, such as model size and language models, reinforcing its value as a multimodal resource for Japanese LMMs. We plan to make the source code and data publicly available upon acceptance.
The development of a generalist agent capable of solving a wide range of sequential decision-making tasks remains a significant challenge. We address this problem in a cross-agent setup where agents share the same observation space but differ in their action spaces. Our approach builds on the universal policy framework, which decouples policy learning into two stages: a diffusion-based planner that generates observation sequences and an inverse dynamics model that assigns actions to these plans. We propose a method for training the planner on a joint dataset composed of trajectories from all agents. This method offers the benefit of positive transfer by pooling data from different agents, while the primary challenge lies in adapting shared plans to each agent's unique constraints. We evaluate our approach on the BabyAI environment, covering tasks of varying complexity, and demonstrate positive transfer across agents. Additionally, we examine the planner's generalisation ability to unseen agents and compare our method to traditional imitation learning approaches. By training on a pooled dataset from multiple agents, our universal policy achieves an improvement of up to $42.20\%$ in task completion accuracy compared to a policy trained on a dataset from a single agent.
In this paper, we investigate the control synthesis problem for Signal Temporal Logic (STL) specifications in the presence of uncontrollable agents. Existing works mainly address this problem in a robust control setting by assuming the uncontrollable agents are adversarial and accounting for the worst-case scenario. While this approach ensures safety, it can be overly conservative in scenarios where uncontrollable agents have their own objectives that are not entirely opposed to the system's goals. Motivated by this limitation, we propose a new framework for STL control synthesis within the Stackelberg game setting. Specifically, we assume that the system controller, acting as the leader, first commits to a plan, after which the uncontrollable agents, acting as followers, take a best response based on the committed plan and their own objectives. Our goal is to synthesize a control sequence for the leader such that, for any rational followers producing a best response, the leader's STL task is guaranteed to be satisfied. We present an effective solution to this problem by transforming it into a single-stage optimization problem and leveraging counter-example guided synthesis techniques. We demonstrate that the proposed approach is sound and identify conditions under which it is optimal. Simulation results are also provided to illustrate the effectiveness of the proposed framework.
Efficient solid-liquid separation is crucial in industries like mining, but traditional chamber filter presses depend heavily on manual monitoring, leading to inefficiencies, downtime, and resource wastage. This paper introduces a machine learning-powered digital twin framework to improve operational flexibility and predictive control. A key challenge addressed is the degradation of the filter medium due to repeated cycles and clogging, which reduces filtration efficiency. To solve this, a neural network-based predictive model was developed to forecast operational parameters, such as pressure and flow rates, under various conditions. This predictive capability allows for optimized filtration cycles, reduced downtime, and improved process efficiency. Additionally, the model predicts the filter mediums lifespan, aiding in maintenance planning and resource sustainability. The digital twin framework enables seamless data exchange between filter press sensors and the predictive model, ensuring continuous updates to the training data and enhancing accuracy over time. Two neural network architectures, feedforward and recurrent, were evaluated. The recurrent neural network outperformed the feedforward model, demonstrating superior generalization. It achieved a relative $L^2$-norm error of $5\%$ for pressure and $9.3\%$ for flow rate prediction on partially known data. For completely unknown data, the relative errors were $18.4\%$ and $15.4\%$, respectively. Qualitative analysis showed strong alignment between predicted and measured data, with deviations within a confidence band of $8.2\%$ for pressure and $4.8\%$ for flow rate predictions. This work contributes an accurate predictive model, a new approach to predicting filter medium cycle impacts, and a real-time interface for model updates, ensuring adaptability to changing operational conditions.
The shift from private vehicles to public and shared transport is crucial to reducing emissions and meeting climate targets. Consequently, there is an urgent need to develop a multimodal transport trip planning approach that integrates public transport and shared mobility solutions, offering viable alternatives to private vehicle use. To this end, we propose a preference-based optimization framework for multi-modal trip planning with public transport, ride-pooling services, and shared micro-mobility fleets. We introduce a mixed-integer programming model that incorporates preferences into the objective function of the mathematical model. We present a meta-heuristic framework that incorporates a customized Adaptive Large Neighborhood Search algorithm and other tailored algorithms, to effectively manage dynamic requests through a rolling horizon approach. Numerical experiments are conducted using real transport network data in a suburban area of Rotterdam, the Netherlands. Model application results demonstrate that the proposed algorithm can efficiently obtain near-optimal solutions. Managerial insights are gained from comprehensive experiments that consider various passenger segments, costs of micro-mobility vehicles, and availability fluctuation of shared mobility.
Articulated object manipulation poses a unique challenge compared to rigid object manipulation as the object itself represents a dynamic environment. In this work, we present a novel RL-based pipeline equipped with variable impedance control and motion adaptation leveraging observation history for generalizable articulated object manipulation, focusing on smooth and dexterous motion during zero-shot sim-to-real transfer. To mitigate the sim-to-real gap, our pipeline diminishes reliance on vision by not leveraging the vision data feature (RGBD/pointcloud) directly as policy input but rather extracting useful low-dimensional data first via off-the-shelf modules. Additionally, we experience less sim-to-real gap by inferring object motion and its intrinsic properties via observation history as well as utilizing impedance control both in the simulation and in the real world. Furthermore, we develop a well-designed training setting with great randomization and a specialized reward system (task-aware and motion-aware) that enables multi-staged, end-to-end manipulation without heuristic motion planning. To the best of our knowledge, our policy is the first to report 84\% success rate in the real world via extensive experiments with various unseen objects.
To enhance tourists' experiences and immersion, this paper proposes a narrative-driven travel planning framework called NarrativeGuide, which generates a geoculturally-grounded narrative script for travelers, offering a novel, role-playing experience for their journey. In the initial stage, NarrativeGuide constructs a knowledge graph for attractions within a city, then configures the worldview, character setting, and exposition based on the knowledge graph. Using this foundation, the knowledge graph is combined to generate an independent scene unit for each attraction. During the itinerary planning stage, NarrativeGuide models narrative-driven travel planning as an optimization problem, utilizing a genetic algorithm (GA) to refine the itinerary. Before evaluating the candidate itinerary, transition scripts are generated for each pair of adjacent attractions, which, along with the scene units, form a complete script. The weighted sum of script coherence, travel time, and attraction scores is then used as the fitness value to update the candidate solution set. Experimental results across four cities, i.e., Nanjing and Yangzhou in China, Paris in France, and Berlin in Germany, demonstrate significant improvements in narrative coherence and cultural fit, alongside a notable reduction in travel time and an increase in the quality of visited attractions. Our study highlights that incorporating external evolutionary optimization effectively addresses the limitations of large language models in travel planning.
Efficient crop production requires early detection of pest outbreaks and timely treatments; we consider a solution based on a fleet of multiple autonomous miniaturized unmanned aerial vehicles (nano-UAVs) to visually detect pests and a single slower heavy vehicle that visits the detected outbreaks to deliver treatments. To cope with the extreme limitations aboard nano-UAVs, e.g., low-resolution sensors and sub-100 mW computational power budget, we design, fine-tune, and optimize a tiny image-based convolutional neural network (CNN) for pest detection. Despite the small size of our CNN (i.e., 0.58 GOps/inference), on our dataset, it scores a mean average precision (mAP) of 0.79 in detecting harmful bugs, i.e., 14% lower mAP but 32x fewer operations than the best-performing CNN in the literature. Our CNN runs in real-time at 6.8 frame/s, requiring 33 mW on a GWT GAP9 System-on-Chip aboard a Crazyflie nano-UAV. Then, to cope with in-field unexpected obstacles, we leverage a global+local path planner based on the A* algorithm. The global path planner determines the best route for the nano-UAV to sweep the entire area, while the local one runs up to 50 Hz aboard our nano-UAV and prevents collision by adjusting the short-distance path. Finally, we demonstrate with in-simulator experiments that once a 25 nano-UAVs fleet has combed a 200x200 m vineyard, collected information can be used to plan the best path for the tractor, visiting all and only required hotspots. In this scenario, our efficient transportation system, compared to a traditional single-ground vehicle performing both inspection and treatment, can save up to 20 h working time.
Deep reinforcement learning agents often face challenges to effectively coordinate perception and decision-making components, particularly in environments with high-dimensional sensory inputs where feature relevance varies. This work introduces SPRIG (Stackelberg Perception-Reinforcement learning with Internal Game dynamics), a framework that models the internal perception-policy interaction within a single agent as a cooperative Stackelberg game. In SPRIG, the perception module acts as a leader, strategically processing raw sensory states, while the policy module follows, making decisions based on extracted features. SPRIG provides theoretical guarantees through a modified Bellman operator while preserving the benefits of modern policy optimization. Experimental results on the Atari BeamRider environment demonstrate SPRIG's effectiveness, achieving around 30% higher returns than standard PPO through its game-theoretical balance of feature extraction and decision-making.
In oncology, recurrence after treatment is one of the major challenges, related to patients' survival and quality of life. Conventionally, prediction of cancer relapse has always relied on clinical observation with statistical model support, which almost fails to explain the complex, multifactorial nature of tumor recurrence. This research explores how AI and ML models may increase the accuracy and reliability of recurrence prediction in cancer. Therefore, AI and ML create new opportunities not only for personalized medicine but also for proactive management of patients through analyzing large volumes of data on genetics, clinical manifestations, and treatment. The paper describes the various AI and ML techniques for pattern identification and outcome prediction in cancer patients using supervised and unsupervised learning. Clinical implications provide an opportunity to review how early interventions could happen and the design of treatment planning.
Motion planning is a fundamental problem in autonomous driving and perhaps the most challenging to comprehensively evaluate because of the associated risks and expenses of real-world deployment. Therefore, simulations play an important role in efficient development of planning algorithms. To be effective, simulations must be accurate and realistic, both in terms of dynamics and behavior modeling, and also highly customizable in order to accommodate a broad spectrum of research frameworks. In this paper, we introduce SMARTS 2.0, the second generation of our motion planning simulator which, in addition to being highly optimized for large-scale simulation, provides many new features, such as realistic map integration, vehicle-to-vehicle (V2V) communication, traffic and pedestrian simulation, and a broad variety of sensor models. Moreover, we present a novel benchmark suite for evaluating planning algorithms in various highly challenging scenarios, including interactive driving, such as turning at intersections, and adaptive driving, in which the task is to closely follow a lead vehicle without any explicit knowledge of its intention. Each scenario is characterized by a variety of traffic patterns and road structures. We further propose a series of common and task-specific metrics to effectively evaluate the performance of the planning algorithms. At the end, we evaluate common motion planning algorithms using the proposed benchmark and highlight the challenges the proposed scenarios impose. The new SMARTS 2.0 features and the benchmark are publicly available at github.com/huawei-noah/SMARTS.
This paper studies high-speed online planning in dynamic environments. The problem requires finding time-optimal trajectories that conform to system dynamics, meeting computational constraints for real-time adaptation, and accounting for uncertainty from environmental changes. To address these challenges, we propose a sampling-based online planning algorithm that leverages neural network inference to replace time-consuming nonlinear trajectory optimization, enabling rapid exploration of multiple trajectory options under uncertainty. The proposed method is applied to the drone interception problem, where a defense drone must intercept a target while avoiding collisions and handling imperfect target predictions. The algorithm efficiently generates trajectories toward multiple potential target drone positions in parallel. It then assesses trajectory reachability by comparing traversal times with the target drone's predicted arrival time, ultimately selecting the minimum-time reachable trajectory. Through extensive validation in both simulated and real-world environments, we demonstrate our method's capability for high-rate online planning and its adaptability to unpredictable movements in unstructured settings.
This paper presents a theoretical framework unifying AIXI -- a model of universal AI -- with variational empowerment as an intrinsic drive for exploration. We build on the existing framework of Self-AIXI -- a universal learning agent that predicts its own actions -- by showing how one of its established terms can be interpreted as a variational empowerment objective. We further demonstrate that universal AI's planning process can be cast as minimizing expected variational free energy (the core principle of active Inference), thereby revealing how universal AI agents inherently balance goal-directed behavior with uncertainty reduction curiosity). Moreover, we argue that power-seeking tendencies of universal AI agents can be explained not only as an instrumental strategy to secure future reward, but also as a direct consequence of empowerment maximization -- i.e.\ the agent's intrinsic drive to maintain or expand its own controllability in uncertain environments. Our main contribution is to show how these intrinsic motivations (empowerment, curiosity) systematically lead universal AI agents to seek and sustain high-optionality states. We prove that Self-AIXI asymptotically converges to the same performance as AIXI under suitable conditions, and highlight that its power-seeking behavior emerges naturally from both reward maximization and curiosity-driven exploration. Since AIXI can be view as a Bayes-optimal mathematical formulation for Artificial General Intelligence (AGI), our result can be useful for further discussion on AI safety and the controllability of AGI.
Lithium ion batteries are widely used in many applications. Battery management systems control their optimal use and charging and predict when the battery will cease to deliver the required output on a planned duty or driving cycle. Such systems use a simulation of a mathematical model of battery performance. These models can be electrochemical or data-driven. Electrochemical models for batteries running at high currents are mathematically and computationally complex. In this work, we show that a well-regarded electrochemical model, the Pseudo Two Dimensional (P2D) model, can be replaced by a computationally efficient Convolutional Neural Network (CNN) surrogate model fit to accurately simulated data from a class of random driving cycles. We demonstrate that a CNN is an ideal choice for accurately capturing Lithium ion concentration profiles. Additionally, we show how the neural network model can be adjusted to correspond to battery changes in State of Health (SOH).
Decarbonization plans promote the transition to heat pumps (HPs), creating new opportunities for their energy flexibility in demand response programs, solar photovoltaic integration and optimization of distribution networks. This paper reviews scheduling-based and real-time optimization methods for controlling HPs with a focus on energy flexibility in distribution networks. Scheduling-based methods fall into two categories: rule-based controllers (RBCs), which rely on predefined control rules without explicitly seeking optimal solutions, and optimization models, which are designed to determine the optimal scheduling of operations. Real-time optimization is achieved through model predictive control (MPC), which relies on a predictive model to optimize decisions over a time horizon, and reinforcement learning (RL), which takes a model-free approach by learning optimal strategies through direct interaction with the environment. The paper also examines studies on the impact of HPs on distribution networks, particularly those leveraging energy flexibility strategies. Key takeaways suggest the need to validate control strategies for extreme cold-weather regions that require backup heaters, as well as develop approaches designed for demand charge schemes that integrate HPs with other controllable loads. From a grid impact assessment perspective, studies have focused primarily on RBCs for providing energy flexibility through HP operation, without addressing more advanced methods such as real-time optimization using MPC or RL-based algorithms. Incorporating these advanced control strategies could help identify key limitations, including the impact of varying user participation levels and the cost-benefit trade-offs associated with their implementation.
In this paper, we consider robotic tasks which require a desirable outcome to be achieved in the physical world that the robot is embedded in and interacting with. Accomplishing this objective requires designing a filter that maintains a useful representation of the physical world and a policy over the filter states. A filter is seen as the robot's perspective of the physical world based on limited sensing, memory, and computation and it is represented as a transition system over a space of information states. To this end, the interactions result from the coupling of an internal and an external system, a filter, and the physical world, respectively, through a sensor mapping and an information-feedback policy. Within this setup, we look for sufficient structures, that is, sufficient internal systems and sensors, for accomplishing a given task. We establish necessary and sufficient conditions for these structures to satisfy for information-feedback policies that can be defined over the states of an internal system to exist. We also show that under mild assumptions, minimal internal systems that can represent a particular plan/policy described over the action-observation histories exist and are unique. Finally, the results are applied to determine sufficient structures for distance-optimal navigation in a polygonal environment.
This paper presents a real-time trajectory planning scheme for a heterogeneous multi-robot system (consisting of a quadrotor and a ground mobile robot) for a cooperative landing task, where the landing position, landing time, and coordination between the robots are determined autonomously under the consideration of feasibility and user specifications. The proposed framework leverages the potential of the complementarity constraint as a decision-maker and an indicator for diverse cooperative tasks and extends it to the collaborative landing scenario. In a potential application of the proposed methodology, a ground mobile robot may serve as a mobile charging station and coordinates in real-time with a quadrotor to be charged, facilitating a safe and efficient rendezvous and landing. We verified the generated trajectories in simulation and real-world applications, demonstrating the real-time capabilities of the proposed landing planning framework.
Estimating the construction year of buildings is of great importance for sustainability. Sustainable buildings minimize energy consumption and are a key part of responsible and sustainable urban planning and development to effectively combat climate change. By using Artificial Intelligence (AI) and recently proposed Transformer models, we are able to estimate the construction epoch of buildings from a multi-modal dataset. In this paper, we introduce a new benchmark multi-modal dataset, i.e. the Map your City Dataset (MyCD), containing top-view Very High Resolution (VHR) images, Earth Observation (EO) multi-spectral data from the Copernicus Sentinel-2 satellite constellation, and street-view images in many different cities in Europe, co-localized with respect to the building under study and labelled with the construction epoch. We assess EO generalization performance on new/ previously unseen cities that have been held-out from training and appear only during inference. In this work, we present the community-based data challenge we organized based on MyCD. The ESA AI4EO Challenge MapYourCity was opened in 2024 for 4 months. Here, we present the Top-4 performing models, and the main evaluation results. During inference, the performance of the models using both all three input modalities and only the two top-view modalities, i.e. without the street-view images, is examined. The evaluation results show that the models are effective and can achieve good performance on this difficult real-world task of estimating the age of buildings, even on previously unseen cities, as well as even using only the two top-view modalities (i.e. VHR and Sentinel-2) during inference.
In this demonstration, we present AnDB, an AI-native database that supports traditional OLTP workloads and innovative AI-driven tasks, enabling unified semantic analysis across structured and unstructured data. While structured data analytics is mature, challenges remain in bridging the semantic gap between user queries and unstructured data. AnDB addresses these issues by leveraging cutting-edge AI-native technologies, allowing users to perform semantic queries using intuitive SQL-like statements without requiring AI expertise. This approach eliminates the ambiguity of traditional text-to-SQL systems and provides a seamless end-to-end optimization for analyzing all data types. AnDB automates query processing by generating multiple execution plans and selecting the optimal one through its optimizer, which balances accuracy, execution time, and financial cost based on user policies and internal optimizing mechanisms. AnDB future-proofs data management infrastructure, empowering users to effectively and efficiently harness the full potential of all kinds of data without starting from scratch.
Digital twin (DT) technology is increasingly used in urban planning, leveraging real-time data integration for environmental monitoring. This paper presents an urban-focused DT that combines computational fluid dynamics simulations with live meteorological data to analyze pollution dispersion. Addressing the health impacts of pollutants like particulate matter and nitrogen dioxide, the DT provides real-time updates on air quality, wind speed, and direction. Using OpenStreetMaps XML-based data, the model distinguishes between porous elements like trees and solid structures, enhancing urban flow analysis. The framework employs the lattice Boltzmann method (LBM) within the open-source software OpenLB to simulate pollution transport. Nitrogen dioxide and particulate matter concentrations are estimated based on traffic and building emissions, enabling hot-spot identification. The DT was used from November 7 to 23, 2024, with hourly updates, capturing pollution trends influenced by wind patterns. Results show that alternating east-west winds during this period create a dynamic pollution distribution, identifying critical residential exposure areas. This work contributes a novel DT framework that integrates real-time meteorological data, OpenStreetMap-based geometry, and high-fidelity LBM simulations for urban wind and pollution modeling. Unlike existing DTs, which focus on structural monitoring or large-scale environmental factors, this approach enables fine-grained, dynamic analyses of urban airflow and pollution dispersion. By allowing interactive modifications to urban geometry and continuous data updates, the DT serves as a powerful tool for adaptive urban planning, supporting evidence-based policy making to improve air quality and public health.
This paper presents a novel framework for decentralized annuities, aiming to address the limitations of traditional pension systems such as defined contribution (DC) and defined benefit (DB) plans, while providing lifetime financial support. It sheds light on often ignored pitfalls within current retirement schemes and introduces individual rationality properties. The research delves into various fairness concepts that underpin existing plans, emphasizing that decentralized annuities, while meeting similar fairness criteria, offer enhanced flexibility for individual rationality and improved social welfare for all participants. Using theoretical models and examples, we demonstrate the potential of decentralized annuities to outperform self-managed plans (DC) and to produce effects comparable to defined benefit (DB) plans, particularly within larger participant pools. The paper concludes by exploring the managerial implications of decentralized annuities and laying the groundwork for the further advancement of equitable and sustainable decentralized annuity systems.
Deployment of robots into hazardous environments typically involves a ``Human-Robot Teaming'' (HRT) paradigm, in which a human supervisor interacts with a remotely operating robot inside the hazardous zone. Situational Awareness (SA) is vital for enabling HRT, to support navigation, planning, and decision-making. This paper explores issues of higher-level ``semantic'' information and understanding in SA. In semi-autonomous, or variable-autonomy paradigms, different types of semantic information may be important, in different ways, for both the human operator and an autonomous agent controlling the robot. We propose a generalizable framework for acquiring and combining multiple modalities of semantic-level SA during remote deployments of mobile robots. We demonstrate the framework with an example application of search and rescue (SAR) in disaster response robotics. We propose a set of ``environment semantic indicators" that can reflect a variety of different types of semantic information, e.g. indicators of risk, or signs of human activity, as the robot encounters different scenes. Based on these indicators, we propose a metric to describe the overall situation of the environment called ``Situational Semantic Richness (SSR)". This metric combines multiple semantic indicators to summarise the overall situation. The SSR indicates if an information-rich and complex situation has been encountered, which may require advanced reasoning for robots and humans and hence the attention of the expert human operator. The framework is tested on a Jackal robot in a mock-up disaster response environment. Experimental results demonstrate that the proposed semantic indicators are sensitive to changes in different modalities of semantic information in different scenes, and the SSR metric reflects overall semantic changes in the situations encountered.
Multi-agent planning under stochastic dynamics is usually formalised using decentralized (partially observable) Markov decision processes ( MDPs) and reachability or expected reward specifications. In this paper, we propose a different approach: we use an MDP describing how a single agent operates in an environment and probabilistic hyperproperties to capture desired temporal objectives for a set of decentralized agents operating in the environment. We extend existing approaches for model checking probabilistic hyperproperties to handle temporal formulae relating paths of different agents, thus requiring the self-composition between multiple MDPs. Using several case studies, we demonstrate that our approach provides a flexible and expressive framework to broaden the specification capabilities with respect to existing planning techniques. Additionally, we establish a close connection between a subclass of probabilistic hyperproperties and planning for a particular type of Dec-MDPs, for both of which we show undecidability. This lays the ground for the use of existing decentralized planning tools in the field of probabilistic hyperproperty verification.
End-to-end autonomous driving, which directly maps raw sensor inputs to low-level vehicle controls, is an important part of Embodied AI. Despite successes in applying Multimodal Large Language Models (MLLMs) for high-level traffic scene semantic understanding, it remains challenging to effectively translate these conceptual semantics understandings into low-level motion control commands and achieve generalization and consensus in cross-scene driving. We introduce Sce2DriveX, a human-like driving chain-of-thought (CoT) reasoning MLLM framework. Sce2DriveX utilizes multimodal joint learning from local scene videos and global BEV maps to deeply understand long-range spatiotemporal relationships and road topology, enhancing its comprehensive perception and reasoning capabilities in 3D dynamic/static scenes and achieving driving generalization across scenes. Building on this, it reconstructs the implicit cognitive chain inherent in human driving, covering scene understanding, meta-action reasoning, behavior interpretation analysis, motion planning and control, thereby further bridging the gap between autonomous driving and human thought processes. To elevate model performance, we have developed the first extensive Visual Question Answering (VQA) driving instruction dataset tailored for 3D spatial understanding and long-axis task reasoning. Extensive experiments demonstrate that Sce2DriveX achieves state-of-the-art performance from scene understanding to end-to-end driving, as well as robust generalization on the CARLA Bench2Drive benchmark.
The efficient planning of stacking boxes, especially in the online setting where the sequence of item arrivals is unpredictable, remains a critical challenge in modern warehouse and logistics management. Existing solutions often address box size variations, but overlook their intrinsic and physical properties, such as density and rigidity, which are crucial for real-world applications. We use reinforcement learning (RL) to solve this problem by employing action space masking to direct the RL policy toward valid actions. Unlike previous methods that rely on heuristic stability assessments which are difficult to assess in physical scenarios, our framework utilizes online learning to dynamically train the action space mask, eliminating the need for manual heuristic design. Extensive experiments demonstrate that our proposed method outperforms existing state-of-the-arts. Furthermore, we deploy our learned task planner in a real-world robotic palletizer, validating its practical applicability in operational settings.
Online trajectory planning enables robot manipulators to react quickly to changing environments or tasks. Many robot trajectory planners exist for known environments but are often too slow for online computations. Current methods in online trajectory planning do not find suitable trajectories in challenging scenarios that respect the limits of the robot and account for collisions. This work proposes a trajectory planning framework consisting of the novel Cartesian path planner based on convex sets, called BoundPlanner, and the online trajectory planner BoundMPC. BoundPlanner explores and maps the collision-free space using convex sets to compute a reference path with bounds. BoundMPC is extended in this work to handle convex sets for path deviations, which allows the robot to optimally follow the path within the bounds while accounting for the robot's kinematics. Collisions of the robot's kinematic chain are considered by a novel convex-set-based collision avoidance formulation independent on the number of obstacles. Simulations and experiments with a 7-DoF manipulator show the performance of the proposed planner compared to state-of-the-art methods. The source code is available at github.com/Thieso/BoundPlanner and videos of the experiments can be found at www.acin.tuwien.ac.at/42d4
We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. Magma is a significant extension of vision-language (VL) models in that it not only retains the VL understanding ability (verbal intelligence) of the latter, but is also equipped with the ability to plan and act in the visual-spatial world (spatial-temporal intelligence) and complete agentic tasks ranging from UI navigation to robot manipulation. To endow the agentic capabilities, Magma is pretrained on large amounts of heterogeneous datasets spanning from images, videos to robotics data, where the actionable visual objects (e.g., clickable buttons in GUI) in images are labeled by Set-of-Mark (SoM) for action grounding, and the object movements (e.g., the trace of human hands or robotic arms) in videos are labeled by Trace-of-Mark (ToM) for action planning. Extensive experiments show that SoM and ToM reach great synergy and facilitate the acquisition of spatial-temporal intelligence for our Magma model, which is fundamental to a wide range of tasks as shown in Fig.1. In particular, Magma creates new state-of-the-art results on UI navigation and robotic manipulation tasks, outperforming previous models that are specifically tailored to these tasks. On image and video-related multimodal tasks, Magma also compares favorably to popular large multimodal models that are trained on much larger datasets. We make our model and code public for reproducibility at https://microsoft.github.io/Magma.
Automated Planning algorithms require a model of the domain that specifies the preconditions and effects of each action. Obtaining such a domain model is notoriously hard. Algorithms for learning domain models exist, yet it remains unclear whether learning a domain model and planning is an effective approach for numeric planning environments, i.e., where states include discrete and numeric state variables. In this work, we explore the benefits of learning a numeric domain model and compare it with alternative model-free solutions. As a case study, we use two tasks in Minecraft, a popular sandbox game that has been used as an AI challenge. First, we consider an offline learning setting, where a set of expert trajectories are available to learn from. This is the standard setting for learning domain models. We used the Numeric Safe Action Model Learning (NSAM) algorithm to learn a numeric domain model and solve new problems with the learned domain model and a numeric planner. We call this model-based solution NSAM_(+p), and compare it to several model-free Imitation Learning (IL) and Offline Reinforcement Learning (RL) algorithms. Empirical results show that some IL algorithms can learn faster to solve simple tasks, while NSAM_(+p) allows solving tasks that require long-term planning and enables generalizing to solve problems in larger environments. Then, we consider an online learning setting, where learning is done by moving an agent in the environment. For this setting, we introduce RAMP. In RAMP, observations collected during the agent's execution are used to simultaneously train an RL policy and learn a planning domain action model. This forms a positive feedback loop between the RL policy and the learned domain model. We demonstrate experimentally the benefits of using RAMP, showing that it finds more efficient plans and solves more problems than several RL baselines.
The intelligent upgrading of metropolitan rail transit systems has made it feasible to implement demand-side management policies that integrate multiple operational strategies in practical operations. However, the tight interdependence between supply and demand necessitates a coordinated approach combining demand-side management policies and supply-side resource allocations to enhance the urban rail transit ecosystem. In this study, we propose a mathematical and computational framework that optimizes train timetables, passenger flow control strategies, and trip-shifting plans through the pricing policy. Our framework incorporates an emerging trip-booking approach that transforms waiting at the stations into waiting at home, thereby mitigating station overcrowding. Additionally, it ensures service fairness by maintaining an equitable likelihood of delays across different stations. We formulate the problem as an integer linear programming model, aiming to minimize passengers' waiting time and government subsidies required to offset revenue losses from fare discounts used to encourage trip shifting. To improve computational efficiency, we develop a Benders decomposition-based algorithm within the branch-and-cut method, which decomposes the model into train timetabling with partial passenger assignment and passenger flow control subproblems. We propose valid inequalities based on our model's properties to strengthen the linear relaxation bounds at each node. Computational results from proof-of-concept and real-world case studies on the Beijing metro show that our solution method outperforms commercial solvers in terms of computational efficiency. We can obtain high-quality solutions, including optimal ones, at the root node with reduced branching requirements thanks to our novel decomposition framework and valid inequalities.
With the 4-meter Multi-Object Spectroscopic Telescope (4MOST) expected to provide an influx of transient spectra when it begins observations in early 2026 we consider the potential for real-time classification of these spectra. We investigate three extant spectroscopic transient classifiers: the Deep Automated Supernova and Host classifier (DASH), Next Generation SuperFit (NGSF) and SuperNova IDentification (SNID), with a focus on comparing the efficiency and purity of the transient samples they produce. We discuss our method for simulating realistic, 4MOST-like, host-galaxy contaminated spectra and determining quality cuts for each classifier used to ensure pure SN Ia samples while maintaining efficient classification in other transient classes. We investigate the classifiers individually and in combinations. We find that a combination of DASH and NGSF can produce a SN Ia sample with a purity of 99.9% while successfully classifying 70% of SNe Ia. However, it struggles to classify non-SN Ia transients. We investigate photometric cuts to transient magnitude and transient flux fraction, finding that both can be used to improve transient classification efficiencies by 7--25% depending on the transient subclass. Finally, we present an example classification plan for live classification and the predicted purities and efficiencies across five transient classes: Ia, Ibc, II, superluminous and non-supernova transients.
This paper introduces RobotIQ, a framework that empowers mobile robots with human-level planning capabilities, enabling seamless communication via natural language instructions through any Large Language Model. The proposed framework is designed in the ROS architecture and aims to bridge the gap between humans and robots, enabling robots to comprehend and execute user-expressed text or voice commands. Our research encompasses a wide spectrum of robotic tasks, ranging from fundamental logical, mathematical, and learning reasoning for transferring knowledge in domains like navigation, manipulation, and object localization, enabling the application of learned behaviors from simulated environments to real-world operations. All encapsulated within a modular crafted robot library suite of API-wise control functions, RobotIQ offers a fully functional AI-ROS-based toolset that allows researchers to design and develop their own robotic actions tailored to specific applications and robot configurations. The effectiveness of the proposed system was tested and validated both in simulated and real-world experiments focusing on a home service scenario that included an assistive application designed for elderly people. RobotIQ with an open-source, easy-to-use, and adaptable robotic library suite for any robot can be found at https://github.com/emmarapt/RobotIQ.
In-band network telemetry (INT) is essential to network management due to its real-time visibility. However, because of the rapid increase in network devices and services, it has become crucial to have targeted access to detailed network information in a dynamic network environment. This paper proposes an intelligent network telemetry system called NTP-INT to obtain more fine-grained network information on high-load switches. Specifically, NTP-INT consists of three modules: network traffic prediction module, network pruning module, and probe path planning module. Firstly, the network traffic prediction module adopts a Multi-Temporal Graph Neural Network (MTGNN) to predict future network traffic and identify high-load switches. Then, we design the network pruning algorithm to generate a subnetwork covering all high-load switches to reduce the complexity of probe path planning. Finally, the probe path planning module uses an attention-mechanism-based deep reinforcement learning (DEL) model to plan efficient probe paths in the network slice. The experimental results demonstrate that NTP-INT can acquire more precise network information on high-load switches while decreasing the control overhead by 50\%.
The return of Comet 1P/Halley will promote a wide interest for ground and space observations of a celestial body of outstanding scientific and cultural interest. In addition to remote observations, space will open the possibility of in situ science similarly to the passage of 1986. In this paper, we first discuss the scientific motivations for a rendezvous mission, capable to overcome the limitations of the flyby missions that took place at that time. In the second part, we describe an example of a rendezvous trajectory that can be carried out with existing power and propulsion technologies. The transfer is made possible by the gravitational assistance of a giant planet. The resulting mission will be capable to reach the comet beyond the distance of Saturn, when the sublimation of super-volatile species will be ongoing, and well before the onset of the sublimation of water (4 AU). After rendezvous, the spacecraft will accompany the comet for several years before, around and after perihelion (July 2061). Our concept mission does not foresee the implementation of solar panels. In this way, operations can occur even inside the dense dust coma at short distance from the nucleus. In the third part of the paper, an innovative imaging system is proposed, with a very large field of view (100{\deg}) capable to record on the same frame details on the surface and the surrounding space, in order to follow for several degrees the trajectories of chunks and clouds ejected by pits or fractures, crucial to the understanding of the cometary activity. A concerted effort is needed in the current decade to plan and approve a rendezvous mission to 1P. Indeed, the scenario here described requires launching before 2040, less than 15 years from now. Later launches imply a severe loss of scientific knowledge, because the spacecraft will not be able to reach the comet before the onset of water sublimation.
With the rise of online applications, recommender systems (RSs) often encounter constraints in balancing exploration and exploitation. Such constraints arise when exploration is carried out by agents whose individual utility should be balanced with overall welfare. Recent work suggests that recommendations should be individually rational. Specifically, if agents have a default arm they would use, relying on the RS should yield each agent at least the reward of the default arm, conditioned on the knowledge available to the RS. Under this individual rationality constraint, striking a balance between exploration and exploitation becomes a complex planning problem. We assume a stochastic order of the rewards (e.g., Bernoulli, unit-variance Gaussian, etc.), and derive an approximately optimal algorithm. Our technique is based on an auxiliary Goal Markov Decision Process problem that is of independent interest. Additionally, we present an incentive-compatible version of our algorithm.
Reinforcement learning (RL) has shown promise in solving various combinatorial optimization problems. However, conventional RL faces challenges when dealing with real-world constraints, especially when action space feasibility is explicit and dependent on the corresponding state or trajectory. In this work, we focus on using RL in container shipping, often considered the cornerstone of global trade, by dealing with the critical challenge of master stowage planning. The main objective is to maximize cargo revenue and minimize operational costs while navigating demand uncertainty and various complex operational constraints, namely vessel capacity and stability, which must be dynamically updated along the vessel's voyage. To address this problem, we implement a deep reinforcement learning framework with feasibility projection to solve the master stowage planning problem (MPP) under demand uncertainty. The experimental results show that our architecture efficiently finds adaptive, feasible solutions for this multi-stage stochastic optimization problem, outperforming traditional mixed-integer programming and RL with feasibility regularization. Our AI-driven decision-support policy enables adaptive and feasible planning under uncertainty, optimizing operational efficiency and capacity utilization while contributing to sustainable and resilient global supply chains.
This paper presents the myEye2Wheeler dataset, a unique resource of real-world gaze behaviour of two-wheeler drivers navigating complex Indian traffic. Most datasets are from four-wheeler drivers on well-planned roads and homogeneous traffic. Our dataset offers a critical lens into the unique visual attention patterns and insights into the decision-making of Indian two-wheeler drivers. The analysis demonstrates that existing saliency models, like TASED-Net, perform less effectively on the myEye-2Wheeler dataset compared to when applied on the European 4-wheeler eye tracking datasets (DR(Eye)VE), highlighting the need for models specifically tailored to the traffic conditions. By introducing the dataset, we not only fill a significant gap in two-wheeler driver behaviour research in India but also emphasise the critical need for developing context-specific saliency models. The larger aim is to improve road safety for two-wheeler users and lane-planning to support a cost-effective mode of transport.
As vehicle automation technology continues to mature, there is a necessity for robust remote monitoring and intervention features. These are essential for intervening during vehicle malfunctions, challenging road conditions, or in areas that are difficult to navigate. This evolution in the role of the human operator - from a constant driver to an intermittent teleoperator - necessitates the development of suitable interaction interfaces. While some interfaces were suggested, a comparative study is missing. We designed, implemented, and evaluated three interaction concepts (path planning, trajectory guidance, and waypoint guidance) with up to four concurrent requests of automated vehicles in a within-subjects study with N=23 participants. The results showed a clear preference for the path planning concept. It also led to the highest usability but lower satisfaction. With trajectory guidance, the fewest requests were resolved. The study's findings contribute to the ongoing development of HMIs focused on the remote assistance of automated vehicles.
Diffusion policies have shown promise in learning complex behaviors from demonstrations, particularly for tasks requiring precise control and long-term planning. However, they face challenges in robustness when encountering distribution shifts. This paper explores improving diffusion-based imitation learning models through online interactions with the environment. We propose OTPR (Optimal Transport-guided score-based diffusion Policy for Reinforcement learning fine-tuning), a novel method that integrates diffusion policies with RL using optimal transport theory. OTPR leverages the Q-function as a transport cost and views the policy as an optimal transport map, enabling efficient and stable fine-tuning. Moreover, we introduce masked optimal transport to guide state-action matching using expert keypoints and a compatibility-based resampling strategy to enhance training stability. Experiments on three simulation tasks demonstrate OTPR's superior performance and robustness compared to existing methods, especially in complex and sparse-reward environments. In sum, OTPR provides an effective framework for combining IL and RL, achieving versatile and reliable policy learning. The code will be released at https://github.com/Sunmmyy/OTPR.git.
State classification of objects and their relations is core to many long-horizon tasks, particularly in robot planning and manipulation. However, the combinatorial explosion of possible object-predicate combinations, coupled with the need to adapt to novel real-world environments, makes it a desideratum for state classification models to generalize to novel queries with few examples. To this end, we propose PHIER, which leverages predicate hierarchies to generalize effectively in few-shot scenarios. PHIER uses an object-centric scene encoder, self-supervised losses that infer semantic relations between predicates, and a hyperbolic distance metric that captures hierarchical structure; it learns a structured latent space of image-predicate pairs that guides reasoning over state classification queries. We evaluate PHIER in the CALVIN and BEHAVIOR robotic environments and show that PHIER significantly outperforms existing methods in few-shot, out-of-distribution state classification, and demonstrates strong zero- and few-shot generalization from simulated to real-world tasks. Our results demonstrate that leveraging predicate hierarchies improves performance on state classification tasks with limited data.
Replacing the quadratic proximal penalty familiar from Hilbert spaces by an unbalanced optimal transport distance, we develop forward-backward type optimisation methods in spaces of Radon measures. We avoid the actual computation of the optimal transport distances through the use of transport three-plans and the rough concept of transport subdifferentials. The resulting algorithm has a step similar to the sliding heuristics previously introduced for conditional gradient methods, however, now non-heuristically derived from the geometry of the space. We demonstrate the improved numerical performance of the approach.
Grid-ignited wildfires are one of the most destructive catastrophic events, profoundly affecting the built and natural environments. Burying power lines is an effective solution for mitigating the risk of wildfire ignition. However, it is a costly capital expenditure (CapEx) requiring meticulous planning and investment prioritization. This paper proposes a systematic approach to estimate the potential wildfire ignition damage associated with each transmission line and accordingly offers a priority list for undergrounding. The proposed approach allows electric utilities to make risk-informed decisions for grid modernization and resiliency improvement against wildfires. As a case study, we examine the likelihood of wildfire ignition for each line segment, i.e., between two high-voltage towers, under diverse weather conditions throughout the year. The studies on the standard IEEE 30-bus test system, simulated on 43,712 scenarios, demonstrate the effectiveness of the proposed approach.
Low-energy electron recoils are of interest in several planned and proposed future nuclear and particle physics experiments. The topology and directions of such recoils provide important particle identification and kinematical constraints, and are experimentally accessible in gaseous targets. Electron recoils have complex trajectories, and the angular resolution that can be achieved has not been well understood. We have developed a method for estimating and optimizing this angular resolution, considering contributions from both multiple scattering and detection. First, we clarify that the formula commonly used for multiple scattering through small angles is actually a fit to Moliere theory for heavy particles. We revise this formula so that it is applicable to electrons in gas. Next, we combine this with an effective point resolution contribution, which accounts for diffusion and detector effects, to obtain an approximation for the angular resolution. We identify the optimal fit length and the corresponding optimal angular resolution. The result is a simple formula to estimate the best achievable angular resolution for electrons in gaseous detectors, given the electron energy and basic gas and detector properties. Our model's predictions show good agreement with simulations. This approach can assist in the design of future experiments and the development of analysis techniques. Given the widespread use of gaseous detectors, this work is relevant to many scientific communities.
Autonomous cyber-physical systems (CPSs) leverage AI for perception, planning, and control but face trust and safety certification challenges due to inherent uncertainties. The neurosymbolic paradigm replaces stochastic layers with interpretable symbolic AI, enabling determinism. While promising, challenges like multisensor fusion, adaptability, and verification remain. This paper introduces NeuroStrata, a neurosymbolic framework to enhance the testing and verification of autonomous CPS. We outline its key components, present early results, and detail future plans.
Weather nowcasting is an essential task that involves predicting future radar echo sequences based on current observations, offering significant benefits for disaster management, transportation, and urban planning. Current prediction methods are limited by training and storage efficiency, mainly focusing on 2D spatial predictions at specific altitudes. Meanwhile, 3D volumetric predictions at each timestamp remain largely unexplored. To address such a challenge, we introduce a comprehensive framework for 3D radar sequence prediction in weather nowcasting, using the newly proposed SpatioTemporal Coherent Gaussian Splatting (STC-GS) for dynamic radar representation and GauMamba for efficient and accurate forecasting. Specifically, rather than relying on a 4D Gaussian for dynamic scene reconstruction, STC-GS optimizes 3D scenes at each frame by employing a group of Gaussians while effectively capturing their movements across consecutive frames. It ensures consistent tracking of each Gaussian over time, making it particularly effective for prediction tasks. With the temporally correlated Gaussian groups established, we utilize them to train GauMamba, which integrates a memory mechanism into the Mamba framework. This allows the model to learn the temporal evolution of Gaussian groups while efficiently handling a large volume of Gaussian tokens. As a result, it achieves both efficiency and accuracy in forecasting a wide range of dynamic meteorological radar signals. The experimental results demonstrate that our STC-GS can efficiently represent 3D radar sequences with over $16\times$ higher spatial resolution compared with the existing 3D representation methods, while GauMamba outperforms state-of-the-art methods in forecasting a broad spectrum of high-dynamic weather conditions.
The remarkable sensitivity achieved by the planned Laser Interferometer Space Antenna (LISA) will allow us to observe gravitational-wave signals from the mergers of massive black hole binaries (MBHBs) with signal-to-noise ratio (SNR) in the hundreds, or even thousands. At such high SNR, our ability to precisely infer the parameters of an MBHB from the detected signal will be limited by the accuracy of the waveform templates we use. In this paper, we explore the systematic biases that arise in parameter estimation if we use waveform templates that do not model radiation in higher-order multipoles. This is an important consideration for the large fraction of high-mass events expected to be observed with LISA. We examine how the biases change for MBHB events with different total masses, mass ratios, and inclination angles. We find that systematic biases due to insufficient mode content are severe for events with total redshifted mass $\gtrsim10^6\,M_\odot$. We then compare several methods of predicting such systematic biases without performing a full Bayesian parameter estimation. In particular, we show that through direct likelihood optimization it is possible to predict systematic biases with remarkable computational efficiency and accuracy. Finally, we devise a method to construct approximate waveforms including angular multipoles with $\ell\geq5$ to better understand how many additional modes (beyond the ones available in current approximants) might be required to perform unbiased parameter estimation on the MBHB signals detected by LISA.
In order to adapt to the issues of climate change and public health, urban policies are trying to encourage soft mobility, but the share of the car remains significant. Beyond known constraints, we study here the impact of perception biases on individual choices. We designed a multi-criteria decision model, integrating the influence of habits and biases. We then conducted an online survey, which received 650 responses. We used these to calculate realistic mobility perception values, in order to initialise the environment and the population of a modal choice simulator, implemented in Netlogo. This allows us to visualize the adaptation of the modal distribution in reaction to the evolution of urban planning, depending on whether or not we activate biases and habits in individual reasoning. This is an extended and translated version of a demo paper published in French at JFSMA-JFMS 2024 "Un simulateur multi-agent de choix modal subjectif"
The transition to a low-carbon economy necessitates effective carbon capture and storage (CCS) solutions, particularly for hard-to-abate sectors. Herein, pipeline networks are indispensable for cost-efficient $CO_2$ transportation over long distances. However, there is deep uncertainty regarding which industrial sectors will participate in such systems. This poses a significant challenge due to substantial investments as well as the lengthy planning and development timelines required for $CO_2$ pipeline projects, which are further constrained by limited upgrade options for already built infrastructure. The economies of scale inherent in pipeline construction exacerbate these challenges, leading to potential regret over earlier decisions. While numerous models were developed to optimize the initial layout of pipeline infrastructure based on known demand, a gap exists in addressing the incremental development of infrastructure in conjunction with deep uncertainty. Hence, this paper introduces a novel optimization model for $CO_2$ pipeline infrastructure development, minimizing regret as its objective function and incorporating various upgrade options, such as looping and pressure increases. The model's effectiveness is also demonstrated by presenting a comprehensive case study of Germany's cement and lime industries. The developed approach quantitatively illustrates the trade-off between different options, which can help in deriving effective strategies for $CO_2$ infrastructure development.
In this paper, we study the impact of reconfigurable intelligent surfaces (RISs) on the coverage extension of integrated access and backhaul (IAB) networks. Particularly, using a finite stochastic geometry model, with random distributions of user equipments (UEs) in a finite region, and planned hierachical architecture for IAB, we study the service coverage probability defined as the probability of the event that the UEs' minimum rate requirements are satisfied. We present comparisons between different cases including IAB-only, IAB assisted with RIS for backhaul as well as IAB assisted by network controlled repeaters (NCRs). Our investigations focus on wide-area IAB assisted with RIS through the lens of different design architectures and deployments, revealing both conflicts and synergies for minimizing the effect of tree foliage over seasonal changes. Our simulation results reveal both opportunities and challenges towards the implementation of RIS in IAB.
Experiments involving sensory analysis of foods and beverages are beneficial for selecting healthy products and assessing the preferences of potential consumers. They are generally planned in incomplete blocks, and their attributes, such as aroma, colour, and flavour, are evaluated using a 9-point hedonic scale, characterising an ordinal variable response. Also, the generalised logit model with random effects for panellists is one of the appropriate models to relate the multivariate response to the covariates. This study aims to present a method for analysing sensory attributes through a unified multivariate model. Due to the nature of the variable, each separate model already corresponds to a multivariate analysis, so our proposal would incorporate a complete analysis with solely one model. This proposal is based on multivariate methods for categorical data and maximum likelihood theory. Our method was evaluated through a simulation study, in which we consider three distinct formulations with two attributes to represent various formulation selection scenarios via mixed discrete models. The simulated results demonstrated overall concordance rates exceeding 80\% for the unified model compared to the separate models. Moreover, as motivation is presented, a study of 13 prebiotic beverages based on cashew nut almonds added to grape juice, with 130 potential consumers. The attributes evaluated were overall impression, aroma, Body, sweetness and flavour, using a 9-point hedonic scale. The selected unified model considering all attributes was the non-proportional odds mixed-effect model. According to this model, the prebiotic beverage formulations most likely to be accepted were: 8\% sugar and 40\% grape juice ($F_4$), 6\% sugar and 44\% grape juice ($F_6$), and 9\% sugar and 30\% grape juice ($F_{13}$). The unified analysis and computational time showed the advantages of this proposal.
This paper presents the full dynamic model of the UR10 industrial robot. A triple-stage identification approach is adopted to estimate the manipulator's dynamic coefficients. First, linear parameters are computed using a standard linear regression algorithm. Subsequently, nonlinear friction parameters are estimated according to a sigmoidal model. Lastly, motor drive gains are devised to map estimated joint currents to torques. The overall identified model can be used for both control and planning purposes, as the accompanied ROS2 software can be easily reconfigured to account for a generic payload. The estimated robot model is experimentally validated against a set of exciting trajectories and compared to the state-of-the-art model for the same manipulator, achieving higher current prediction accuracy (up to a factor of 4.43) and more precise motor gains. The related software is available at https://codeocean.com/capsule/8515919/tree/v2.
As artificial intelligence (AI) systems become increasingly integrated into critical domains, ensuring their responsible design and continuous development is imperative. Effective AI quality management (QM) requires tools and methodologies that address the complexities of the AI lifecycle. In this paper, we propose an approach for AI lifecycle planning that bridges the gap between generic guidelines and use case-specific requirements (MQG4AI). Our work aims to contribute to the development of practical tools for implementing Responsible AI (RAI) by aligning lifecycle planning with technical, ethical and regulatory demands. Central to our approach is the introduction of a flexible and customizable Methodology based on Quality Gates, whose building blocks incorporate RAI knowledge through information linking along the AI lifecycle in a continuous manner, addressing AIs evolutionary character. For our present contribution, we put a particular emphasis on the Explanation stage during model development, and illustrate how to align a guideline to evaluate the quality of explanations with MQG4AI, contributing to overall Transparency.
Human-robot collaboration (HRC) relies on accurate and timely recognition of human intentions to ensure seamless interactions. Among common HRC tasks, human-to-robot object handovers have been studied extensively for planning the robot's actions during object reception, assuming the human intention for object handover. However, distinguishing handover intentions from other actions has received limited attention. Most research on handovers has focused on visually detecting motion trajectories, which often results in delays or false detections when trajectories overlap. This paper investigates whether human intentions for object handovers are reflected in non-movement-based physiological signals. We conduct a multimodal analysis comparing three data modalities: electroencephalogram (EEG), gaze, and hand-motion signals. Our study aims to distinguish between handover-intended human motions and non-handover motions in an HRC setting, evaluating each modality's performance in predicting and classifying these actions before and after human movement initiation. We develop and evaluate human intention detectors based on these modalities, comparing their accuracy and timing in identifying handover intentions. To the best of our knowledge, this is the first study to systematically develop and test intention detectors across multiple modalities within the same experimental context of human-robot handovers. Our analysis reveals that handover intention can be detected from all three modalities. Nevertheless, gaze signals are the earliest as well as the most accurate to classify the motion as intended for handover or non-handover.
Learning tool use from a single human demonstration video offers a highly intuitive and efficient approach to robot teaching. While humans can effortlessly generalize a demonstrated tool manipulation skill to diverse tools that support the same function (e.g., pouring with a mug versus a teapot), current one-shot imitation learning (OSIL) methods struggle to achieve this. A key challenge lies in establishing functional correspondences between demonstration and test tools, considering significant geometric variations among tools with the same function (i.e., intra-function variations). To address this challenge, we propose FUNCTO (Function-Centric OSIL for Tool Manipulation), an OSIL method that establishes function-centric correspondences with a 3D functional keypoint representation, enabling robots to generalize tool manipulation skills from a single human demonstration video to novel tools with the same function despite significant intra-function variations. With this formulation, we factorize FUNCTO into three stages: (1) functional keypoint extraction, (2) function-centric correspondence establishment, and (3) functional keypoint-based action planning. We evaluate FUNCTO against exiting modular OSIL methods and end-to-end behavioral cloning methods through real-robot experiments on diverse tool manipulation tasks. The results demonstrate the superiority of FUNCTO when generalizing to novel tools with intra-function geometric variations. More details are available at https://sites.google.com/view/functo.
Generating natural language explanations for recommendations has become increasingly important in recommender systems. Traditional approaches typically treat user reviews as ground truth for explanations and focus on improving review prediction accuracy by designing various model architectures. However, due to limitations in data scale and model capability, these explanations often fail to meet key user-centric aspects such as factuality, personalization, and sentiment coherence, significantly reducing their overall helpfulness to users. In this paper, we propose a novel paradigm that refines initial explanations generated by existing explainable recommender models during the inference stage to enhance their quality in multiple aspects. Specifically, we introduce a multi-agent collaborative refinement framework based on large language models. To ensure alignment between the refinement process and user demands, we employ a plan-then-refine pattern to perform targeted modifications. To enable continuous improvements, we design a hierarchical reflection mechanism that provides feedback on the refinement process from both strategic and content perspectives. Extensive experiments on three datasets demonstrate the effectiveness of our framework.
The Location-Routing Problem (LRP), which combines the challenges of facility (depot) locating and vehicle route planning, is critically constrained by the reliance on predefined depot candidates, limiting the solution space and potentially leading to suboptimal outcomes. Previous research on LRP without predefined depots is scant and predominantly relies on heuristic algorithms that iteratively attempt depot placements across a planar area. Such approaches lack the ability to proactively generate depot locations that meet specific geographic requirements, revealing a notable gap in current research landscape. To bridge this gap, we propose a data-driven generative DRL framework, designed to proactively generate depots for LRP without predefined depot candidates, solely based on customer requests data which include geographic and demand information. It can operate in two distinct modes: direct generation of exact depot locations, and the creation of a multivariate Gaussian distribution for flexible depots sampling. By extracting depots' geographic pattern from customer requests data, our approach can dynamically respond to logistical needs, identifying high-quality depot locations that further reduce total routing costs compared to traditional methods. Extensive experiments demonstrate that, for a same group of customer requests, compared with those depots identified through random attempts, our framework can proactively generate depots that lead to superior solution routes with lower routing cost. The implications of our framework potentially extend into real-world applications, particularly in emergency medical rescue and disaster relief logistics, where rapid establishment and adjustment of depot locations are paramount, showcasing its potential in addressing LRP for dynamic and unpredictable environments.
The renewed global interest in lunar exploration requires new orbital strategies to ensure flight safety which can benefit extended lunar missions and service a plethora of planned instruments in the lunar orbit and surface. We investigate here the equivalent fuel consumption cost to transfer from (to) a given orbit and enter (leave) at any point of an invariant manifold associated with a Lyapunov orbit around the Earth-Moon $L_1$ Lagrangian point using bi-impulsive maneuvers. Whereas solving this type of transfer is generally computationally expensive, we simulate here tens of millions of transfers orbits, for different times of flight, Jacobi constants and spatial location on the manifold. We are able to reduce computational cost by taking advantage of the efficient procedure given by the Theory of Functional Connections for solving boundary value problems, represented with special constraints created to the purposes of this work. We develop here the methodology for constructing these transfers, and apply it to find a low-cost transfer from an orbit around the Earth to a stable manifold and another low-cost transfer from an unstable manifold to an orbit around the Moon. In the end, we obtain an innovative Earth-to-Moon transfer that involves a gravity assist maneuver with the Moon and allows a long stationed stage at the Lyapunov orbit around $L_1$ which can be used for designing multi-purpose missions for extended periods of time with low fuel costs. This is paramount to optimize new exploration concepts.
This study introduces and compares the Hankel dynamic mode decomposition with control (Hankel-DMDc) and a novel Bayesian extension of Hankel-DMDc as model-free (i.e., data-driven and equation-free) approaches for system identification and prediction of free-running ship motions in irregular waves. The proposed DMDc methods create a reduced-order model using limited data from the system state and incoming wave elevation histories, with the latter and rudder angle serving as forcing inputs. The inclusion of delayed states of the system as additional dimensions per the Hankel-DMDc improves the representation of the underlying non-linear dynamics of the system by DMD. The approaches are statistically assessed using data from free-running simulations of a 5415M hull's course-keeping in irregular beam-quartering waves at sea state 7, a highly severe condition characterized by nonlinear responses near roll-resonance. The results demonstrate robust performance and remarkable computational efficiency. The results indicate that the proposed methods effectively identify the dynamic system in analysis. Furthermore, the Bayesian formulation incorporates uncertainty quantification and enhances prediction accuracy. Ship motions are predicted with good agreement with test data over a 15 encounter waves observation window. No significant accuracy degradation is noted along the test sequences, suggesting the method can support accurate and efficient maritime design and operational planning.
Binarity in massive stars has proven to be an important aspect in the their evolution. For Be stars, it might be the cause of their spin up, and thus part of the mechanism behind the formation of their viscous decretion disks. Detecting companions in systems with Be stars is challenging, making it difficult to obtain observational constraints on their binary fraction. We explore the effects of a binary companion in a system with a Be star, from disk formation to quasi steady-state using smoothed particle hydrodynamics (SPH) simulations of coplanar, circular binary systems. High spatial resolution is achieved by adopting particle splitting in the SPH code, as well as a more realistic description of the secondary star and the disk viscosity. The tidal forces considerably affect the Be disk, forming distinct regions in the system, with observational consequences that can be used to infer the presence of a otherwise undetectable companion. With the upgraded code, we can probe a region approximately 4 times larger than previously possible. We describe the configuration and kinematics of each part of the system, and provide a summary of their expected observational signals. Material that enters the Roche lobe of the companion is partially captured by it, forming a rotationally supported, disk-like structure. Material not accreted escapes and forms a circumbinary disk around the system. This is the first work to describe the region beyond the truncation region of the Be disk and its observational consequences with detail. We argue that observational features of previously unclear origin, such as the intermittent shell features and emission features of HR 2142 and HD 55606, originate in areas beyond the truncation region. This new understanding of the behavior of disks in Be binaries will allow not just for better interpretation of existing data, but also for the planning of future observations.
Token-based world models emerged as a promising modular framework, modeling dynamics over token streams while optimizing tokenization separately. While successful in visual environments with discrete actions (e.g., Atari games), their broader applicability remains uncertain. In this paper, we introduce $\text{M}^{\text{3}}$, a $\textbf{m}$odular $\textbf{w}$orld $\textbf{m}$odel that extends this framework, enabling flexible combinations of observation and action modalities through independent modality-specific components. $\text{M}^{\text{3}}$ integrates several improvements from existing literature to enhance agent performance. Through extensive empirical evaluation across diverse benchmarks, $\text{M}^{\text{3}}$ achieves state-of-the-art sample efficiency for planning-free world models. Notably, among these methods, it is the first to reach a human-level median score on Atari 100K, with superhuman performance on 13 games. Our code and model weights are publicly available at https://github.com/leor-c/M3.
The China Space Station Telescope (CSST) is a forthcoming space-based optical telescope designed to co-orbit with the Chinese Space Station. With a planned slitless spectroscopic survey spanning a broad wavelength range of $255-1000$nm and an average spectral resolution exceeding 200, the CSST holds significant potential for cosmic large-scale structure analysis. In this study, we focus on redshift determinations from slitless spectra through emission line analysis within the CSST framework. Our tailored redshift measurement process involves identifying emission lines in one-dimensional slitless spectra, aligning observed wavelengths with their rest-frame counterparts from prominent galaxy emissions, and calculating wavelength shifts to determine redshifts accurately. To validate our redshift measurement algorithm, we leverage simulated spectra generated by the CSST emulator for slitless spectroscopy. The outcomes demonstrate a remarkable redshift completeness exceeding 95 per cent for emission line galaxies (ELGs), alongside a purity surpassing 85 per cent. The redshift uncertainty remains impressively below than $\sim 0.001$. Notably, when concentrating on galaxies with more than three matched emission lines, the completeness of ELGs and the purity of measurable galaxies can reach 98 per cent and 97 per cent, respectively. Furthermore, we explore the influence of parameters like magnitude, spectral signal-to-noise ratio, and redshift on redshift completeness and purity. The discussion also delves into redshift degeneracies stemming from emission-line matching confusion. Our developed redshift measurement process will be applied to extensive simulated datasets and forthcoming CSST slitless spectroscopic observations for further cosmological and extragalactic analyses.
In this work, we address the limitation of surface fitting-based grasp planning algorithm, which primarily focuses on geometric alignment between the gripper and object surface while overlooking the stability of contact point distribution, often resulting in unstable grasps due to inadequate contact configurations. To overcome this limitation, we propose a novel surface fitting algorithm that integrates contact stability while preserving geometric compatibility. Inspired by human grasping behavior, our method disentangles the grasp pose optimization into three sequential steps: (1) rotation optimization to align contact normals, (2) translation refinement to improve Center of Mass (CoM) alignment, and (3) gripper aperture adjustment to optimize contact point distribution. We validate our approach through simulations on ten YCB dataset objects, demonstrating an 80% improvement in grasp success over conventional surface fitting methods that disregard contact stability. Further details can be found on our project page: https://tomoya-yamanokuchi.github.io/disf-project-page/.
Embodied multi-agent systems (EMAS) have attracted growing attention for their potential to address complex, real-world challenges in areas such as logistics and robotics. Recent advances in foundation models pave the way for generative agents capable of richer communication and adaptive problem-solving. This survey provides a systematic examination of how EMAS can benefit from these generative capabilities. We propose a taxonomy that categorizes EMAS by system architectures and embodiment modalities, emphasizing how collaboration spans both physical and virtual contexts. Central building blocks, perception, planning, communication, and feedback, are then analyzed to illustrate how generative techniques bolster system robustness and flexibility. Through concrete examples, we demonstrate the transformative effects of integrating foundation models into embodied, multi-agent frameworks. Finally, we discuss challenges and future directions, underlining the significant promise of EMAS to reshape the landscape of AI-driven collaboration.
Transitioning to renewable power generation is often difficult for remote or isolated communities, due to generation intermittency and high cost barriers. Our paper presents a simulation-based optimization approach for the design of policy incentives and planning of microgrids with renewable energy sources, targeting isolated communities. We propose a novel framework that integrates stochastic simulation to account for weather uncertainty and system availability while optimizing microgrid configurations and policy incentives. Utilizing the mixed-variable Simultaneous Perturbation Stochastic Approximation (MSPSA) algorithm, our method demonstrates a significant reduction in Net Present Cost (NPC) for microgrids, achieving a 68.1% reduction in total costs in a case study conducted on Popova Island. The results indicate the effectiveness of our approach in enhancing the economic viability of microgrids while promoting cleaner energy solutions. Future research directions include refining uncertainty models and exploring applications in grid-connected microgrids.
In autonomous driving systems, motion planning is commonly implemented as a two-stage process: first, a trajectory proposer generates multiple candidate trajectories, then a scoring mechanism selects the most suitable trajectory for execution. For this critical selection stage, rule-based scoring mechanisms are particularly appealing as they can explicitly encode driving preferences, safety constraints, and traffic regulations in a formalized, human-understandable format. However, manually crafting these scoring rules presents significant challenges: the rules often contain complex interdependencies, require careful parameter tuning, and may not fully capture the nuances present in real-world driving data. This work introduces FLoRA, a novel framework that bridges this gap by learning interpretable scoring rules represented in temporal logic. Our method features a learnable logic structure that captures nuanced relationships across diverse driving scenarios, optimizing both rules and parameters directly from real-world driving demonstrations collected in NuPlan. Our approach effectively learns to evaluate driving behavior even though the training data only contains positive examples (successful driving demonstrations). Evaluations in closed-loop planning simulations demonstrate that our learned scoring rules outperform existing techniques, including expert-designed rules and neural network scoring models, while maintaining interpretability. This work introduces a data-driven approach to enhance the scoring mechanism in autonomous driving systems, designed as a plug-in module to seamlessly integrate with various trajectory proposers. Our video and code are available on xiong.zikang.me/FLoRA.
This paper proposes that Artificial Intelligence (AI) progresses through several overlapping generations: AI 1.0 (Information AI), AI 2.0 (Agentic AI), AI 3.0 (Physical AI), and now a speculative AI 4.0 (Conscious AI). Each of these AI generations is driven by shifting priorities among algorithms, computing power, and data. AI 1.0 ushered in breakthroughs in pattern recognition and information processing, fueling advances in computer vision, natural language processing, and recommendation systems. AI 2.0 built on these foundations through real-time decision-making in digital environments, leveraging reinforcement learning and adaptive planning for agentic AI applications. AI 3.0 extended intelligence into physical contexts, integrating robotics, autonomous vehicles, and sensor-fused control systems to act in uncertain real-world settings. Building on these developments, AI 4.0 puts forward the bold vision of self-directed AI capable of setting its own goals, orchestrating complex training regimens, and possibly exhibiting elements of machine consciousness. This paper traces the historical foundations of AI across roughly seventy years, mapping how changes in technological bottlenecks from algorithmic innovation to high-performance computing to specialized data, have spurred each generational leap. It further highlights the ongoing synergies among AI 1.0, 2.0, 3.0, and 4.0, and explores the profound ethical, regulatory, and philosophical challenges that arise when artificial systems approach (or aspire to) human-like autonomy. Ultimately, understanding these evolutions and their interdependencies is pivotal for guiding future research, crafting responsible governance, and ensuring that AI transformative potential benefits society as a whole.
Efficient Service Function Chain (SFC) provisioning and Virtual Network Function (VNF) placement are critical for enhancing network performance in modern architectures such as Software-Defined Networking (SDN) and Network Function Virtualization (NFV). While Deep Reinforcement Learning (DRL) aids decision-making in dynamic network environments, its reliance on structured inputs and predefined rules limits adaptability in unforeseen scenarios. Additionally, incorrect actions by a DRL agent may require numerous training iterations to correct, potentially reinforcing suboptimal policies and degrading performance. This paper integrates DRL with Language Models (LMs), specifically Bidirectional Encoder Representations from Transformers (BERT) and DistilBERT, to enhance network management. By feeding final VNF allocations from DRL into the LM, the system can process and respond to queries related to SFCs, DCs, and VNFs, enabling real-time insights into resource utilization, bottleneck detection, and future demand planning. The LMs are fine-tuned to our domain-specific dataset using Low-Rank Adaptation (LoRA). Results show that BERT outperforms DistilBERT with a lower test loss (0.28 compared to 0.36) and higher confidence (0.83 compared to 0.74), though BERT requires approximately 46% more processing time.
Our objective in this paper is to develop a machinery that makes a given organizational strategic plan resilient to the actions of competitor agents (adverse environmental actions). We assume that we are given a goal tree representing strategic goals (can also be seen business requirements for a software systems) with the assumption that competitor agents are behaving in a maximally adversarial fashion(opposing actions against our sub goals or goals in general). We use game tree search methods (such as minimax) to select an optimal execution strategy(at a given point in time), such that it can maximize our chances of achieving our (high level) strategic goals. Our machinery helps us determine which path to follow(strategy selection) to achieve the best end outcome. This is done by comparing alternative execution strategies available to us via an evaluation function. Our evaluation function is based on the idea that we want to make our execution plans defensible(future-proof) by selecting execution strategies that make us least vulnerable to adversarial actions by the competitor agents. i.e we want to select an execution strategy such that its leaves minimum room(or options) for the adversary to cause impediment/damage to our business goals/plans.
Today's global supply chains face growing challenges due to rapidly changing market conditions, increased network complexity and inter-dependency, and dynamic uncertainties in supply, demand, and other factors. To combat these challenges, organizations employ Material Requirements Planning (MRP) software solutions to set inventory stock buffers - for raw materials, work-in-process goods, and finished products - to help them meet customer service levels. However, holding excess inventory further complicates operations and can lock up millions of dollars of capital that could be otherwise deployed. Furthermore, most commercially available MRP solutions fall short in considering uncertainties and do not result in optimal solutions for modern enterprises. At C3 AI, we fundamentally reformulate the inventory management problem as a constrained stochastic optimization. We then propose a simulation-optimization framework that minimizes inventory and related costs while maintaining desired service levels. The framework's goal is to find the optimal reorder parameters that minimize costs subject to a pre-defined service-level constraint and all other real-world operational constraints. These optimal reorder parameters can be fed back into an MRP system to drive optimal order placement, or used to place optimal orders directly. This approach has proven successful in reducing inventory levels by 10-35 percent, resulting in hundreds of millions of dollars of economic benefit for major enterprises at a global scale.
In the astronomical observation field, determining the allocation of observation resources of the telescope array and planning follow-up observations for targets of opportunity (ToOs) are indispensable components of astronomical scientific discovery. This problem is computationally challenging, given the online observation setting and the abundance of time-varying factors that can affect whether an observation can be conducted. This paper presents ROARS, a reinforcement learning approach for online astronomical resource-constrained scheduling. To capture the structure of the astronomical observation scheduling, we depict every schedule using a directed acyclic graph (DAG), illustrating the dependency of timing between different observation tasks within the schedule. Deep reinforcement learning is used to learn a policy that can improve the feasible solution by iteratively local rewriting until convergence. It can solve the challenge of obtaining a complete solution directly from scratch in astronomical observation scenarios, due to the high computational complexity resulting from numerous spatial and temporal constraints. A simulation environment is developed based on real-world scenarios for experiments, to evaluate the effectiveness of our proposed scheduling approach. The experimental results show that ROARS surpasses 5 popular heuristics, adapts to various observation scenarios and learns effective strategies with hindsight.
Diffusion-based planning, learning, and control methods present a promising branch of powerful and expressive decision-making solutions. Given the growing interest, such methods have undergone numerous refinements over the past years. However, despite these advancements, existing methods are limited in their investigations regarding general methods for reward maximization within the decision-making process. In this work, we study extensions of fine-tuning approaches for control applications. Specifically, we explore extensions and various design choices for four fine-tuning approaches: reward alignment through reinforcement learning, direct preference optimization, supervised fine-tuning, and cascading diffusion. We optimize their usage to merge these independent efforts into one unified paradigm. We show the utility of such propositions in offline RL settings and demonstrate empirical improvements over a rich array of control tasks.
The co-design of robot morphology and neural control typically requires using reinforcement learning to approximate a unique control policy gradient for each body plan, demanding massive amounts of training data to measure the performance of each design. Here we show that a universal, morphology-agnostic controller can be rapidly and directly obtained by gradient-based optimization through differentiable simulation. This process of morphological pretraining allows the designer to explore non-differentiable changes to a robot's physical layout (e.g. adding, removing and recombining discrete body parts) and immediately determine which revisions are beneficial and which are deleterious using the pretrained model. We term this process "zero-shot evolution" and compare it with the simultaneous co-optimization of a universal controller alongside an evolving design population. We find the latter results in diversity collapse, a previously unknown pathology whereby the population -- and thus the controller's training data -- converges to similar designs that are easier to steer with a shared universal controller. We show that zero-shot evolution with a pretrained controller quickly yields a diversity of highly performant designs, and by fine-tuning the pretrained controller on the current population throughout evolution, diversity is not only preserved but significantly increased as superior performance is achieved.
Excess mortality, i.e. the difference between expected and observed mortality, is used to quantify the death toll of mortality shocks, such as infectious disease-related epidemics and pandemics. However, predictions of expected mortality are sensitive to model assumptions. Among three specifications of a Serfling-Poisson regression for seasonal mortality, we analyse which one yields the most accurate predictions. We compare the Serfling-Poisson models with: 1) parametric effect for the trend and seasonality (SP), 2) non-parametric effect for the trend and seasonality (SP-STSS), also known as modulation model, and 3) non-parametric effect for the trend and parametric effect for the seasonality (SP-STFS). Forecasting is achieved with P-splines smoothing. The SP-STFS model resulted in more accurate historical forecasts of monthly rates from national statistical offices in 25 European countries. An application to the COVID-19 pandemic years illustrates how excess mortality can be used to evaluate the vulnerability of populations and aid public health planning.
The unconditioned reflex (e.g., protective reflex), which is the innate reaction of the organism and usually performed through the spinal cord rather than the brain, can enable organisms to escape harms from environments. In this paper, we propose an online, highly-dynamic motion planning algorithm to endow manipulators the highly-dynamic unconditioned reflexes to humans and/or environments. Our method is based on a chained version of Signed Distance Functions (SDFs), which can be pre-computed and stored. Our proposed algorithm is divided into two stages. In the offline stage, we create 3 groups of local SDFs to store the geometric information of the manipulator and its working environment. In the online stage, the pre-computed local SDFs are chained together according the configuration of the manipulator, to provide global geometric information about the environment. While the point clouds of the dynamic objects serve as query points to look up these local SDFs for quickly generating escape velocity. Then we propose a modified geometric Jacobian matrix and use the Jacobian-pseudo-inverse method to generate real-time reflex behaviors to avoid the static and dynamic obstacles in the environment. The benefits of our method are validated in both static and dynamic scenarios. In the static scenario, our method identifies the path solutions with lower time consumption and shorter trajectory length compared to existing solutions. In the dynamic scenario, our method can reliably pursue the dynamic target point, avoid dynamic obstacles, and react to these obstacles within 1ms, which surpasses the unconditioned reflex reaction time of humans.
Semantic segmentation is an important task for autonomous driving. A powerful autonomous driving system should be capable of handling images under all conditions, including nighttime. Generating accurate and diverse nighttime semantic segmentation datasets is crucial for enhancing the performance of computer vision algorithms in low-light conditions. In this thesis, we introduce a novel approach named NPSim, which enables the simulation of realistic nighttime images from real daytime counterparts with monocular inverse rendering and ray tracing. NPSim comprises two key components: mesh reconstruction and relighting. The mesh reconstruction component generates an accurate representation of the scene structure by combining geometric information extracted from the input RGB image and semantic information from its corresponding semantic labels. The relighting component integrates real-world nighttime light sources and material characteristics to simulate the complex interplay of light and object surfaces under low-light conditions. The scope of this thesis mainly focuses on the implementation and evaluation of the mesh reconstruction component. Through experiments, we demonstrate the effectiveness of the mesh reconstruction component in producing high-quality scene meshes and their generality across different autonomous driving datasets. We also propose a detailed experiment plan for evaluating the entire pipeline, including both quantitative metrics in training state-of-the-art supervised and unsupervised semantic segmentation approaches and human perceptual studies, aiming to indicate the capability of our approach to generate realistic nighttime images and the value of our dataset in steering future progress in the field.
Human motion is stochastic and ensuring safe robot navigation in a pedestrian-rich environment requires proactive decision-making. Past research relied on incorporating deterministic future states of surrounding pedestrians which can be overconfident leading to unsafe robot behaviour. The current paper proposes a predictive uncertainty-aware planner that integrates neural network based probabilistic trajectory prediction into planning. Our method uses a deep ensemble based network for probabilistic forecasting of surrounding humans and integrates the predictive uncertainty as constraints into the planner. We compare numerous constraint satisfaction methods on the planner and evaluated its performance on real world pedestrian datasets. Further, offline robot navigation was carried out on out-of-distribution pedestrian trajectories inside a narrow corridor
Compositionally graded alloys (CGAs) are often proposed for use in structural components where the combination of two or more alloys within a single part can yield substantial enhancement in performance and functionality. For these applications, numerous design methodologies have been developed, one of the most sophisticated being the application of path planning algorithms originally designed for robotics to solve CGA design problems. In addition to the traditional application to structural components, this work proposes and demonstrates the application of this CGA design framework to rapid alloy design, synthesis, and characterization. A composition gradient in the CoCrFeNi alloy space was planned between the maximum and minimum stacking fault energy (SFE) as predicted by a previously developed model in a face-centered cubic (FCC) high entropy alloy (HEA) space. The path was designed to be monotonic in SFE and avoid regions that did not meet FCC phase fraction and solidification range constraints predicted by CALculation of PHAse Diagrams (CALPHAD). Compositions from the path were selected to produce a linear gradient in SFE, and the CGA was built using laser directed energy deposition (L-DED). The resulting gradient was characterized for microstructure and mechanical properties, including hardness, elastic modulus, and strain rate sensitivity. Despite being predicted to contain a single FCC phase throughout the gradient, part of the CGA underwent a martensitic transformation, thereby demonstrating a limitation of using equilibrium CALPHAD calculations for phase stability predictions. More broadly, this demonstrates the ability of the methods employed to bring attention to blind spots in alloy models.
In this article, we are interested in planning problems where the agent is aware of the presence of an observer, and where this observer is in a partial observability situation. The agent has to choose its strategy so as to optimize the information transmitted by observations. Building on observer-aware Markov decision processes (OAMDPs), we propose a framework to handle this type of problems and thus formalize properties such as legibility, explicability and predictability. This extension of OAMDPs to partial observability can not only handle more realistic problems, but also permits considering dynamic hidden variables of interest. These dynamic target variables allow, for instance, working with predictability, or with legibility problems where the goal might change during execution. We discuss theoretical properties of PO-OAMDPs and, experimenting with benchmark problems, we analyze HSVI's convergence behavior with dedicated initializations and study the resulting strategies.
This work establishes the technical fundamentals of a well-tuned Customizable Contraction Hierarchies (CCH) implementation that is simple and elegant. We give a detailed overview of the state of the art of CCH, review recent advances on CCH and show how to combine them. Additionally, we propose further refinements that improve the performance of CCH. An extensive evaluation confirms that a CCH framework is not only comprehensive in supported features but also competitive in performance to both Contraction Hierarchies (CH) and Customizable Route Planning (CRP).
Blockchain and Cloud Computing are two of the main topics related to the distributed computing paradigm, and in the last decade, they have seen exponential growth in their adoption. Cloud computing has long been established as the main mechanism to test, develop, and deliver new applications and services in a distributed manner across the World Wide Web. Large data centers host many services and store petabytes of user data. Infrastructure and services owners rule the access to data and may even be able to change contents and attest to its veracity. Blockchain is a step towards a future where the user's data are considered safer, besides being public. Advances in blockchain-based technologies, now, support service provisioning over permissioned and private infrastructures. Therefore, organizations or groups of individuals may share information, service even if they do not trust each other, besides supporting infrastructure management tasks. This paper presents and evaluates models for assessing the availability and capacity-oriented availability of cloud computing infrastructures. It aims at running Blockchain's distributed applications based on the Ethereum blockchain platform and the required expenses to perform service delivery in public and private infrastructures. Most of the obtained results also apply to other blockchains based platforms.
Hyperledger Fabric is a platform for permissioned blockchain networks that enables secure and auditable distributed data storage for enterprise applications. There is a growing interest in applications based on this platform, but its use requires the configuration of different blockchain parameters. Various configurations impact the system's non-functional qualities, especially performance and cost. In this article, we propose a Stochastic Petri Net to model the performance of the Hyperledger Fabric platform with different blockchain parameters, computer capacity, and transaction rates. We also present a set of case studies to demonstrate the feasibility of the proposed model. This model serves as a practical guide to help administrators of permissioned blockchain networks find the best performance for their applications. The proposed model allowed us to identify the block size that leads to a high mean response time (ranging from 1 to 25 seconds) caused by a change in the arrival rate.
Antibodies are widely used as therapeutics, but their development requires costly affinity maturation, involving iterative mutations to enhance binding affinity.This paper explores a sequence-only scenario for affinity maturation, using solely antibody and antigen sequences. Recently AlphaFlow wraps AlphaFold within flow matching to generate diverse protein structures, enabling a sequence-conditioned generative model of structure. Building on this, we propose an alternating optimization framework that (1) fixes the sequence to guide structure generation toward high binding affinity using a structure-based affinity predictor, then (2) applies inverse folding to create sequence mutations, refined by a sequence-based affinity predictor for post selection. A key challenge is the lack of labeled data for training both predictors. To address this, we develop a co-teaching module that incorporates valuable information from noisy biophysical energies into predictor refinement. The sequence-based predictor selects consensus samples to teach the structure-based predictor, and vice versa. Our method, AffinityFlow, achieves state-of-the-art performance in affinity maturation experiments. We plan to open-source our code after acceptance.
Classically, planning tasks are studied as a two-step process: plan creation and plan execution. In situations where plan creation is slow (for example, due to expensive information access or complex constraints), a natural speed-up tactic is interleaving planning and execution. We implement such an approach with an enumeration algorithm that, after little preprocessing time, outputs parts of a plan one by one with little delay in-between consecutive outputs. As concrete planning task, we consider efficient connectivity in a network formalized as the minimum spanning tree problem in all four standard variants: (un)weighted (un)directed graphs. Solution parts to be emitted one by one for this concrete task are the individual edges that form the final tree. We show with algorithmic upper bounds and matching unconditional adversary lower bounds that efficient enumeration is possible for three of four problem variants; specifically for undirected unweighted graphs (delay in the order of the average degree), as well as graphs with either weights (delay in the order of the maximum degree and the average runtime per emitted edge of a total-time algorithm) or directions (delay in the order of the maximum degree). For graphs with both weighted and directed edges, we show that no meaningful enumeration is possible. Finally, with experiments on random undirected unweighted graphs, we show that the theoretical advantage of little preprocessing and delay carries over to practice.
A key objective of embodied intelligence is enabling agents to perform long-horizon tasks in dynamic environments while maintaining robust decision-making and adaptability. To achieve this goal, we propose the Spatio-Temporal Memory Agent (STMA), a novel framework designed to enhance task planning and execution by integrating spatio-temporal memory. STMA is built upon three critical components: (1) a spatio-temporal memory module that captures historical and environmental changes in real time, (2) a dynamic knowledge graph that facilitates adaptive spatial reasoning, and (3) a planner-critic mechanism that iteratively refines task strategies. We evaluate STMA in the TextWorld environment on 32 tasks, involving multi-step planning and exploration under varying levels of complexity. Experimental results demonstrate that STMA achieves a 31.25% improvement in success rate and a 24.7% increase in average score compared to the state-of-the-art model. The results highlight the effectiveness of spatio-temporal memory in advancing the memory capabilities of embodied agents.
Effective planning is crucial for navigating complex environments and achieving goals efficiently. In this study, we investigated how environmental structure influences the selection of planning strategies. Participants navigated a space station to collect colored spheres, with environments either structured (spheres grouped by color) or unstructured (spheres scattered randomly). We tested three types of plans: hierarchical (grouping spheres by color), shortest path (minimizing travel distance), and neutral (none of the above). By manipulating environmental structure, we were able to nudge participants toward a preference for hierarchical planning in structured environments, while shortest path plans were favored in unstructured environments. A mismatch between self-reported preferences and actual choices indicated that participants often adopted implicit strategies, unaware of their decision-making processes. These findings highlight the powerful effect of environmental cues on planning and suggest that even subtle changes in structure can guide the selection of planning strategies.
Humans possess an extraordinary ability to understand and execute complex manipulation tasks by interpreting abstract instruction manuals. For robots, however, this capability remains a substantial challenge, as they cannot interpret abstract instructions and translate them into executable actions. In this paper, we present Manual2Skill, a novel framework that enables robots to perform complex assembly tasks guided by high-level manual instructions. Our approach leverages a Vision-Language Model (VLM) to extract structured information from instructional images and then uses this information to construct hierarchical assembly graphs. These graphs represent parts, subassemblies, and the relationships between them. To facilitate task execution, a pose estimation model predicts the relative 6D poses of components at each assembly step. At the same time, a motion planning module generates actionable sequences for real-world robotic implementation. We demonstrate the effectiveness of Manual2Skill by successfully assembling several real-world IKEA furniture items. This application highlights its ability to manage long-horizon manipulation tasks with both efficiency and precision, significantly enhancing the practicality of robot learning from instruction manuals. This work marks a step forward in advancing robotic systems capable of understanding and executing complex manipulation tasks in a manner akin to human capabilities.
In software engineering, the concept of a ``feature'' is widely used but inconsistently defined across disciplines such as requirements engineering (RE) and software product lines (SPL). This lack of consistency often results in communication gaps, rework, and inefficiencies in projects. To address these challenges, this paper proposes an empirical, data-driven approach to explore how features are described, implemented, and managed across real-world projects, starting with open-source software (OSS). By analyzing feature-related branches in OSS repositories, we identify patterns in contributor behavior, feature implementation, and project management activities. Our findings provide actionable insights to improve project planning, resource allocation, and team coordination. Additionally, we outline a roadmap to unify the understanding of features across software engineering disciplines. This research aims to bridge gaps between academic inquiry and practical strategies, fostering better feature planning and development workflows in diverse project environments.
Differentiable simulators have recently shown great promise for training autonomous vehicle controllers. Being able to backpropagate through them, they can be placed into an end-to-end training loop where their known dynamics turn into useful priors for the policy to learn, removing the typical black box assumption of the environment. So far, these systems have only been used to train policies. However, this is not the end of the story in terms of what they can offer. Here, for the first time, we use them to train world models. Specifically, we present three new task setups that allow us to learn next state predictors, optimal planners, and optimal inverse states. Unlike analytic policy gradients (APG), which requires the gradient of the next simulator state with respect to the current actions, our proposed setups rely on the gradient of the next state with respect to the current state. We call this approach Analytic World Models (AWMs) and showcase its applications, including how to use it for planning in the Waymax simulator. Apart from pushing the limits of what is possible with such simulators, we offer an improved training recipe that increases performance on the large-scale Waymo Open Motion dataset by up to 12% compared to baselines at essentially no additional cost.
Interactive decision-making is essential in applications such as autonomous driving, where the agent must infer the behavior of nearby human drivers while planning in real-time. Traditional predict-then-act frameworks are often insufficient or inefficient because accurate inference of human behavior requires a continuous interaction rather than isolated prediction. To address this, we propose an active learning framework in which we rigorously derive predicted belief distributions. Additionally, we introduce a novel model-based diffusion solver tailored for online receding horizon control problems, demonstrated through a complex, non-convex highway merging scenario. Our approach extends previous high-fidelity dual control simulations to hardware experiments, which may be viewed at https://youtu.be/Q_JdZuopGL4, and verifies behavior inference in human-driven traffic scenarios, moving beyond idealized models. The results show improvements in adaptive planning under uncertainty, advancing the field of interactive decision-making for real-world applications.
Context. (3200) Phaethon is a ~5-km-diameter near-Earth asteroid with a small perihelion distance of 0.14 au and is the parent body of the Geminids. JAXA's DESTINY+ mission will fly by Phaethon in the near future. Aims. We aim to support the pre-flight planning for the DESTINY+ mission by performing a geophysical analysis on Phaethon's surface and near-surface environment utilizing the latest shape model from numerous observations. Methods. We employed the soft-sphere discrete element method code PKDGRAV to construct a "mascon" model of Phaethon and determine its gravity. We then computed the geopotential on Phaethon and derived various physical quantities related to its surface and near-surface dynamics. Results. We calculated geophysical quantities for the surface, including surface acceleration and slope. To assess whether surface objects could be launched off the surface, we computed the escape speed, return speed, Jacobi speed, and the location and stability of equilibrium points around Phaethon, and conducted a simple dynamical simulation of launched particles. Conclusions. Our results suggest that a large depression feature in the northern hemisphere could harbor exposed subsurface material and the freshest material on Phaethon. We propose that this depression be considered a key area for observation by the DESTINY+ mission
Effective parking management is essential for ensuring accessibility, safety, and convenience in master-planned communities, particularly in active adult neighborhoods experiencing rapid growth. Accurately assessing parking utilization is a crucial first step in planning for future demand, but data collection methods can be costly and labor-intensive. This paper presents a low-cost yet highly accurate methodology for measuring parking utilization using road tubes connected to portable traffic counters from JAMAR Technologies, Inc. By integrating results from JAMAR's analysis tool with custom Python scripting, the methodology enables precise parking lot counts through parameter optimization and automated error correction. The system's efficiency allows for scalable deployment without significant manual observation, reducing both costs and disruptions to daily operations. Using Tellico Village as a case study, this research demonstrates that community planners can obtain actionable parking insights on a limited budget, empowering them to make informed decisions about capacity expansion, traffic flow improvements, and facility scheduling. The findings underscore the feasibility of leveraging cost-effective technology to optimize infrastructure planning and ensure long-term resident satisfaction as communities grow.
Weak interactions in neutron $\beta$-decay exhibit parity violation through the preferential emission of right-handed antineutrinos. We identify this symmetry breaking with a reduction of phase space due to the small neutrino mass. During a brief interval of momentum exchange, a small mass neutrino puts the emission process close to the bifurcation horizon of Rindler space, doubly covered by Minkowski space ${\cal M}$ as dictated by the Equivalence Principle of general relativity. In the limit of arbitrarily small mass, this two-sheet covering effectively collapses into a single sheet, reducing the dimension of Dirac spinors from four to two, leaving neutrinos single-handed. This predicts a similar reduction to single-handed particle states in electrons created at TeV energies, which may be tested with the planned linear leptonic colliders. If confirmed, right-handed small mass neutrinos are expected to exist at sufficiently low energies.
The bicuspid aortic valve (BAV) is the most prevalent congenital heart defect and may require surgery for complications such as stenosis, regurgitation, and aortopathy. BAV repair surgery is effective but challenging due to the heterogeneity of BAV morphology. Multiple imaging modalities can be employed to assist the quantitative assessment of BAVs for surgical planning. Contrast-enhanced 4D computed tomography (CT) produces volumetric temporal sequences with excellent contrast and spatial resolution. Segmentation of the aortic cusps and root in these images is an essential step in creating patient specific models for visualization and quantification. While deep learning-based methods are capable of fully automated segmentation, no BAV-specific model exists. Among valve segmentation studies, there has been limited quantitative assessment of the clinical usability of the segmentation results. In this work, we developed a fully automated multi-label BAV segmentation pipeline based on nnU-Net. The predicted segmentations were used to carry out surgically relevant morphological measurements including geometric cusp height, commissural angle and annulus diameter, and the results were compared against manual segmentation. Automated segmentation achieved average Dice scores of over 0.7 and symmetric mean distance below 0.7 mm for all three aortic cusps and the root wall. Clinically relevant benchmarks showed good consistency between manual and predicted segmentations. Overall, fully automated BAV segmentation of 3D frames in 4D CT can produce clinically usable measurements for surgical risk stratification, but the temporal consistency of segmentations needs to be improved.
This comprehensive survey examines the integration of knowledge-based approaches into autonomous driving systems, with a focus on trajectory prediction and planning. We systematically review methodologies for incorporating domain knowledge, traffic rules, and commonsense reasoning into these systems, spanning purely symbolic representations to hybrid neuro-symbolic architectures. In particular, we analyze recent advancements in formal logic and differential logic programming, reinforcement learning frameworks, and emerging techniques that leverage large foundation models and diffusion models for knowledge representation. Organized under a unified literature survey section, our discussion synthesizes the state-of-the-art into a high-level overview, supported by a detailed comparative table that maps key works to their respective methodological categories. This survey not only highlights current trends -- including the growing emphasis on interpretable AI, formal verification in safety-critical systems, and the increased use of generative models in prediction and planning -- but also outlines the challenges and opportunities for developing robust, knowledge-enhanced autonomous driving systems.
Autonomous agents are often required to plan under multiple objectives whose preference ordering varies based on context. The agent may encounter multiple contexts during its course of operation, each imposing a distinct lexicographic ordering over the objectives, with potentially different reward functions associated with each context. Existing approaches to multi-objective planning typically consider a single preference ordering over the objectives, across the state space, and do not support planning under multiple objective orderings within an environment. We present Contextual Lexicographic Markov Decision Process (CLMDP), a framework that enables planning under varying lexicographic objective orderings, depending on the context. In a CLMDP, both the objective ordering at a state and the associated reward functions are determined by the context. We employ a Bayesian approach to infer a state-context mapping from expert trajectories. Our algorithm to solve a CLMDP first computes a policy for each objective ordering and then combines them into a single context-aware policy that is valid and cycle-free. The effectiveness of the proposed approach is evaluated in simulation and using a mobile robot.
The Variational Quantum Eigensolver (VQE) is a promising algorithm for quantum computing applications in chemistry and materials science, particularly in addressing the limitations of classical methods for complex systems. This study benchmarks the performance of the VQE for calculating ground-state energies of aluminum clusters (Al$^-$, Al$_2$, and Al$_3^-$) within a quantum-density functional theory (DFT) embedding framework, systematically varying key parameters -- (I) classical optimizers, (II) circuit types, (III) number of repetitions, (IV) simulator types, (V) basis sets, and (VI) noise models. Our findings demonstrate that certain optimizers achieve efficient and accurate convergence, while circuit choice and basis set selection significantly impact accuracy, with higher-level basis sets closely matching classical computation data from Numerical Python Solver (NumPy) and Computational Chemistry Comparison and Benchmark DataBase (CCCBDB). To evaluate the workflow under realistic conditions, we employed IBM noise models to simulate the effects of hardware noise. The results showed close agreement with CCCBDB benchmarks, with percent errors consistently below 0.2 percent. The results establish VQE's capability for reliable energy estimations and highlight the importance of optimizing quantum-DFT parameters to balance computational cost and precision. This work paves the way for broader VQE benchmarking on diverse chemical systems, with plans to make results accessible on Joint Automated Repository for Various Integrated Simulations (JARVIS) and develop a Python package to support the quantum chemistry and materials science communities in advancing quantum-enhanced discovery.
Realistic driving simulation requires that NPCs not only mimic natural driving behaviors but also react to the behavior of other simulated agents. Recent developments in diffusion-based scenario generation focus on creating diverse and realistic traffic scenarios by jointly modelling the motion of all the agents in the scene. However, these traffic scenarios do not react when the motion of agents deviates from their modelled trajectories. For example, the ego-agent can be controlled by a stand along motion planner. To produce reactive scenarios with joint scenario models, the model must regenerate the scenario at each timestep based on new observations in a Model Predictive Control (MPC) fashion. Although reactive, this method is time-consuming, as one complete possible future for all NPCs is generated per simulation step. Alternatively, one can utilize an autoregressive model (AR) to predict only the immediate next-step future for all NPCs. Although faster, this method lacks the capability for advanced planning. We present a rolling diffusion based traffic scene generation model which mixes the benefits of both methods by predicting the next step future and simultaneously predicting partially noised further future steps at the same time. We show that such model is efficient compared to diffusion model based AR, achieving a beneficial compromise between reactivity and computational efficiency.
Traffic safety is a critical concern in transportation engineering and urban planning. Traditional traffic safety analysis requires trained observers to collect data in the field, which is time-consuming, labor-intensive, and sometimes inaccurate. In recent years, microscopic traffic simulation, which simulates individual vehicles' movements within a transportation network, have been utilized to study traffic safety. However, microscopic traffic simulation only focuses on traffic-related factors, such as traffic volume, traffic signals, and lane configurations, neglecting vehicle dynamics and environment-related factors like weather and lighting conditions, which can significantly impact traffic safety. In light of this, this paper explores the application of digital twin technology in traffic safety analysis, integrating vehicle simulators, which consider vehicle dynamics and environmental factors, and microscopic traffic simulators, which simulate the operations of traffic flow, for enhanced safety evaluations. Various scenarios, including different weather conditions and visibility levels, are simulated using a digital twin of a road segment in Tuscaloosa, Alabama. The simulations employ Surrogate Safety Measures (SSMs) like Time to Collision (TTC) and Deceleration Rate to Avoid a Crash (DRAC) to assess safety under varying conditions. The results demonstrate that traffic digital twin can identify potential safety issues that traditional microscopic simulation cannot, providing insights for improving traffic control strategies and transportation infrastructure to enhance traffic safety.
Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents remain underexplored due to the lack of comprehensive evaluation frameworks. To bridge this gap, we introduce EmbodiedBench, an extensive benchmark designed to evaluate vision-driven embodied agents. EmbodiedBench features: (1) a diverse set of 1,128 testing tasks across four environments, ranging from high-level semantic tasks (e.g., household) to low-level tasks involving atomic actions (e.g., navigation and manipulation); and (2) six meticulously curated subsets evaluating essential agent capabilities like commonsense reasoning, complex instruction understanding, spatial awareness, visual perception, and long-term planning. Through extensive experiments, we evaluated 19 leading proprietary and open-source MLLMs within EmbodiedBench. Our findings reveal that: MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only 28.9% on average. EmbodiedBench provides a multifaceted standardized evaluation platform that not only highlights existing challenges but also offers valuable insights to advance MLLM-based embodied agents. Our code is available at https://embodiedbench.github.io.
This paper proposes the Real-Time Fast Marching Tree (RT-FMT), a real-time planning algorithm that features local and global path generation, multiple-query planning, and dynamic obstacle avoidance. During the search, RT-FMT quickly looks for the global solution and, in the meantime, generates local paths that can be used by the robot to start execution faster. In addition, our algorithm constantly rewires the tree to keep branches from forming inside the dynamic obstacles and to maintain the tree root near the robot, which allows the tree to be reused multiple times for different goals. Our algorithm is based on the planners Fast Marching Tree (FMT*) and Real-time Rapidly-Exploring Random Tree (RT-RRT*). We show via simulations that RT-FMT outperforms RT- RRT* in both execution cost and arrival time, in most cases. Moreover, we also demonstrate via simulation that it is worthwhile taking the local path before the global path is available in order to reduce arrival time, even though there is a small possibility of taking an inferior path.
Many pharmaceutical companies face concerns with the maintenance of desired revenue levels. Sales forecasts for the current portfolio of products and projects may indicate a decline in revenue as the marketed products approach patent expiry. To counteract the potential downturn in revenue, and to establish revenue growth, an in-flow of new projects into the development phases is required. In this article, we devise an approach with which the in-flow of new projects could be optimized, while adhering to the objectives and constraints set on revenue targets, budget limitations and strategic considerations on the composition of the company's portfolio.
Among all public transit modes, bus transit systems stand out as the most prevalent and popular. This prominence has spurred a significant body of research addressing various aspects of bus systems. In the literature, analytical approaches and mathematical programming are predominantly used to explore the Public Bus Transit Network Design Problem and Operations Planning (PBTNDP&OP). Part I of our study presented statistical analyses of literature applying these methodologies to PBTNDP&OP, along with a comprehensive review of analytical papers, highlighting the strengths and weaknesses of each approach. In Part II, we delve into the applications of mathematical programming within PBTNDP&OP, building upon the 15 major sub-categories identified in Part I. We have critically analyzed the identified papers within these sub-categories from various perspectives, including the problems investigated, modeling methods employed, decision variables, network structures, and key findings. This critical review highlights selected papers in each category. Finally, acknowledging existing research gaps, we propose potential extensions for future research. Despite the extensive array of publications, numerous topics still warrant further exploration. Notably, sustainable PBTNDP&OP and challenges associated with integrating emerging technologies are poised to dominate future research agendas.
The Public Bus Transit Network Design Problem and Operations Planning (PBTNDP&OP) remains a core research area within transportation, in particular, because of the emergence of new transit technologies and services. Analytical approaches and mathematical programming are the most commonly applied methodologies to study this problem. Many studies utilize either of these two methods, often viewed as competing due to the unique benefits each provides that the other does not. This two-part paper systematically reviews the application of analytical approaches and mathematical programming in PBTNDP&OP, analyzing publications from 1968 to 2021. It begins by comparing analytical methods and mathematical programming through various statistical analyses, including the number of published papers, the most active journals and authors, keyword frequencies, keyword co-occurrence maps, and co-authorship maps. Subsequent analysis of the identified papers includes examinations from multiple perspectives: the problems investigated, modeling methods used, decision variables considered, network structures, and key findings. This is followed by a critical review of selected papers. The paper concludes by discussing the advantages and disadvantages of each approach and suggests potential extensions for future research based on identified gaps in existing studies.
In this paper we address the speed planning problem for a vehicle over an assigned path with the aim of minimizing a weighted sum of travel time and energy consumption under suitable constraints (maximum allowed speed, maximum traction or braking force, maximum power consumption). The resulting mathematical model is a non--convex optimization problem. We prove that, under some mild assumptions, a convex reformulation of the non--convex problem is exact. In particular, the convex reformulation is a Second Order Cone Programming (SOCP) problem, for which efficient solvers exist. Through the numerical experiments we confirm that the convex relaxation can be solved very efficiently and, moreover, we also provide the Pareto front of the trade-off between the two objectives (travel time and energy consumption).
Real-time autonomous systems utilize multi-layer computational frameworks to perform critical tasks such as perception, goal finding, and path planning. Traditional methods implement perception using occupancy grid mapping (OGM), segmenting the environment into discretized cells with probabilistic information. This classical approach is well-established and provides a structured input for downstream processes like goal finding and path planning algorithms. Recent approaches leverage a biologically inspired mathematical framework known as vector symbolic architectures (VSA), commonly known as hyperdimensional computing, to perform probabilistic OGM in hyperdimensional space. This approach, VSA-OGM, provides native compatibility with spiking neural networks, positioning VSA-OGM as a potential neuromorphic alternative to conventional OGM. However, for large-scale integration, it is essential to assess the performance implications of VSA-OGM on downstream tasks compared to established OGM methods. This study examines the efficacy of VSA-OGM against a traditional OGM approach, Bayesian Hilbert Maps (BHM), within reinforcement learning based goal finding and path planning frameworks, across a controlled exploration environment and an autonomous driving scenario inspired by the F1-Tenth challenge. Our results demonstrate that VSA-OGM maintains comparable learning performance across single and multi-scenario training configurations while improving performance on unseen environments by approximately 47%. These findings highlight the increased generalizability of policy networks trained with VSA-OGM over BHM, reinforcing its potential for real-world deployment in diverse environments.
The increasing complexity of natural disaster incidents demands innovative technological solutions to support first responders in their efforts. This paper introduces the TRIFFID system, a comprehensive technical framework that integrates unmanned ground and aerial vehicles with advanced artificial intelligence functionalities to enhance disaster response capabilities across wildfires, urban floods, and post-earthquake search and rescue missions. By leveraging state-of-the-art autonomous navigation, semantic perception, and human-robot interaction technologies, TRIFFID provides a sophisticated system composed of the following key components: hybrid robotic platform, centralized ground station, custom communication infrastructure, and smartphone application. The defined research and development activities demonstrate how deep neural networks, knowledge graphs, and multimodal information fusion can enable robots to autonomously navigate and analyze disaster environments, reducing personnel risks and accelerating response times. The proposed system enhances emergency response teams by providing advanced mission planning, safety monitoring, and adaptive task execution capabilities. Moreover, it ensures real-time situational awareness and operational support in complex and risky situations, facilitating rapid and precise information collection and coordinated actions.
Federated Learning (FL) offers a pioneering distributed learning paradigm that enables devices/clients to build a shared global model. This global model is obtained through frequent model transmissions between clients and a central server, which may cause high latency, energy consumption, and congestion over backhaul links. To overcome these drawbacks, Hierarchical Federated Learning (HFL) has emerged, which organizes clients into multiple clusters and utilizes edge nodes (e.g., edge servers) for intermediate model aggregations between clients and the central server. Current research on HFL mainly focus on enhancing model accuracy, latency, and energy consumption in scenarios with a stable/fixed set of clients. However, addressing the dynamic availability of clients -- a critical aspect of real-world scenarios -- remains underexplored. This study delves into optimizing client selection and client-to-edge associations in HFL under intermittent client participation so as to minimize overall system costs (i.e., delay and energy), while achieving fast model convergence. We unveil that achieving this goal involves solving a complex NP-hard problem. To tackle this, we propose a stagewise methodology that splits the solution into two stages, referred to as Plan A and Plan B. Plan A focuses on identifying long-term clients with high chance of participation in subsequent model training rounds. Plan B serves as a backup, selecting alternative clients when long-term clients are unavailable during model training rounds. This stagewise methodology offers a fresh perspective on client selection that can enhance both HFL and conventional FL via enabling low-overhead decision-making processes. Through evaluations on MNIST and CIFAR-10 datasets, we show that our methodology outperforms existing benchmarks in terms of model accuracy and system costs.
The traditional heat-load generation pattern of combined heat and power generators has become a problem leading to renewable energy source (RES) power curtailment in cold regions, motivating the proposal of a planning model for alternative heat sources. The model aims to identify non-dominant capacity allocation schemes for heat pumps, thermal energy storage, electric boilers, and combined storage heaters to construct a Pareto front, considering both economic and sustainable objectives. The integration of various heat sources from both generation and consumption sides enhances flexibility in utilization. The study introduces a novel optimization algorithm, the adaptive multi-objective Bayesian optimization (AMBO). Compared to other widely used multi-objective optimization algorithms, AMBO eliminates predefined parameters that may introduce subjectivity from planners. Beyond the algorithm, the proposed model incorporates a noise term to account for inevitable simulation deviations, enabling the identification of better-performing planning results that meet the unique requirements of cold regions. What's more, the characteristics of electric-thermal coupling scenarios are captured and reflected in the operation simulation model to make sure the simulation is close to reality. Numerical simulation verifies the superiority of the proposed approach in generating a more diverse and evenly distributed Pareto front in a sample-efficient manner, providing comprehensive and objective planning choices.
With the rapid development of embodied artificial intelligence, significant progress has been made in vision-language-action (VLA) models for general robot decision-making. However, the majority of existing VLAs fail to account for the inevitable external perturbations encountered during deployment. These perturbations introduce unforeseen state information to the VLA, resulting in inaccurate actions and consequently, a significant decline in generalization performance. The classic internal model control (IMC) principle demonstrates that a closed-loop system with an internal model that includes external input signals can accurately track the reference input and effectively offset the disturbance. We propose a novel closed-loop VLA method GEVRM that integrates the IMC principle to enhance the robustness of robot visual manipulation. The text-guided video generation model in GEVRM can generate highly expressive future visual planning goals. Simultaneously, we evaluate perturbations by simulating responses, which are called internal embeddings and optimized through prototype contrastive learning. This allows the model to implicitly infer and distinguish perturbations from the external environment. The proposed GEVRM achieves state-of-the-art performance on both standard and perturbed CALVIN benchmarks and shows significant improvements in realistic robot tasks.
The hemorrhagic lesion segmentation plays a critical role in ophthalmic diagnosis, directly influencing early disease detection, treatment planning, and therapeutic efficacy evaluation. However, the task faces significant challenges due to lesion morphological variability, indistinct boundaries, and low contrast with background tissues. To improve diagnostic accuracy and treatment outcomes, developing advanced segmentation techniques remains imperative. This paper proposes an adversarial learning-based dynamic architecture adjustment approach that integrates hierarchical U-shaped encoder-decoder, residual blocks, attention mechanisms, and ASPP modules. By dynamically optimizing feature fusion, our method enhances segmentation performance. Experimental results demonstrate a Dice coefficient of 0.6802, IoU of 0.5602, Recall of 0.766, Precision of 0.6525, and Accuracy of 0.9955, effectively addressing the challenges in fundus image hemorrhage segmentation.[* Corresponding author.]
My research explores integrating deep learning and logic programming to set the basis for a new generation of AI systems. By combining neural networks with Inductive Logic Programming (ILP), the goal is to construct systems that make accurate predictions and generate comprehensible rules to validate these predictions. Deep learning models process and analyze complex data, while ILP techniques derive logical rules to prove the network's conclusions. Explainable AI methods, like eXplainable Answer Set Programming (XASP), elucidate the reasoning behind these rules and decisions. The focus is on applying ILP frameworks, specifically ILASP and FastLAS, to enhance explainability in various domains. My test cases span weather prediction, the legal field, and image recognition. In weather forecasting, the system will predict events and provides explanations using FastLAS, with plans to integrate recurrent neural networks in the future. In the legal domain, the research focuses on interpreting vague decisions and assisting legal professionals by encoding Italian legal articles and learning reasoning patterns from Court of Cassation decisions using ILASP. For biological laboratories, we will collaborate with a research group to automate spermatozoa morphology classification for Bull Breeding Soundness Evaluation using YOLO networks and ILP to explain classification outcomes. This hybrid approach aims to bridge the gap between the high performance of deep learning models and the transparency of symbolic reasoning, advancing AI by providing interpretable and trustworthy applications.
This paper presents an architecture for simulating the actions of a norm-aware intelligent agent whose behavior with respect to norm compliance is set, and can later be changed, by a human controller. Updating an agent's behavior mode from a norm-abiding to a riskier one may be relevant when the agent is involved in time-sensitive rescue operations, for example. We base our work on the Authorization and Obligation Policy Language AOPL designed by Gelfond and Lobo for the specification of norms. We introduce an architecture and a prototype software system that can be used to simulate an agent's plans under different behavior modes that can later be changed by the controller. We envision such software to be useful to policy makers, as they can more readily understand how agents may act in certain situations based on the agents' attitudes towards norm-compliance. Policy makers may then refine their policies if simulations show unwanted consequences.
Task planning for autonomous agents has typically been done using deep learning models and simulation-based reinforcement learning. This research proposes combining inductive learning techniques with goal-directed answer set programming to increase the explainability and reliability of systems for task breakdown and completion. Preliminary research has led to the creation of a Python harness that utilizes s(CASP) to solve task problems in a computationally efficient way. Although this research is in the early stages, we are exploring solutions to complex problems in simulated task completion.
There has been considerable recent interest in explainability in AI, especially with black-box machine learning models. As correctly observed by the planning community, when the application at hand is not a single-shot decision or prediction, but a sequence of actions that depend on observations, a richer notion of explanations are desirable. In this paper, we look to provide a formal account of ``counterfactual explanations," based in terms of action sequences. We then show that this naturally leads to an account of model reconciliation, which might take the form of the user correcting the agent's model, or suggesting actions to the agent's plan. For this, we will need to articulate what is true versus what is known, and we appeal to a modal fragment of the situation calculus to formalise these intuitions. We consider various settings: the agent knowing partial truths, weakened truths and having false beliefs, and show that our definitions easily generalize to these different settings.
Closed-loop simulation environments play a crucial role in the validation and enhancement of autonomous driving systems (ADS). However, certain challenges warrant significant attention, including balancing simulation accuracy with duration, reconciling functionality with practicality, and establishing comprehensive evaluation mechanisms. This paper addresses these challenges by introducing the LimSim Series, a comprehensive simulation platform designed to support the rapid deployment and efficient iteration of ADS. The LimSim Series integrates multi-type information from road networks, employs human-like decision-making and planning algorithms for background vehicles, and introduces the concept of the Area of Interest (AoI) to optimize computational resources. The platform offers a variety of baseline algorithms and user-friendly interfaces, facilitating flexible validation of multiple technical pipelines. Additionally, the LimSim Series incorporates multi-dimensional evaluation metrics, delivering thorough insights into system performance, thus enabling researchers to promptly identify issues for further improvements. Experiments demonstrate that the LimSim Series is compatible with modular, end-to-end, and VLM-based knowledge-driven systems. It can assist in the iteration and updating of ADS by evaluating performance across various scenarios. The code of the LimSim Series is released at: https://github.com/PJLab-ADG/LimSim.
The Gromov-Wasserstein (GW) problem is a variant of the classical optimal transport problem that allows one to compute meaningful transportation plans between incomparable spaces. At an intuitive level, it seeks plans that minimize the discrepancy between metric evaluations of pairs of points. The GW problem is typically cast as an instance of a non-convex quadratic program that is, unfortunately, intractable to solve. In this paper, we describe tractable semidefinite relaxations of the GW problem based on the Sum-of-Squares (SOS) hierarchy. We describe how the Putinar-type and the Schm\"udgen-type moment hierarchies can be simplified using marginal constraints, and we prove convergence rates for these hierarchies towards computing global optimal solutions to the GW problem. The proposed SOS hierarchies naturally induce a distance measure analogous to the distortion metrics, and we show that these are genuine distances in that they satisfy the triangle inequality. In particular, the proposed SOS hierarchies provide computationally tractable proxies of the GW distance and the associated distortion distances (over metric measure spaces) that are otherwise intractable to compute.
Accessing the internet in regions with expensive data plans and limited connectivity poses significant challenges, restricting information access and economic growth. Images, as a major contributor to webpage sizes, exacerbate this issue, despite advances in compression formats like WebP and AVIF. The continued growth of complex and curated web content, coupled with suboptimal optimization practices in many regions, has prevented meaningful reductions in web page sizes. This paper introduces PixLift, a novel solution to reduce webpage sizes by downscaling their images during transmission and leveraging AI models on user devices to upscale them. By trading computational resources for bandwidth, PixLift enables more affordable and inclusive web access. We address key challenges, including the feasibility of scaled image requests on popular websites, the implementation of PixLift as a browser extension, and its impact on user experience. Through the analysis of 71.4k webpages, evaluations of three mainstream upscaling models, and a user study, we demonstrate PixLift's ability to significantly reduce data usage without compromising image quality, fostering a more equitable internet.
The results of a study of the accuracy characteristics and image quality on the SAO RAS optical telescopes, Zeiss-1000 and BTA, using the recently developed "Telescope Analyzer" device are described: a method for determining the coefficients of the pointing correction system, the position of the aberration axis along the coma in images of star fields, natural frequencies of vibrations of mechanical systems, prospects for the development of the device. Attention is paid to the thermal deformations of the BTA main mirror and measures to reduce them. Mention is made of systems being developed for partial correction of wavefront aberrations due to imperfect mechanics, and plans to modernize the control system of the BTA. The complex of 0.5-meter telescopes "Astro-M" has not been forgotten: hardware and software solutions for automating the first and second telescopes, plans for commissioning of telescopes No 3-5 are described. Links to repositories with developed software and hardware products are provided.
Physical reasoning is a remarkable human ability that enables rapid learning and generalization from limited experience. Current AI models, despite extensive training, still struggle to achieve similar generalization, especially in Out-of-distribution (OOD) settings. This limitation stems from their inability to abstract core physical principles from observations. A key challenge is developing representations that can efficiently learn and generalize physical dynamics from minimal data. Here we present Neural Force Field (NFF) a modeling framework built on Neural Ordinary Differential Equation (NODE) that learns interpretable force field representations which can be efficiently integrated through an Ordinary Differential Equation ( ODE) solver to predict object trajectories. Unlike existing approaches that rely on high-dimensional latent spaces, NFF captures fundamental physical concepts such as gravity, support, and collision in an interpretable manner. Experiments on two challenging physical reasoning tasks demonstrate that NFF, trained with only a few examples, achieves strong generalization to unseen scenarios. This physics-grounded representation enables efficient forward-backward planning and rapid adaptation through interactive refinement. Our work suggests that incorporating physics-inspired representations into learning systems can help bridge the gap between artificial and human physical reasoning capabilities.
Extracting lane topology from perspective views (PV) is crucial for planning and control in autonomous driving. This approach extracts potential drivable trajectories for self-driving vehicles without relying on high-definition (HD) maps. However, the unordered nature and weak long-range perception of the DETR-like framework can result in misaligned segment endpoints and limited topological prediction capabilities. Inspired by the learning of contextual relationships in language models, the connectivity relations in roads can be characterized as explicit topology sequences. In this paper, we introduce Topo2Seq, a novel approach for enhancing topology reasoning via topology sequences learning. The core concept of Topo2Seq is a randomized order prompt-to-sequence learning between lane segment decoder and topology sequence decoder. The dual-decoder branches simultaneously learn the lane topology sequences extracted from the Directed Acyclic Graph (DAG) and the lane graph containing geometric information. Randomized order prompt-to-sequence learning extracts unordered key points from the lane graph predicted by the lane segment decoder, which are then fed into the prompt design of the topology sequence decoder to reconstruct an ordered and complete lane graph. In this way, the lane segment decoder learns powerful long-range perception and accurate topological reasoning from the topology sequence decoder. Notably, topology sequence decoder is only introduced during training and does not affect the inference efficiency. Experimental evaluations on the OpenLane-V2 dataset demonstrate the state-of-the-art performance of Topo2Seq in topology reasoning.
We consider a general problem where an agent is in a multi-agent environment and must plan for herself without any prior information about her opponents. At each moment, this pivotal agent is faced with a trade-off between exploiting her currently accumulated information about the other agents and exploring further to improve future (re-)planning. We propose a theoretic framework that unifies a spectrum of planners for the pivotal agent to address this trade-off. The planner at one end of this spectrum aims to find exact solutions, while those towards the other end yield approximate solutions as the problem scales up. Beyond theoretical analysis, we also implement \textbf{13} planners and conduct experiments in a specific domain called \textit{multi-agent route planning} with the number of agents \textbf{up to~50}, to compare their performaces in various scenarios. One interesting observation comes from a class of planners that we call \textit{safe-agents} and their enhanced variants by incorporating domain-specific knowledge, which is a simple special case under the proposed general framework, but performs sufficiently well in most cases. Our unified framework, as well as those induced planners, provides new insights on multi-agent decision-making, with potential applications to related areas such as mechanism design.
Vision-language models (VLMs) have achieved remarkable success in scene understanding and perception tasks, enabling robots to plan and execute actions adaptively in dynamic environments. However, most multimodal large language models lack robust 3D scene localization capabilities, limiting their effectiveness in fine-grained robotic operations. Additionally, challenges such as low recognition accuracy, inefficiency, poor transferability, and reliability hinder their use in precision tasks. To address these limitations, we propose a novel framework that integrates a 2D prompt synthesis module by mapping 2D images to point clouds, and incorporates a small language model (SLM) for supervising VLM outputs. The 2D prompt synthesis module enables VLMs, trained on 2D images and text, to autonomously extract precise 3D spatial information without manual intervention, significantly enhancing 3D scene understanding. Meanwhile, the SLM supervises VLM outputs, mitigating hallucinations and ensuring reliable, executable robotic control code generation. Our framework eliminates the need for retraining in new environments, thereby improving cost efficiency and operational robustness. Experimental results that the proposed framework achieved a 96.0\% Task Success Rate (TSR), outperforming other methods. Ablation studies demonstrated the critical role of both the 2D prompt synthesis module and the output supervision module (which, when removed, caused a 67\% TSR drop). These findings validate the framework's effectiveness in improving 3D recognition, task planning, and robotic task execution.
3D Multi-Object Tracking (MOT) provides the trajectories of surrounding objects, assisting robots or vehicles in smarter path planning and obstacle avoidance. Existing 3D MOT methods based on the Tracking-by-Detection framework typically use a single motion model to track an object throughout its entire tracking process. However, objects may change their motion patterns due to variations in the surrounding environment. In this paper, we introduce the Interacting Multiple Model filter in IMM-MOT, which accurately fits the complex motion patterns of individual objects, overcoming the limitation of single-model tracking in existing approaches. In addition, we incorporate a Damping Window mechanism into the trajectory lifecycle management, leveraging the continuous association status of trajectories to control their creation and termination, reducing the occurrence of overlooked low-confidence true targets. Furthermore, we propose the Distance-Based Score Enhancement module, which enhances the differentiation between false positives and true positives by adjusting detection scores, thereby improving the effectiveness of the Score Filter. On the NuScenes Val dataset, IMM-MOT outperforms most other single-modal models using 3D point clouds, achieving an AMOTA of 73.8%. Our project is available at https://github.com/Ap01lo/IMM-MOT.
The sharing of large-scale transportation data is beneficial for transportation planning and policymaking. However, it also raises significant security and privacy concerns, as the data may include identifiable personal information, such as individuals' home locations. To address these concerns, synthetic data generation based on real transportation data offers a promising solution that allows privacy protection while potentially preserving data utility. Although there are various synthetic data generation techniques, they are often not tailored to the unique characteristics of transportation data, such as the inherent structure of transportation networks formed by all trips in the datasets. In this paper, we use New York City taxi data as a case study to conduct a systematic evaluation of the performance of widely used tabular data generative models. In addition to traditional metrics such as distribution similarity, coverage, and privacy preservation, we propose a novel graph-based metric tailored specifically for transportation data. This metric evaluates the similarity between real and synthetic transportation networks, providing potentially deeper insights into their structural and functional alignment. We also introduced an improved privacy metric to address the limitations of the commonly-used one. Our experimental results reveal that existing tabular data generative models often fail to perform as consistently as claimed in the literature, particularly when applied to transportation data use cases. Furthermore, our novel graph metric reveals a significant gap between synthetic and real data. This work underscores the potential need to develop generative models specifically tailored to take advantage of the unique characteristics of emerging domains, such as transportation.
This study presents a framework for high-resolution mortality simulations tailored to insured and general populations. Due to the scarcity of detailed demographic-specific mortality data, we leverage Iterative Proportional Fitting (IPF) and Monte Carlo simulations to generate refined mortality tables that incorporate age, gender, smoker status, and regional distributions. This methodology enhances public health planning and actuarial analysis by providing enriched datasets for improved life expectancy projections and insurance product development.
Depression and anxiety are prevalent mental health disorders that frequently cooccur, with anxiety significantly influencing both the manifestation and treatment of depression. An accurate assessment of anxiety levels in individuals with depression is crucial to develop effective and personalized treatment plans. This study proposes a new noninvasive method for quantifying anxiety severity by analyzing head movements -- specifically speed, acceleration, and angular displacement -- during video-recorded interviews with patients suffering from severe depression. Using data from a new CALYPSO Depression Dataset, we extracted head motion characteristics and applied regression analysis to predict clinically evaluated anxiety levels. Our results demonstrate a high level of precision, achieving a mean absolute error (MAE) of 0.35 in predicting the severity of psychological anxiety based on head movement patterns. This indicates that our approach can enhance the understanding of anxiety's role in depression and assist psychiatrists in refining treatment strategies for individuals.
Decoder-only transformers lead to a step-change in capability of large language models. However, opinions are mixed as to whether they are really planning or reasoning. A path to making progress in this direction is to study the model's behavior in a setting with carefully controlled data. Then interpret the learned representations and reverse-engineer the computation performed internally. We study decoder-only transformer language models trained from scratch to predict shortest paths on simple, connected and undirected graphs. In this setting, the representations and the dynamics learned by the model are interpretable. We present three major results: (1) Two-layer decoder-only language models can learn to predict shortest paths on simple, connected graphs containing up to 10 nodes. (2) Models learn a graph embedding that is correlated with the spectral decomposition of the line graph. (3) Following the insights, we discover a novel approximate path-finding algorithm Spectral Line Navigator (SLN) that finds shortest path by greedily selecting nodes in the space of spectral embedding of the line graph.
Vision-language navigation (VLN) has emerged as a promising paradigm, enabling mobile robots to perform zero-shot inference and execute tasks without specific pre-programming. However, current systems often separate map exploration and path planning, with exploration relying on inefficient algorithms due to limited (partially observed) environmental information. In this paper, we present a novel navigation pipeline named ''ClipRover'' for simultaneous exploration and target discovery in unknown environments, leveraging the capabilities of a vision-language model named CLIP. Our approach requires only monocular vision and operates without any prior map or knowledge about the target. For comprehensive evaluations, we design the functional prototype of a UGV (unmanned ground vehicle) system named ''Rover Master'', a customized platform for general-purpose VLN tasks. We integrate and deploy the ClipRover pipeline on Rover Master to evaluate its throughput, obstacle avoidance capability, and trajectory performance across various real-world scenarios. Experimental results demonstrate that ClipRover consistently outperforms traditional map traversal algorithms and achieves performance comparable to path-planning methods that depend on prior map and target knowledge. Notably, ClipRover offers real-time active navigation without requiring pre-captured candidate images or pre-built node graphs, addressing key limitations of existing VLN pipelines.
Precise segmentation and classification of cell instances are vital for analyzing the tissue microenvironment in histology images, supporting medical diagnosis, prognosis, treatment planning, and studies of brain cytoarchitecture. However, the creation of high-quality annotated datasets for training remains a major challenge. This study introduces a novel single-stage approach (HistoSmith) for generating image-label pairs to augment histology datasets. Unlike state-of-the-art methods that utilize diffusion models with separate components for label and image generation, our approach employs a latent diffusion model to learn the joint distribution of cellular layouts, classification masks, and histology images. This model enables tailored data generation by conditioning on user-defined parameters such as cell types, quantities, and tissue types. Trained on the Conic H&E histopathology dataset and the Nissl-stained CytoDArk0 dataset, the model generates realistic and diverse labeled samples. Experimental results demonstrate improvements in cell instance segmentation and classification, particularly for underrepresented cell types like neutrophils in the Conic dataset. These findings underscore the potential of our approach to address data scarcity challenges.
A robot that learns from demonstrations should not just imitate what it sees -- it should understand the high-level concepts that are being demonstrated and generalize them to new tasks. Bilevel planning is a hierarchical model-based approach where predicates (relational state abstractions) can be leveraged to achieve compositional generalization. However, previous bilevel planning approaches depend on predicates that are either hand-engineered or restricted to very simple forms, limiting their scalability to sophisticated, high-dimensional state spaces. To address this limitation, we present IVNTR, the first bilevel planning approach capable of learning neural predicates directly from demonstrations. Our key innovation is a neuro-symbolic bilevel learning framework that mirrors the structure of bilevel planning. In IVNTR, symbolic learning of the predicate "effects" and neural learning of the predicate "functions" alternate, with each providing guidance for the other. We evaluate IVNTR in six diverse robot planning domains, demonstrating its effectiveness in abstracting various continuous and high-dimensional states. While most existing approaches struggle to generalize (with <35% success rate), our IVNTR achieves an average of 77% success rate on unseen tasks. Additionally, we showcase IVNTR on a mobile manipulator, where it learns to perform real-world mobile manipulation tasks and generalizes to unseen test scenarios that feature new objects, new states, and longer task horizons. Our findings underscore the promise of learning and planning with abstractions as a path towards high-level generalization.
Testing Autonomous Driving Systems (ADS) is crucial for ensuring their safety, reliability, and performance. Despite numerous testing methods available that can generate diverse and challenging scenarios to uncover potential vulnerabilities, these methods often treat ADS as a black-box, primarily focusing on identifying system failures like collisions or near-misses without pinpointing the specific modules responsible for these failures. Understanding the root causes of failures is essential for effective debugging and subsequent system repair. We observed that existing methods also fall short in generating diverse failures that adequately test the distinct modules of an ADS, such as perception, prediction, planning and control. To bridge this gap, we introduce MoDitector, the first root-cause-aware testing method for ADS. Unlike previous approaches, MoDitector not only generates scenarios leading to collisions but also showing which specific module triggered the failure. This method targets specific modules, creating test scenarios that highlight the weaknesses of these given modules. Specifically, our approach involves designing module-specific oracles to ascertain module failures and employs a module-directed testing strategy that includes module-specific feedback, adaptive seed selection, and mutation. This strategy guides the generation of tests that effectively provoke module-specific failures. We evaluated MoDitector across four critical ADS modules and four testing scenarios. Our approach represents a significant innovation in ADS testing by focusing on identifying and rectifying module-specific errors within the system, moving beyond conventional black-box failure detection.
The Deep Underground Neutrino Experiment (DUNE) is a next-generation long-baseline neutrino oscillation experiment. Its primary goal is the determination of the neutrino mass hierarchy and the CP-violating phase. The DUNE physics program also includes the detection of astrophysical neutrinos and the search for beyond the Standard Model phenomena, such as nucleon decays. DUNE will consist of a near detector complex placed at Fermilab, several hundred meters downstream of the neutrino production point, and 17-kton Liquid Argon Time Projection Chamber (LArTPC) far detector modules to be built in the Sanford Underground Research Facility (SURF), approximately 1.5 km underground and 1300 km away. The detectors will be exposed to a wide-band neutrino beam generated by a 1.2 MW proton beam, with a planned upgrade to 2.4 MW. Two prototypes of the FD technology, the ProtoDUNE 700 ton LArTPCs, have been operated at CERN for over 2 years, and have been recently optimized to take new data in 2024-2025. Additionally, the 2x2 Demonstrator, a prototype of the LAr component of the near detector, has recently started operations in the NuMI beam at Fermilab. This talk will present the science programme, as well as recent progress, of DUNE and its different prototyping efforts.
Referring Remote Sensing Image Segmentation (RRSIS) is critical for ecological monitoring, urban planning, and disaster management, requiring precise segmentation of objects in remote sensing imagery guided by textual descriptions. This task is uniquely challenging due to the considerable vision-language gap, the high spatial resolution and broad coverage of remote sensing imagery with diverse categories and small targets, and the presence of clustered, unclear targets with blurred edges. To tackle these issues, we propose \ours, a novel framework designed to bridge the vision-language gap, enhance multi-scale feature interaction, and improve fine-grained object differentiation. Specifically, \ours introduces: (1) the Bidirectional Spatial Correlation (BSC) for improved vision-language feature alignment, (2) the Target-Background TwinStream Decoder (T-BTD) for precise distinction between targets and non-targets, and (3) the Dual-Modal Object Learning Strategy (D-MOLS) for robust multimodal feature reconstruction. Extensive experiments on the benchmark datasets RefSegRS and RRSIS-D demonstrate that \ours achieves state-of-the-art performance. Specifically, \ours improves the overall IoU (oIoU) by 3.76 percentage points (80.57) and 1.44 percentage points (79.23) on the two datasets, respectively. Additionally, it outperforms previous methods in the mean IoU (mIoU) by 5.37 percentage points (67.95) and 1.84 percentage points (66.04), effectively addressing the core challenges of RRSIS with enhanced precision and robustness.
Designing proper incentives in mobile crowdsensing (MCS) networks represents a critical mechanism in engaging distributed mobile users (workers) to contribute heterogeneous data for diverse applications (tasks). We develop a novel stagewise trading framework to reach efficient and stable matching between tasks and workers, upon considering the diversity of tasks and the dynamism of MCS networks. This framework integrates futures and spot trading stages, where in the former, we propose futures trading-driven stable matching and pre-path-planning (FT-SMP^3) for long-term task-worker assignment and pre-planning of workers' paths based on historical statistics and risk analysis. While in the latter, we investigate spot trading-driven DQN path planning and onsite worker recruitment (ST-DP^2WR) mechanism to enhance workers' and tasks' practical utilities by facilitating temporary worker recruitment. We prove that our proposed mechanisms support crucial properties such as stability, individual rationality, competitive equilibrium, and weak Pareto optimality theoretically. Also, comprehensive evaluations confirm the satisfaction of these properties in practical network settings, demonstrating our commendable performance in terms of service quality, running time, and decision-making overheads.
Accurate power load forecasting is essential for the efficient operation and planning of electrical grids, particularly given the increased variability and complexity introduced by renewable energy sources. This paper introduces GAT-LSTM, a hybrid model that combines Graph Attention Networks (GAT) and Long Short-Term Memory (LSTM) networks. A key innovation of the model is the incorporation of edge attributes, such as line capacities and efficiencies, into the attention mechanism, enabling it to dynamically capture spatial relationships grounded in grid-specific physical and operational constraints. Additionally, by employing an early fusion of spatial graph embeddings and temporal sequence features, the model effectively learns and predicts complex interactions between spatial dependencies and temporal patterns, providing a realistic representation of the dynamics of power grids. Experimental evaluations on the Brazilian Electricity System dataset demonstrate that the GAT-LSTM model significantly outperforms state-of-the-art models, achieving reductions of 21. 8% in MAE, 15. 9% in RMSE and 20. 2% in MAPE. These results underscore the robustness and adaptability of the GAT-LSTM model, establishing it as a powerful tool for applications in grid management and energy planning.
Combinatorial optimization problems, such as scheduling and route planning, are crucial in various industries but are computationally intractable due to their NP-hard nature. Neural Combinatorial Optimization methods leverage machine learning to address these challenges but often depend on sequential decision-making, which is prone to error accumulation as small mistakes propagate throughout the process. Inspired by self-evaluation techniques in Large Language Models, we propose a novel framework that generates and evaluates subsets of assignments, moving beyond traditional stepwise approaches. Applied to the Job-Shop Scheduling Problem, our method integrates a heterogeneous graph neural network with a Transformer to build a policy model and a self-evaluation function. Experimental validation on challenging, well-known benchmarks demonstrates the effectiveness of our approach, surpassing state-of-the-art methods.
We summarize the status of lattice QCD ensemble generation efforts and their data management characteristics. Namely, these proceedings combine the contributions to a dedicated parallel session during the 41st International Symposium on Lattice Field Theory (Lattice 2024), during which representatives of 16 lattice QCD collaborations provided details on their simulation program, with focus on plans for publication, data management, and storage requirements. The parallel session was organized by the International Lattice Data Grid (ILDG), following an open call to the lattice QCD community for participation in the session.
Transforming recorded videos into concise and accurate textual summaries is a growing challenge in multimodal learning. This paper introduces VISTA, a dataset specifically designed for video-to-text summarization in scientific domains. VISTA contains 18,599 recorded AI conference presentations paired with their corresponding paper abstracts. We benchmark the performance of state-of-the-art large models and apply a plan-based framework to better capture the structured nature of abstracts. Both human and automated evaluations confirm that explicit planning enhances summary quality and factual consistency. However, a considerable gap remains between models and human performance, highlighting the challenges of scientific video summarization.
Autonomous Vehicles (AVs) are advancing rapidly, with Level-4 AVs already operating in real-world conditions. Current AVs, however, still lag behind human drivers in adaptability and performance, often exhibiting overly conservative behaviours and occasionally violating traffic laws. Existing solutions, such as runtime enforcement, mitigate this by automatically repairing the AV's planned trajectory at runtime, but such approaches lack transparency and should be a measure of last resort. It would be preferable for AV repairs to generalise beyond specific incidents and to be interpretable for users. In this work, we propose FixDrive, a framework that analyses driving records from near-misses or law violations to generate AV driving strategy repairs that reduce the chance of such incidents occurring again. These repairs are captured in {\mu}Drive, a high-level domain-specific language for specifying driving behaviours in response to event-based triggers. Implemented for the state-of-the-art autonomous driving system Apollo, FixDrive identifies and visualises critical moments from driving records, then uses a Multimodal Large Language Model (MLLM) with zero-shot learning to generate {\mu}Drive programs. We tested FixDrive on various benchmark scenarios, and found that the generated repairs improved the AV's performance with respect to following traffic laws, avoiding collisions, and successfully reaching destinations. Furthermore, the direct costs of repairing an AV -- 15 minutes of offline analysis and $0.08 per violation -- are reasonable in practice.
Fare planning is one among several steps in public transport planning. Fares are relevant for the covering of costs of the public transport operator, but also affect the ridership and the passenger satisfaction. A fare structure is the assignment of prices to all paths in a network. In practice, often a given fare structure shall be changed to fulfill new requirements, meaning that a new fare strategy is desired. This motivates the usage of prices of the former fare structure or other desirable prices as reference prices. In this paper, we investigate the fare structure design problem that aims to determine fares such that the sum of absolute deviations between the new fares and the reference prices is minimized. Fare strategies that are considered here are flat tariffs, affine distance tariffs and zone tariffs. Additionally, we regard constraints that ensure that it is not beneficial to buy a ticket for a longer journey than actually traveled (no-elongation property) or to split a ticket into several sub-tickets to cover a journey (no-stopover property). Our literature review provides an overview of the research on fare planning. We analyze the fare structure design problem for flat, distance and zone tariffs, pointing out connections to median problems. Further, we study its complexity which ranges from linear-time solvability to NP-complete cases.
Open human mobility data is considered an essential basis for the profound research and analysis required for the transition to sustainable mobility and sustainable urban planning. Cycling data has especially been the focus of data collection endeavors in recent years. Although privacy risks regarding location data are widely known, practitioners often refrain from advanced privacy mechanisms to prevent utility losses. Removing user identifiers from trips is thereby deemed a major privacy gain, as it supposedly prevents linking single trips to obtain entire movement patterns. In this paper, we propose a novel attack to reconstruct user identifiers in GPS trip datasets consisting of single trips, unlike previous ones that are dedicated to evaluating trajectory-user linking in the context of check-in data. We evaluate the remaining privacy risk for users in such datasets and our empirical findings from two real-world datasets show that the risk of re-identification is significant even when personal identifiers have been removed, and that truncation as a simple additional privacy mechanism may not be effective in protecting user privacy. Further investigations indicate that users who frequently visit locations that are only visited by a small number of others, tend to be more vulnerable to re-identification.
Collaborative perception, fusing information from multiple agents, can extend perception range so as to improve perception performance. However, temporal asynchrony in real-world environments, caused by communication delays, clock misalignment, or sampling configuration differences, can lead to information mismatches. If this is not well handled, then the collaborative performance is patchy, and what's worse safety accidents may occur. To tackle this challenge, we propose CoDynTrust, an uncertainty-encoded asynchronous fusion perception framework that is robust to the information mismatches caused by temporal asynchrony. CoDynTrust generates dynamic feature trust modulus (DFTM) for each region of interest by modeling aleatoric and epistemic uncertainty as well as selectively suppressing or retaining single-vehicle features, thereby mitigating information mismatches. We then design a multi-scale fusion module to handle multi-scale feature maps processed by DFTM. Compared to existing works that also consider asynchronous collaborative perception, CoDynTrust combats various low-quality information in temporally asynchronous scenarios and allows uncertainty to be propagated to downstream tasks such as planning and control. Experimental results demonstrate that CoDynTrust significantly reduces performance degradation caused by temporal asynchrony across multiple datasets, achieving state-of-the-art detection performance even with temporal asynchrony. The code is available at https://github.com/CrazyShout/CoDynTrust.
State estimation methods using factor graph optimization (FGO) have garnered significant attention in global navigation satellite system (GNSS) research. FGO exhibits superior estimation accuracy compared with traditional state estimation methods that rely on least-squares or Kalman filters. However, only a few FGO libraries are specialized for GNSS observations. This paper introduces an open-source GNSS FGO package named gtsam\_gnss, which has a simple structure and can be easily applied to GNSS research and development. This package separates the preprocessing of GNSS observations from factor optimization. Moreover, it describes the error function of the GNSS factor in a straightforward manner, allowing for general-purpose inputs. This design facilitates the transition from ordinary least-squares-based positioning to FGO and supports user-specific GNSS research. In addition, gtsam\_gnss includes analytical examples involving various factors using GNSS data in real urban environments. This paper presents three application examples: the use of a robust error model, estimation of integer ambiguity in the carrier phase, and combination of GNSS and inertial measurements from smartphones. The proposed framework demonstrates excellent state estimation performance across all use cases.
Extreme heat events exacerbated by climate change pose significant challenges to urban resilience and planning. This study introduces a climate-responsive digital twin framework integrating the Spatiotemporal Vision Transformer (ST-ViT) model to enhance heat stress forecasting and decision-making. Using a Texas campus as a testbed, we synthesized high-resolution physical model simulations with spatial and meteorological data to develop fine-scale human thermal predictions. The ST-ViT-powered digital twin enables efficient, data-driven insights for planners, policymakers, and campus stakeholders, supporting targeted heat mitigation strategies and advancing climate-adaptive urban design.
Energy systems modeling frequently relies on time series data, whether observed or forecast. This is particularly the case, for example, in capacity planning models that use hourly production and load data forecast to occur over the coming several decades. This paper addresses the attendant problem of performing sensitivity, robustness, and other post-solution analyses using time series data. We explore two efficient and relatively simple, non-parametric, bootstrapping methods for generating arbitrary numbers of time series from a single observed or forecast series. The paper presents and assesses each method. We find that the generated series are both visually and by statistical summary measures close to the original observational data. In consequence these series are credibly taken as stochastic instances from a common distribution, that of the original series of observations. With climate change in mind, the paper further proposes and explores two general techniques for systematically altering (increasing or decreasing) time series. Both for the perturbed and unperturbed synthetic series data, we find that the generated series induce variability in properties of the series that are important for energy modeling, in particular periods of under- and over-production, and periods of increased ramping rates. In consequence, series produced in this way are apt for use in robustness, sensitivity, and in general post-solution analysis of energy planning models. These validity factors auger well for applications beyond energy modeling.
Current GUI agents have achieved outstanding performance in GUI element grounding. However, planning remains highly challenging, especially due to sensitivity to the initial state of the environment. Specifically, slight differences in the initial state-such as the target software not being open or the interface not being in its default state-often lead to planning errors. This issue is widespread in real user scenarios, but existing benchmarks fail to evaluate it. In this paper, we present WorldGUI, a novel GUI benchmark that designs GUI tasks with various initial states to simulate real computer-user interactions. The benchmark spans a wide range of tasks across 10 popular software applications, including PowerPoint, VSCode, and Adobe Acrobat. In addition, to address the challenges of dynamic GUI automation tasks, we propose GUI-Thinker, a holistic framework, leveraging a critique mechanism, that effectively manages the unpredictability and complexity of GUI interactions. Experimental results demonstrate that GUI-Thinker significantly outperforms Claude-3.5 (Computer Use) by 14.9% in success rate on WorldGUI tasks. This improvement underscores the effectiveness of our critical-thinking-based framework in enhancing GUI automation. The code is available at https://github.com/showlab/WorldGUI.
Trajectory prediction and planning are fundamental components for autonomous vehicles to navigate safely and efficiently in dynamic environments. Traditionally, these components have often been treated as separate modules, limiting the ability to perform interactive planning and leading to computational inefficiency in multi-agent scenarios. In this paper, we present a novel unified and data-driven framework that integrates prediction and planning with a single consistency model. Trained on real-world human driving datasets, our consistency model generates samples from high-dimensional, multimodal joint trajectory distributions of the ego and multiple surrounding agents, enabling end-to-end predictive planning. It effectively produces interactive behaviors, such as proactive nudging and yielding to ensure both safe and efficient interactions with other road users. To incorporate additional planning constraints on the ego vehicle, we propose an alternating direction method for multi-objective guidance in online guided sampling. Compared to diffusion models, our consistency model achieves better performance with fewer sampling steps, making it more suitable for real-time deployment. Experimental results on Waymo Open Motion Dataset (WOMD) demonstrate our method's superiority in trajectory quality, constraint satisfaction, and interactive behavior compared to various existing approaches.
With the advent of the 6G era, global connectivity has become a common goal in the evolution of communications, aiming to bring Internet services to more unconnected regions. Additionally, the rise of applications such as the Internet of Everything and remote education also requires global connectivity. Non-terrestrial networks (NTN), particularly low earth orbit (LEO) satellites, play a crucial role in this future vision. Although some literature already analyze the coverage performance using stochastic geometry, the ability of generating large-scale continuous service area is still expected to analyze. Therefore, in this paper, we mainly investigate the necessary conditions of LEO satellite deployment for large-scale continuous service coverage on the earth. Firstly, we apply percolation theory to a closed spherical surface and define the percolation on a sphere for the first time. We introduce the sub-critical and super-critical cases to prove the existence of the phase transition of percolation probability. Then, through stereographic projection, we introduce the tight bounds and closed-form expression of the critical number of LEO satellites on the same constellation. In addition, we also investigate how the altitude and maximum slant range of LEO satellites affect percolation probability, and derive the critical values of them. Based on our findings, we provide useful recommendations for companies planning to deploy LEO satellite networks to enhance connectivity.
Ethanolamine (EA), a key component of phospholipids, has recently been detected in the interstellar medium within molecular clouds. To understand this observation, laboratory studies of its formation and destruction are essential and should be complemented by astrochemical models. This study investigates the photostability of EA ice under Lyman (Ly)-$\alpha$ (10.2 eV) irradiation at 10 K, and explores its potential role in the formation of simple and complex organic molecules in molecular clouds. The UV destruction cross section of EA was estimated to be ($4.7\pm0.3)\times10^{-18}$ cm$^2$, providing insight into its half-life of $6.5\times10^{7}$ yr in dense interstellar clouds. Fourier transform infrared spectroscopy and quadrupole mass spectrometry were used to identify various photoproducts, with their formation pathways discussed. Ethylene glycol and serine were tentatively detected during the warming up process following irradiation, suggesting that EA could contribute to the formation of prebiotic molecules such as sugars, peptides and their derivatives. High mass signals detected in the mass spectrometer suggest the presence of several complex organic molecules, and further analysis of residues at room temperature is planned for future work. The results suggest that EA could contribute to the formation of prebiotic molecules in space, with implications for the origin of life.
While self-attention has been instrumental in the success of Transformers, it can lead to over-concentration on a few tokens during training, resulting in suboptimal information flow. Enforcing doubly-stochastic constraints in attention matrices has been shown to improve structure and balance in attention distributions. However, existing methods rely on iterative Sinkhorn normalization, which is computationally costly. In this paper, we introduce a novel, fully parallelizable doubly-stochastic attention mechanism based on sliced optimal transport, leveraging Expected Sliced Transport Plans (ESP). Unlike prior approaches, our method enforces double stochasticity without iterative Sinkhorn normalization, significantly enhancing efficiency. To ensure differentiability, we incorporate a temperature-based soft sorting technique, enabling seamless integration into deep learning models. Experiments across multiple benchmark datasets, including image classification, point cloud classification, sentiment analysis, and neural machine translation, demonstrate that our enhanced attention regularization consistently improves performance across diverse applications.
In recent years, Software Engineering (SE) scholars and practitioners have emphasized the importance of integrating soft skills into SE education. However, teaching and learning soft skills are complex, as they cannot be acquired passively through raw knowledge acquisition. On the other hand, hackathons have attracted increasing attention due to their experiential, collaborative, and intensive nature, which certain tasks could be similar to real-world software development. This paper aims to discuss the idea of hackathons as an educational strategy for shaping SE students' soft skills in practice. Initially, we overview the existing literature on soft skills and hackathons in SE education. Then, we report preliminary empirical evidence from a seven-day hybrid hackathon involving 40 students. We assess how the hackathon experience promoted innovative and creative thinking, collaboration and teamwork, and knowledge application among participants through a structured questionnaire designed to evaluate students' self-awareness. Lastly, our findings and new directions are analyzed through the lens of Self-Determination Theory, which offers a psychological lens to understand human behavior. This paper contributes to academia by advocating the potential of hackathons in SE education and proposing concrete plans for future research within SDT. For industry, our discussion has implications around developing soft skills in future SE professionals, thereby enhancing their employability and readiness in the software market.
Our work introduces the effect of supply/demand imbalances into the literature on online matching with stochastic rewards in bipartite graphs. We provide a parameterized definition that characterizes instances as over- or undersupplied (or balanced), and show that higher competitive ratios against an offline clairvoyant algorithm are achievable, for both adversarial and stochastic arrivals, when instances are more imbalanced. The competitive ratio guarantees we obtain are the best-possible for the class of delayed algorithms we focus on (such algorithms may adapt to the history of arrivals and the algorithm's own decisions, but not to the stochastic realization of each potential match). We then explore the real-world implications of our improved competitive ratios. First, we demonstrate analytically that the improved competitive ratios under imbalanced instances is not a one-way street by showing that a platform that conducts effective supply- and demand management should incorporate the effect of imbalance on its matching performance on its supply planning in order to create imbalanced instances. Second, we empirically study the relationship between achieved competitive ratios and imbalance using the data of a volunteer matching platform.
Perceiving the environment and its changes over time corresponds to two fundamental yet heterogeneous types of information: semantics and motion. Previous end-to-end autonomous driving works represent both types of information in a single feature vector. However, including motion tasks, such as prediction and planning, always impairs detection and tracking performance, a phenomenon known as negative transfer in multi-task learning. To address this issue, we propose Neural-Bayes motion decoding, a novel parallel detection, tracking, and prediction method separating semantic and motion learning, similar to the Bayes filter. Specifically, we employ a set of learned motion queries that operate in parallel with the detection and tracking queries, sharing a unified set of recursively updated reference points. Moreover, we employ interactive semantic decoding to enhance information exchange in semantic tasks, promoting positive transfer. Experiments on the nuScenes dataset show improvements of 5% in detection and 11% in tracking. Our method achieves state-of-the-art collision rates in open-loop planning evaluation without any modifications to the planning module.
Predicting future scene representations is a crucial task for enabling robots to understand and interact with the environment. However, most existing methods rely on video sequences and simulations with precise action annotations, limiting their ability to leverage the large amount of available unlabeled video data. To address this challenge, we propose PlaySlot, an object-centric video prediction model that infers object representations and latent actions from unlabeled video sequences. It then uses these representations to forecast future object states and video frames. PlaySlot allows to generate multiple possible futures conditioned on latent actions, which can be inferred from video dynamics, provided by a user, or generated by a learned action policy, thus enabling versatile and interpretable world modeling. Our results show that PlaySlot outperforms both stochastic and object-centric baselines for video prediction across different environments. Furthermore, we show that our inferred latent actions can be used to learn robot behaviors sample-efficiently from unlabeled video demonstrations. Videos and code are available at https://play-slot.github.io/PlaySlot/.
Imagination in world models is crucial for enabling agents to learn long-horizon policy in a sample-efficient manner. Existing recurrent state-space model (RSSM)-based world models depend on single-step statistical inference to capture the environment dynamics, and, hence, they are unable to perform long-term imagination tasks due to the accumulation of prediction errors. Inspired by the dual-process theory of human cognition, we propose a novel dual-mind world model (DMWM) framework that integrates logical reasoning to enable imagination with logical consistency. DMWM is composed of two components: an RSSM-based System 1 (RSSM-S1) component that handles state transitions in an intuitive manner and a logic-integrated neural network-based System 2 (LINN-S2) component that guides the imagination process through hierarchical deep logical reasoning. The inter-system feedback mechanism is designed to ensure that the imagination process follows the logical rules of the real environment. The proposed framework is evaluated on benchmark tasks that require long-term planning from the DMControl suite. Extensive experimental results demonstrate that the proposed framework yields significant improvements in terms of logical coherence, trial efficiency, data efficiency and long-term imagination over the state-of-the-art world models.
Water distribution systems (WDSs) are an important part of critical infrastructure becoming increasingly significant in the face of climate change and urban population growth. We propose a robust and scalable surrogate deep learning (DL) model to enable efficient planning, expansion, and rehabilitation of WDSs. Our approach incorporates an improved graph neural network architecture, an adapted physics-informed algorithm, an innovative training scheme, and a physics-preserving data normalization method. Evaluation results on a number of WDSs demonstrate that our model outperforms the current state-of-the-art DL model. Moreover, our method allows us to scale the model to bigger and more realistic WDSs. Furthermore, our approach makes the model more robust to out-of-distribution input features (demands, pipe diameters). Hence, our proposed method constitutes a significant step towards bridging the simulation-to-real gap in the use of artificial intelligence for WDSs.
Road information extraction from 3D point clouds is useful for urban planning and traffic management. Existing methods often rely on local features and the refraction angle of lasers from kerbs, which makes them sensitive to variable kerb designs and issues in high-density areas due to data homogeneity. We propose an approach for extracting road points and fitting centrelines using a top-down view of LiDAR based ground-collected point clouds. This prospective view reduces reliance on specific kerb design and results in better road extraction. We first perform statistical outlier removal and density-based clustering to reduce noise from 3D point cloud data. Next, we perform ground point filtering using a grid-based segmentation method that adapts to diverse road scenarios and terrain characteristics. The filtered points are then projected onto a 2D plane, and the road is extracted by a skeletonisation algorithm. The skeleton is back-projected onto the 3D point cloud with calculated normals, which guide a region growing algorithm to find nearby road points. The extracted road points are then smoothed with the Savitzky-Golay filter to produce the final centreline. Our initial approach without post-processing of road skeleton achieved 67% in IoU by testing on the Perth CBD dataset with different road types. Incorporating the post-processing of the road skeleton improved the extraction of road points around the smoothed skeleton. The refined approach achieved a higher IoU value of 73% and with 23% reduction in the processing time. Our approach offers a generalised and computationally efficient solution that combines 3D and 2D processing techniques, laying the groundwork for future road reconstruction and 3D-to-2D point cloud alignment.
Reasoning is a fundamental capability of Large Language Models. While prior research predominantly focuses on enhancing narrow skills like math or code generation, improving performance on many other reasoning tasks remains challenging due to sparse and fragmented training data. To address this issue, we propose CodeI/O, a novel approach that systematically condenses diverse reasoning patterns inherently embedded in contextually-grounded codes, through transforming the original code into a code input-output prediction format. By training models to predict inputs/outputs given code and test cases entirely in natural language as Chain-of-Thought (CoT) rationales, we expose them to universal reasoning primitives -- like logic flow planning, state-space searching, decision tree traversal, and modular decomposition -- while decoupling structured reasoning from code-specific syntax and preserving procedural rigor. Experimental results demonstrate CodeI/O leads to consistent improvements across symbolic, scientific, logic, math & numerical, and commonsense reasoning tasks. By matching the existing ground-truth outputs or re-executing the code with predicted inputs, we can verify each prediction and further enhance the CoTs through multi-turn revision, resulting in CodeI/O++ and achieving higher performance. Our data and models are available at https://github.com/hkust-nlp/CodeIO.
Understanding world dynamics is crucial for planning in autonomous driving. Recent methods attempt to achieve this by learning a 3D occupancy world model that forecasts future surrounding scenes based on current observation. However, 3D occupancy labels are still required to produce promising results. Considering the high annotation cost for 3D outdoor scenes, we propose a semi-supervised vision-centric 3D occupancy world model, PreWorld, to leverage the potential of 2D labels through a novel two-stage training paradigm: the self-supervised pre-training stage and the fully-supervised fine-tuning stage. Specifically, during the pre-training stage, we utilize an attribute projection head to generate different attribute fields of a scene (e.g., RGB, density, semantic), thus enabling temporal supervision from 2D labels via volume rendering techniques. Furthermore, we introduce a simple yet effective state-conditioned forecasting module to recursively forecast future occupancy and ego trajectory in a direct manner. Extensive experiments on the nuScenes dataset validate the effectiveness and scalability of our method, and demonstrate that PreWorld achieves competitive performance across 3D occupancy prediction, 4D occupancy forecasting and motion planning tasks.
Diffusion models have recently emerged as a powerful tool for planning. However, unlike Monte Carlo Tree Search (MCTS)-whose performance naturally improves with additional test-time computation (TTC), standard diffusion-based planners offer only limited avenues for TTC scalability. In this paper, we introduce Monte Carlo Tree Diffusion (MCTD), a novel framework that integrates the generative strength of diffusion models with the adaptive search capabilities of MCTS. Our method reconceptualizes denoising as a tree-structured process, allowing partially denoised plans to be iteratively evaluated, pruned, and refined. By selectively expanding promising trajectories while retaining the flexibility to revisit and improve suboptimal branches, MCTD achieves the benefits of MCTS such as controlling exploration-exploitation trade-offs within the diffusion framework. Empirical results on challenging long-horizon tasks show that MCTD outperforms diffusion baselines, yielding higher-quality solutions as TTC increases.
Segmentation of colorectal cancer (CRC) tumors in 3D medical imaging is both complex and clinically critical, providing vital support for effective radiation therapy planning and survival outcome assessment. Recently, 3D volumetric segmentation architectures incorporating long-range sequence modeling mechanisms, such as Transformers and Mamba, have gained attention for their capacity to achieve high accuracy in 3D medical image segmentation. In this work, we evaluate the effectiveness of these global token modeling techniques by pitting them against our proposed MambaOutUNet within the context of our newly introduced colorectal tumor segmentation dataset (CTS-204). Our findings suggest that robust local token interactions can outperform long-range modeling techniques in cases where the region of interest is small and anatomically complex, proposing a potential shift in 3D tumor segmentation research.
The materials science community seeks to support the FAIR principles for computational simulation research. The MatCore Project was recently launched to address this need, with the goal of developing an overall metadata framework and accompanying guidelines. This paper reports on the MatCore goals and overall progress. Historical background context is provided, including a review of the principles underlying successful core metadata standards. The paper also presents selected MatCore examples and discusses future plans.
Short-form videos are popular on platforms like TikTok and Instagram as they quickly capture viewers' attention. Many creators repurpose their long-form videos to produce short-form videos, but creators report that planning, extracting, and arranging clips from long-form videos is challenging. Currently, creators make extractive short-form videos composed of existing long-form video clips or abstractive short-form videos by adding newly recorded narration to visuals. While extractive videos maintain the original connection between audio and visuals, abstractive videos offer flexibility in selecting content to be included in a shorter time. We present Lotus, a system that combines both approaches to balance preserving the original content with flexibility over the content. Lotus first creates an abstractive short-form video by generating both a short-form script and its corresponding speech, then matching long-form video clips to the generated narration. Creators can then add extractive clips with an automated method or Lotus's editing interface. Lotus's interface can be used to further refine the short-form video. We compare short-form videos generated by Lotus with those using an extractive baseline method. In our user study, we compare creating short-form videos using Lotus to participants' existing practice.
Purpose: Laparoscopic cholecystectomy (LC) operative difficulty (LCOD) is highly variable and influences outcomes. Despite extensive LC studies in surgical workflow analysis, limited efforts explore LCOD using intraoperative video data. Early recognition of LCOD could allow prompt review by expert surgeons, enhance operating room (OR) planning, and improve surgical outcomes. Methods: We propose the clinical task of early LCOD assessment using limited video observations. We design SurgPrOD, a deep learning model to assess LCOD by analyzing features from global and local temporal resolutions (snapshots) of the observed LC video. Also, we propose a novel snapshot-centric attention (SCA) module, acting across snapshots, to enhance LCOD prediction. We introduce the CholeScore dataset, featuring video-level LCOD labels to validate our method. Results: We evaluate SurgPrOD on 3 LCOD assessment scales in the CholeScore dataset. On our new metric assessing early and stable correct predictions, SurgPrOD surpasses baselines by at least 0.22 points. SurgPrOD improves over baselines by at least 9 and 5 percentage points in F1 score and top1-accuracy, respectively, demonstrating its effectiveness in correct predictions. Conclusion: We propose a new task for early LCOD assessment and a novel model, SurgPrOD analyzing surgical video from global and local perspectives. Our results on the CholeScore dataset establishes a new benchmark to study LCOD using intraoperative video data.
Reinforcement learning (RL) and model predictive control (MPC) offer a wealth of distinct approaches for automatic decision-making. Given the impact both fields have had independently across numerous domains, there is growing interest in combining the general-purpose learning capability of RL with the safety and robustness features of MPC. To this end, this paper presents a tutorial-style treatment of RL and MPC, treating them as alternative approaches to solving Markov decision processes. In our formulation, RL aims to learn a global value function through offline exploration in an uncertain environment, whereas MPC constructs a local value function through online optimization. This local-global perspective suggests new ways to design policies that combine robustness and goal-conditioned learning. Robustness is incorporated into the RL and MPC pipelines through a scenario-based approach. Goal-conditioned learning aims to alleviate the burden of engineering a reward function for RL. Combining the two leads to a single policy that unites a robust, high-level RL terminal value function with short-term, scenario-based MPC planning for reliable constraint satisfaction. This approach leverages the benefits of both RL and MPC, the effectiveness of which is demonstrated on classical control benchmarks.
In recent years, masked diffusion models (MDMs) have emerged as a promising alternative approach for generative modeling over discrete domains. Compared to autoregressive models (ARMs), MDMs trade off complexity at training time with flexibility at inference time. At training time, they must learn to solve an exponentially large number of infilling problems, but at inference time, they can decode tokens in essentially arbitrary order. In this work, we closely examine these two competing effects. On the training front, we theoretically and empirically demonstrate that MDMs indeed train on computationally intractable subproblems compared to their autoregressive counterparts. On the inference front, we show that a suitable strategy for adaptively choosing the token decoding order significantly enhances the capabilities of MDMs, allowing them to sidestep hard subproblems. On logic puzzles like Sudoku, we show that adaptive inference can boost solving accuracy in pretrained MDMs from $<7$% to $\approx 90$%, even outperforming ARMs with $7\times$ as many parameters and that were explicitly trained via teacher forcing to learn the right order of decoding.
Autonomous drone navigation in dynamic environments remains a critical challenge, especially when dealing with unpredictable scenarios including fast-moving objects with rapidly changing goal positions. While traditional planners and classical optimisation methods have been extensively used to address this dynamic problem, they often face real-time, unpredictable changes that ultimately leads to sub-optimal performance in terms of adaptiveness and real-time decision making. In this work, we propose a novel motion planner, AgilePilot, based on Deep Reinforcement Learning (DRL) that is trained in dynamic conditions, coupled with real-time Computer Vision (CV) for object detections during flight. The training-to-deployment framework bridges the Sim2Real gap, leveraging sophisticated reward structures that promotes both safety and agility depending upon environment conditions. The system can rapidly adapt to changing environments, while achieving a maximum speed of 3.0 m/s in real-world scenarios. In comparison, our approach outperforms classical algorithms such as Artificial Potential Field (APF) based motion planner by 3 times, both in performance and tracking accuracy of dynamic targets by using velocity predictions while exhibiting 90% success rate in 75 conducted experiments. This work highlights the effectiveness of DRL in tackling real-time dynamic navigation challenges, offering intelligent safety and agility.
To achieve true scalability on massive datasets, a modern query engine needs to be able to take advantage of large, shared-memory, multicore systems. Binary joins are conceptually easy to parallelize on a multicore system; however, several applications require a different approach to query evaluation, using a Worst-Case Optimal Join (WCOJ) algorithm. WCOJ is known to outperform traditional query plans for cyclic queries. However, there is no obvious adaptation of WCOJ to parallel architectures. The few existing systems that parallelize WCOJ do this by partitioning only the top variable of the WCOJ algorithm. This leads to work skew (since some relations end up being read entirely by every thread), possible contention between threads (when the hierarchical trie index is built lazily, which is the case on most recent WCOJ systems), and exacerbates the redundant computations already existing in WCOJ. We introduce HoneyComb, a parallel version of WCOJ, optimized for large multicore, shared-memory systems. HoneyComb partitions the domains of all query variables, not just that of the top loop. We adapt the partitioning idea from the HyperCube algorithm, developed by the theory community for computing multi-join queries on a massively parallel shared-nothing architecture, and introduce new methods for computing the shares, optimized for a shared-memory architecture. To avoid the contention created by the lazy construction of the trie-index, we introduce CoCo, a new and very simple index structure, which we build eagerly, by sorting the entire relation. Finally, in order to remove some of the redundant computations of WCOJ, we introduce a rewriting technique of the WCOJ plan that factors out some of these redundant computations. Our experimental evaluation compares HoneyComb with several recent implementations of WCOJ.
The recent development of powerful AI systems has highlighted the need for robust risk management frameworks in the AI industry. Although companies have begun to implement safety frameworks, current approaches often lack the systematic rigor found in other high-risk industries. This paper presents a comprehensive risk management framework for the development of frontier AI that bridges this gap by integrating established risk management principles with emerging AI-specific practices. The framework consists of four key components: (1) risk identification (through literature review, open-ended red-teaming, and risk modeling), (2) risk analysis and evaluation using quantitative metrics and clearly defined thresholds, (3) risk treatment through mitigation measures such as containment, deployment controls, and assurance processes, and (4) risk governance establishing clear organizational structures and accountability. Drawing from best practices in mature industries such as aviation or nuclear power, while accounting for AI's unique challenges, this framework provides AI developers with actionable guidelines for implementing robust risk management. The paper details how each component should be implemented throughout the life-cycle of the AI system - from planning through deployment - and emphasizes the importance and feasibility of conducting risk management work prior to the final training run to minimize the burden associated with it.
We present DDTO--deferred-decision trajectory optimization--a framework for trajectory generation with resilience to unmodeled uncertainties and contingencies. The key idea is to ensure that a collection of candidate targets is reachable for as long as possible while satisfying constraints, which provides time to quantify the uncertainties. We propose optimization-based constrained reachability formulations and construct equivalent cardinality minimization problems, which then inform the design of computationally tractable and efficient solution methods that leverage state-of-the-art convex solvers and sequential convex programming (SCP) algorithms. The goal of establishing the equivalence between constrained reachability and cardinality minimization is to provide theoretically-sound underpinnings for the proposed solution methods. We demonstrate the solution methods on real-world optimal control applications encountered in quadrotor motion planning.
Accurate segmentation of the left atrium (LA) from late gadolinium-enhanced magnetic resonance imaging plays a vital role in visualizing diseased atrial structures, enabling the diagnosis and management of cardiovascular diseases. It is particularly essential for planning treatment with ablation therapy, a key intervention for atrial fibrillation (AF). However, manual segmentation is time-intensive and prone to inter-observer variability, underscoring the need for automated solutions. Class-agnostic foundation models like DINOv2 have demonstrated remarkable feature extraction capabilities in vision tasks. However, their lack of domain specificity and task-specific adaptation can reduce spatial resolution during feature extraction, impacting the capture of fine anatomical detail in medical imaging. To address this limitation, we propose a segmentation framework that integrates DINOv2 as an encoder with a UNet-style decoder, incorporating multi-scale feature fusion and input image integration to enhance segmentation accuracy. The learnable weighting mechanism dynamically prioritizes hierarchical features from different encoder blocks of the foundation model, optimizing feature selection for task relevance. Additionally, the input image is reintroduced during the decoding stage to preserve high-resolution spatial details, addressing limitations of downsampling in the encoder. We validate our approach on the LAScarQS 2022 dataset and demonstrate improved performance with a 92.3% Dice and 84.1% IoU score for giant architecture compared to the nnUNet baseline model. These findings emphasize the efficacy of our approach in advancing the field of automated left atrium segmentation from cardiac MRI.
Hyperspectral image (HSI) classification plays a pivotal role in domains such as environmental monitoring, agriculture, and urban planning. However, it faces significant challenges due to the high-dimensional nature of the data and the complex spectral-spatial relationships inherent in HSI. Traditional methods, including conventional machine learning and convolutional neural networks (CNNs), often struggle to effectively capture these intricate spectral-spatial features and global contextual information. Transformer-based models, while powerful in capturing long-range dependencies, often demand substantial computational resources, posing challenges in scenarios where labeled datasets are limited, as is commonly seen in HSI applications. To overcome these challenges, this work proposes GraphMamba, a hybrid model that combines spectral-spatial token generation, graph-based token prioritization, and cross-attention mechanisms. The model introduces a novel hybridization of state-space modeling and Gated Recurrent Units (GRU), capturing both linear and nonlinear spatial-spectral dynamics. GraphMamba enhances the ability to model complex spatial-spectral relationships while maintaining scalability and computational efficiency across diverse HSI datasets. Through comprehensive experiments, we demonstrate that GraphMamba outperforms existing state-of-the-art models, offering a scalable and robust solution for complex HSI classification tasks.
Diffusion models have shown great promise in decision-making, also known as diffusion planning. However, the slow inference speeds limit their potential for broader real-world applications. Here, we introduce Habi, a general framework that transforms powerful but slow diffusion planning models into fast decision-making models, which mimics the cognitive process in the brain that costly goal-directed behavior gradually transitions to efficient habitual behavior with repetitive practice. Even using a laptop CPU, the habitized model can achieve an average 800+ Hz decision-making frequency (faster than previous diffusion planners by orders of magnitude) on standard offline reinforcement learning benchmarks D4RL, while maintaining comparable or even higher performance compared to its corresponding diffusion planner. Our work proposes a fresh perspective of leveraging powerful diffusion models for real-world decision-making tasks. We also provide robust evaluations and analysis, offering insights from both biological and engineering perspectives for efficient and effective decision-making.
Ensuring safe driving while maintaining travel efficiency for autonomous vehicles in dynamic and occluded environments is a critical challenge. This paper proposes an occlusion-aware contingency safety-critical planning approach for real-time autonomous driving in such environments. Leveraging reachability analysis for risk assessment, forward reachable sets of occluded phantom vehicles are computed to quantify dynamic velocity boundaries. These velocity boundaries are incorporated into a biconvex nonlinear programming (NLP) formulation, enabling simultaneous optimization of exploration and fallback trajectories within a receding horizon planning framework. To facilitate real-time optimization and ensure coordination between trajectories, we employ the consensus alternating direction method of multipliers (ADMM) to decompose the biconvex NLP problem into low-dimensional convex subproblems. The effectiveness of the proposed approach is validated through simulation studies and real-world experiments in occluded intersections. Experimental results demonstrate enhanced safety and improved travel efficiency, enabling real-time safe trajectory generation in dynamic occluded intersections under varying obstacle conditions. A video showcasing the experimental results is available at https://youtu.be/CHayG7NChqM.
During crowd navigation, robot motion plan needs to consider human motion uncertainty, and the human motion uncertainty is dependent on the robot motion plan. We introduce Interaction-aware Conformal Prediction (ICP) to alternate uncertainty-aware robot motion planning and decision-dependent human motion uncertainty quantification. ICP is composed of a trajectory predictor to predict human trajectories, a model predictive controller to plan robot motion with confidence interval radii added for probabilistic safety, a human simulator to collect human trajectory calibration dataset conditioned on the planned robot motion, and a conformal prediction module to quantify trajectory prediction error on the decision-dependent calibration dataset. Crowd navigation simulation experiments show that ICP strikes a good balance of performance among navigation efficiency, social awareness, and uncertainty quantification compared to previous works. ICP generalizes well to navigation tasks under various crowd densities. The fast runtime and efficient memory usage make ICP practical for real-world applications. Code is available at https://github.com/tedhuang96/icp.
The COVID-19 pandemic underscored the critical need for rapid epidemic trend identification and effective intervention strategies to mitigate disease progression and its socio-economic impact. Concurrent with emerging threats, endemic diseases like dengue continue to strain healthcare systems, particularly in populous, economically challenged nations. This paper introduces AVSim (Airborne and Vectorborne Simulator), an agent-based model designed to provide granular insights for optimizing resource allocation within existing healthcare management frameworks. AVSim leverages realistic human mobility and behavioral patterns to simulate disease propagation within a detailed, scalable environment encompassing homes, schools, hospitals, and commercial venues. Human movement is modeled based on occupational and behavioral patterns, including age-specific activities. The simulator incorporates age- and environment-specific disease outcomes, host-host and host-vector interactions, and multiple disease stages, including mild, severe, and critical phases. Immunity, quarantine, and hospitalization are also modeled. Furthermore, AVSim supports tracing the path of disease spread, providing micro-level insights into transmission dynamics. Implemented in Python, AVSim offers flexibility and extensibility, enabling users to create highly customized scenarios for airborne and vector-borne disease modeling. Case studies demonstrating AVSim's application to COVID-19 and dengue illustrate its potential for generating actionable epidemic insights, thereby enhancing public health planning and response.
Unsupervised Continuous Anomaly Detection (UCAD) faces significant challenges in multi-task representation learning, with existing methods suffering from incomplete representation and catastrophic forgetting. Unlike supervised models, unsupervised scenarios lack prior information, making it difficult to effectively distinguish redundant and complementary multimodal features. To address this, we propose the Multimodal Task Representation Memory Bank (MTRMB) method through two key technical innovations: A Key-Prompt-Multimodal Knowledge (KPMK) mechanism that uses concise key prompts to guide cross-modal feature interaction between BERT and ViT. Refined Structure-based Contrastive Learning (RSCL) leveraging Grounding DINO and SAM to generate precise segmentation masks, pulling features of the same structural region closer while pushing different structural regions apart. Experiments on MVtec AD and VisA datasets demonstrate MTRMB's superiority, achieving an average detection accuracy of 0.921 at the lowest forgetting rate, significantly outperforming state-of-the-art methods. We plan to open source on GitHub.
Despite the promise of synthesizing high-fidelity videos, Diffusion Transformers (DiTs) with 3D full attention suffer from expensive inference due to the complexity of attention computation and numerous sampling steps. For example, the popular Open-Sora-Plan model consumes more than 9 minutes for generating a single video of 29 frames. This paper addresses the inefficiency issue from two aspects: 1) Prune the 3D full attention based on the redundancy within video data; We identify a prevalent tile-style repetitive pattern in the 3D attention maps for video data, and advocate a new family of sparse 3D attention that holds a linear complexity w.r.t. the number of video frames. 2) Shorten the sampling process by adopting existing multi-step consistency distillation; We split the entire sampling trajectory into several segments and perform consistency distillation within each one to activate few-step generation capacities. We further devise a three-stage training pipeline to conjoin the low-complexity attention and few-step generation capacities. Notably, with 0.1% pretraining data, we turn the Open-Sora-Plan-1.2 model into an efficient one that is 7.4x -7.8x faster for 29 and 93 frames 720p video generation with a marginal performance trade-off in VBench. In addition, we demonstrate that our approach is amenable to distributed inference, achieving an additional 3.91x speedup when running on 4 GPUs with sequence parallelism.
This paper introduces a new mission planning algorithm for autonomous robots that enables the reward-based selection of an optimal waypoint sequence from a predefined set. The algorithm computes a feasible trajectory and corresponding control inputs for a robot to navigate between waypoints while avoiding obstacles, maximizing the total reward, and adhering to constraints on state, input and its derivatives, mission time window, and maximum distance. This also solves a generalized prize-collecting traveling salesman problem. The proposed algorithm employs a new genetic algorithm that evolves solution candidates toward the optimal solution based on a fitness function and crossover. During fitness evaluation, a penalty method enforces constraints, and the differential flatness property with clothoid curves efficiently penalizes infeasible trajectories. The Euler spiral method showed promising results for trajectory parameterization compared to minimum snap and jerk polynomials. Due to the discrete exploration space, crossover is performed using a dynamic time-warping-based method and extended convex combination with projection. A mutation step enhances exploration. Results demonstrate the algorithm's ability to find the optimal waypoint sequence, fulfill constraints, avoid infeasible waypoints, and prioritize high-reward ones. Simulations and experiments with a ground vehicle, quadrotor, and quadruped are presented, complemented by benchmarking and a time-complexity analysis.
Efficient exploration is critical for learning relational models in large-scale environments with complex, long-horizon tasks. Random exploration methods often collect redundant or irrelevant data, limiting their ability to learn accurate relational models of the environment. Goal-literal babbling (GLIB) improves upon random exploration by setting and planning to novel goals, but its reliance on random actions and random novel goal selection limits its scalability to larger domains. In this work, we identify the principles underlying efficient exploration in relational domains: (1) operator initialization with demonstrations that cover the distinct lifted effects necessary for planning and (2) refining preconditions to collect maximally informative transitions by selecting informative goal-action pairs and executing plans to them. To demonstrate these principles, we introduce Baking-Large, a challenging domain with extensive state-action spaces and long-horizon tasks. We evaluate methods using oracle-driven demonstrations for operator initialization and precondition-targeting guidance to efficiently gather critical transitions. Experiments show that both the oracle demonstrations and precondition-targeting oracle guidance significantly improve sample efficiency and generalization, paving the way for future methods to use these principles to efficiently learn accurate relational models in complex domains.
This paper describes the problem of coordination of an autonomous Multi-Agent System which aims to solve the coverage planning problem in a complex environment. The considered applications are the detection and identification of objects of interest while covering an area. These tasks, which are highly relevant for space applications, are also of interest among various domains including the underwater context, which is the focus of this study. In this context, coverage planning is traditionally modelled as a Markov Decision Process where a coordinated MAS, a swarm of heterogeneous autonomous underwater vehicles, is required to survey an area and search for objects. This MDP is associated with several challenges: environment uncertainties, communication constraints, and an ensemble of hazards, including time-varying and unpredictable changes in the underwater environment. MARL algorithms can solve highly non-linear problems using deep neural networks and display great scalability against an increased number of agents. Nevertheless, most of the current results in the underwater domain are limited to simulation due to the high learning time of MARL algorithms. For this reason, a novel strategy is introduced to accelerate this convergence rate by incorporating biologically inspired heuristics to guide the policy during training. The PSO method, which is inspired by the behaviour of a group of animals, is selected as a heuristic. It allows the policy to explore the highest quality regions of the action and state spaces, from the beginning of the training, optimizing the exploration/exploitation trade-off. The resulting agent requires fewer interactions to reach optimal performance. The method is applied to the MSAC algorithm and evaluated for a 2D covering area mission in a continuous control environment.
Ground truth labels/outcomes are critical for advancing scientific and engineering applications, e.g., evaluating the treatment effect of an intervention or performance of a predictive model. Since randomly sampling inputs for labeling can be prohibitively expensive, we introduce an adaptive labeling framework where measurement effort can be reallocated in batches. We formulate this problem as a Markov decision process where posterior beliefs evolve over time as batches of labels are collected (state transition), and batches (actions) are chosen to minimize uncertainty at the end of data collection. We design a computational framework that is agnostic to different uncertainty quantification approaches including those based on deep learning, and allows a diverse array of policy gradient approaches by relying on continuous policy parameterizations. On real and synthetic datasets, we demonstrate even a one-step lookahead policy can substantially outperform common adaptive labeling heuristics, highlighting the virtue of planning. On the methodological side, we note that standard REINFORCE-style policy gradient estimators can suffer high variance since they rely only on zeroth order information. We propose a direct backpropagation-based approach, Smoothed-Autodiff, based on a carefully smoothed version of the original non-differentiable MDP. Our method enjoys low variance at the price of introducing bias, and we theoretically and empirically show that this trade-off can be favorable.
One of the most far-reaching use cases of the internet of things is in smart grid and smart home operation. The smart home concept allows residents to control, monitor, and manage their energy consumption with minimum loss and self-involvement. Since each household's lifestyle and energy consumption is unique, the management system needs background knowledge about residents' energy consumption behavioral patterns for more accurate planning. To obtain this information, data related to residents' consumption records must be processed. This research has attempted to provide an optimal decentralized management system consisting of interoperable sections to forecast, optimize, schedule, and implement load management in a smart home. Comparing different prediction models using 4 years of 1-min interval real data of a smart home with photovoltaic generation (PV) and electric vehicle (EV), forecasting non-controllable loads and taking a deterministic approach in different scenarios, the system uses mixed integer linear programming (MILP) to provide load scheduling with the objective of an optimal total energy cost reduction with minimum changes in the household's desired consumption compared to the initial state. The results have shown that the proposed system has reliable performance due to the high precision of the forecast and has led to increased energy efficiency, reduced energy cost (up to 62. 05\%), reduced peak-to-average ratio (PAR) (up to 44. 19\%) and reduced standard deviation (SD) (up to 19. 70\%) in net consumption.
Understanding the generation and development of the continuous outflow from the Sun requires tracing the physical conditions from deep in the corona to the heliosphere. Detailed global observations of plasma state variables and the magnetic field are needed to provide critical constraints to the underlying physics driving models of the corona and solar wind. Key diagnostics of the solar wind require measurements at its formation site and during its outflow to continuously track it across rapidly changing regions of space. A unified view of the solar wind is only possible through coordinated remote and in situ observations that probe these different regions. Here, we discuss current observational coverage and gaps of different plasma properties and review recent coordinated studies. We highlight how these efforts may become more routine with the launch of upcoming and planned missions.
Vision-based object tracking is a critical component for achieving autonomous aerial navigation, particularly for obstacle avoidance. Neuromorphic Dynamic Vision Sensors (DVS) or event cameras, inspired by biological vision, offer a promising alternative to conventional frame-based cameras. These cameras can detect changes in intensity asynchronously, even in challenging lighting conditions, with a high dynamic range and resistance to motion blur. Spiking neural networks (SNNs) are increasingly used to process these event-based signals efficiently and asynchronously. Meanwhile, physics-based artificial intelligence (AI) provides a means to incorporate system-level knowledge into neural networks via physical modeling. This enhances robustness, energy efficiency, and provides symbolic explainability. In this work, we present a neuromorphic navigation framework for autonomous drone navigation. The focus is on detecting and navigating through moving gates while avoiding collisions. We use event cameras for detecting moving objects through a shallow SNN architecture in an unsupervised manner. This is combined with a lightweight energy-aware physics-guided neural network (PgNN) trained with depth inputs to predict optimal flight times, generating near-minimum energy paths. The system is implemented in the Gazebo simulator and integrates a sensor-fused vision-to-planning neuro-symbolic framework built with the Robot Operating System (ROS) middleware. This work highlights the future potential of integrating event-based vision with physics-guided planning for energy-efficient autonomous navigation, particularly for low-latency decision-making.
Robotic grasping is facing a variety of real-world uncertainties caused by non-static object states, unknown object properties, and cluttered object arrangements. The difficulty of grasping increases with the presence of more uncertainties, where commonly used learning-based approaches struggle to perform consistently across varying conditions. In this study, we integrate the idea of similarity matching to tackle the challenge of grasping novel objects that are simultaneously in motion and densely cluttered using a single RGBD camera, where multiple uncertainties coexist. We achieve this by shifting visual detection from global to local states and operating grasp planning from static to dynamic scenes. Notably, we introduce optimization methods to enhance planning efficiency for this time-sensitive task. Our proposed system can adapt to various object types, arrangements and movement speeds without the need for extensive training, as demonstrated by real-world experiments. Videos are available at https://youtu.be/sdC50dx-xp8?si=27oVr4dhG0rqN_tT.
Cardinality estimation is the problem of estimating the size of the output of a query, without actually evaluating the query. The cardinality estimator is a critical piece of a query optimizer, and is often the main culprit when the optimizer chooses a poor plan. This paper introduces LpBound, a pessimistic cardinality estimator for multijoin queries (acyclic or cyclic) with selection predicates and group-by clauses. LpBound computes a guaranteed upper bound on the size of the query output using simple statistics on the input relations, consisting of $\ell_p$-norms of degree sequences. The bound is the optimal solution of a linear program whose constraints encode data statistics and Shannon inequalities. We introduce two optimizations that exploit the structure of the query in order to speed up the estimation time and make LpBound practical. We experimentally evaluate LpBound against a range of traditional, pessimistic, and machine learning-based estimators on the JOB, STATS, and subgraph matching benchmarks. Our main finding is that LpBound can be orders of magnitude more accurate than traditional estimators used in mainstream open-source and commercial database systems. Yet it has comparable low estimation time and space requirements. When injected the estimates of LpBound, Postgres derives query plans at least as good as those derived using the true cardinalities.
Medical images often exhibit low and blurred contrast between lesions and surrounding tissues, with considerable variation in lesion edges and shapes even within the same disease, leading to significant challenges in segmentation. Therefore, precise segmentation of lesions has become an essential prerequisite for patient condition assessment and formulation of treatment plans. Significant achievements have been made in research related to the U-Net model in recent years. It improves segmentation performance and is extensively applied in the semantic segmentation of medical images to offer technical support for consistent quantitative lesion analysis methods. First, this paper classifies medical image datasets on the basis of their imaging modalities and then examines U-Net and its various improvement models from the perspective of structural modifications. The research objectives, innovative designs, and limitations of each approach are discussed in detail. Second, we summarize the four central improvement mechanisms of the U-Net and U-Net variant algorithms: the jump-connection mechanism, residual-connection mechanism, 3D-UNet, and transformer mechanism. Finally, we examine the relationships among the four core enhancement mechanisms and commonly utilized medical datasets and propose potential avenues and strategies for future advancements. This paper provides a systematic summary and reference for researchers in related fields, and we look forward to designing more efficient and stable medical image segmentation network models based on the U-Net network.
Humans learn from observations and experiences to adjust their behaviours towards better performance. Interacting with such dynamic humans is challenging, as the robot needs to predict the humans accurately for safe and efficient operations. Long-term interactions with dynamic humans have not been extensively studied by prior works. We propose an adaptive human prediction model based on the Theory-of-Mind (ToM), a fundamental social-cognitive ability that enables humans to infer others' behaviours and intentions. We formulate the human internal belief about others using a game-theoretic model, which predicts the future motions of all agents in a navigation scenario. To estimate an evolving belief, we use an Unscented Kalman Filter to update the behavioural parameters in the human internal model. Our formulation provides unique interpretability to dynamic human behaviours by inferring how the human predicts the robot. We demonstrate through long-term experiments in both simulations and real-world settings that our prediction effectively promotes safety and efficiency in downstream robot planning. Code will be available at https://github.com/centiLinda/AToM-human-prediction.git.
Urban digital twins are virtual replicas of cities that use multi-source data and data analytics to optimize urban planning, infrastructure management, and decision-making. Towards this, we propose a framework focused on the single-building scale. By connecting to cloud mapping platforms such as Google Map Platforms APIs, by leveraging state-of-the-art multi-agent Large Language Models data analysis using ChatGPT(4o) and Deepseek-V3/R1, and by using our Gaussian Splatting-based mesh extraction pipeline, our Digital Twin Buildings framework can retrieve a building's 3D model, visual descriptions, and achieve cloud-based mapping integration with large language model-based data analytics using a building's address, postal code, or geographic coordinates.
Understanding the progression trajectories of diseases is crucial for early diagnosis and effective treatment planning. This is especially vital for life-threatening conditions such as Idiopathic Pulmonary Fibrosis (IPF), a chronic, progressive lung disease with a prognosis comparable to many cancers. Computed tomography (CT) imaging has been established as a reliable diagnostic tool for IPF. Accurately predicting future CT scans of early-stage IPF patients can aid in developing better treatment strategies, thereby improving survival outcomes. In this paper, we propose 4D Vector Quantised Generative Adversarial Networks (4D-VQ-GAN), a model capable of generating realistic CT volumes of IPF patients at any time point. The model is trained using a two-stage approach. In the first stage, a 3D-VQ-GAN is trained to reconstruct CT volumes. In the second stage, a Neural Ordinary Differential Equation (ODE) based temporal model is trained to capture the temporal dynamics of the quantised embeddings generated by the encoder in the first stage. We evaluate different configurations of our model for generating longitudinal CT scans and compare the results against ground truth data, both quantitatively and qualitatively. For validation, we conduct survival analysis using imaging biomarkers derived from generated CT scans and achieve a C-index comparable to that of biomarkers derived from the real CT scans. The survival analysis results demonstrate the potential clinical utility inherent to generated longitudinal CT scans, showing that they can reliably predict survival outcomes.
Recent deep learning-based image completion methods, including both inpainting and outpainting, have demonstrated promising results in restoring corrupted images by effectively filling various missing regions. Among these, Generative Adversarial Networks (GANs) and Denoising Diffusion Probabilistic Models (DDPMs) have been employed as key generative image completion approaches, excelling in the field of generating high-quality restorations with reduced artifacts and improved fine details. In previous work, we developed a method aimed at synthesizing views from novel microscope positions for mastoidectomy surgeries; however, that approach did not have the ability to restore the surrounding surgical scene environment. In this paper, we propose an efficient method to complete the surgical scene of the synthetic postmastoidectomy dataset. Our approach leverages self-supervised learning on real surgical datasets to train a Single-Step Denoising Diffusion-GAN (SSDD-GAN), combining the advantages of diffusion models with the adversarial optimization of GANs for improved Structural Similarity results of 6%. The trained model is then directly applied to the synthetic postmastoidectomy dataset using a zero-shot approach, enabling the generation of realistic and complete surgical scenes without the need for explicit ground-truth labels from the synthetic postmastoidectomy dataset. This method addresses key limitations in previous work, offering a novel pathway for full surgical microscopy scene completion and enhancing the usability of the synthetic postmastoidectomy dataset in surgical preoperative planning and intraoperative navigation.
This paper proposes a novel approach using Graph Neural Networks (GNNs) to solve the AC Power Flow problem in power grids. AC OPF is essential for minimizing generation costs while meeting the operational constraints of the grid. Traditional solvers struggle with scalability, especially in large systems with renewable energy sources. Our approach models the power grid as a graph, where buses are nodes and transmission lines are edges. We explore different GNN architectures, including GCN, GAT, SAGEConv, and GraphConv to predict AC power flow solutions efficiently. Our experiments on IEEE test systems show that GNNs can accurately predict power flow solutions and scale to larger systems, outperforming traditional solvers in terms of computation time. This work highlights the potential of GNNs for real-time power grid management, with future plans to apply the model to even larger grid systems.
Numerical methods that preserves geometric invariants of the system such as energy, momentum and symplectic form, are called geometric integrators. These include variational integrators as an important subclass of geometric integrators. The general idea for those variational integrators is to discretize Hamilton's principle rather than the equations of motion and as a consequence these methods preserves some of the invariants of the original system (symplecticity, symmetry, good behavior of energy,...). In this paper, we construct variational integrators for control-dependent Lagrangian systems on Lie groups. These integrators are derived via a discrete-time variational principle for discrete-time control-dependent reduced Lagrangians. We employ the variational integrator into optimal control problems for path planning of foldable unmanned aerial vehicles (UAVs). Simulation are shown to validate the performance of the geometric integrator.
We completely characterise the optimal solutions for the three-marginal optimal transport problem - introduced in [K. Bolbotowski, G. Bouchitt\'e, Kantorovich-Rubinstein duality theory for the Hessian, 2024, preprint], and whose relaxation is the second-order Beckmann problem - for arbitrary pairs $\mu,\nu\in\mathcal{P}_2(\mathbb{R}^n)$ of absolutely continuous measures with common barycentre such that there exists an optimal plan with absolutely continuous third marginal. In our work, we define the concept of bimartingale couplings for a pair of measures and establish several equivalent conditions that ensure such couplings exist. One of these conditions is that the pair is ordered according to the convex-concave order, thereby generalising the classical Strassen theorem. Another equivalent condition is that the dual problem associated with the second-order Beckmann problem attains its optimum at a $\mathcal{C}^{1,1}(\mathbb{R}^n)$ function with isometric derivative. We prove that the problem for $\mu,\nu$ completely decomposes into a collection of simpler problems on the leaves of the $1$-Lipschitz derivative $Du$ of an optimal solution $u\in\mathcal{C}^{1,1}(\mathbb{R}^n)$ for the dual problem. On each such, leaf the solution is expressed in terms of bimartingale couplings between conditional measures of $\mu,\nu$, where the conditioning is defined relative to the foliation induced by $Du$.
One of the most frequent modalities of breast cancer treatment is surgery. Breast surgery can cause visual alterations to the breasts, due to scars and asymmetries. To enable an informed choice of treatment, the patient must be adequately informed of the aesthetic outcomes of each treatment plan. In this work, we propose an inpainting approach to manipulate breast shape and nipple position in breast images, for the purpose of predicting the aesthetic outcomes of breast cancer treatment. We perform experiments with various model architectures for the inpainting task, including invertible networks capable of manipulating breasts in the absence of ground-truth breast contour and nipple annotations. Experiments on two breast datasets show the proposed models' ability to realistically alter a patient's breasts, enabling a faithful reproduction of breast asymmetries of post-operative patients in pre-operative images.
This work focuses on generating realistic, physically-based human behaviors from multi-modal inputs, which may only partially specify the desired motion. For example, the input may come from a VR controller providing arm motion and body velocity, partial key-point animation, computer vision applied to videos, or even higher-level motion goals. This requires a versatile low-level humanoid controller that can handle such sparse, under-specified guidance, seamlessly switch between skills, and recover from failures. Current approaches for learning humanoid controllers from demonstration data capture some of these characteristics, but none achieve them all. To this end, we introduce the Masked Humanoid Controller (MHC), a novel approach that applies multi-objective imitation learning on augmented and selectively masked motion demonstrations. The training methodology results in an MHC that exhibits the key capabilities of catch-up to out-of-sync input commands, combining elements from multiple motion sequences, and completing unspecified parts of motions from sparse multimodal input. We demonstrate these key capabilities for an MHC learned over a dataset of 87 diverse skills and showcase different multi-modal use cases, including integration with planning frameworks to highlight MHC's ability to solve new user-defined tasks without any finetuning.
Pick-and-place (PnP) operations, featuring object grasping and trajectory planning, are fundamental in industrial robotics applications. Despite many advancements in the field, PnP is limited by workspace constraints, reducing flexibility. Pick-and-throw (PnT) is a promising alternative where the robot throws objects to target locations, leveraging extrinsic resources like gravity to improve efficiency and expand the workspace. However, PnT execution is complex, requiring precise coordination of high-speed movements and object dynamics. Solutions to the PnT problem are categorized into analytical and learning-based approaches. Analytical methods focus on system modeling and trajectory generation but are time-consuming and offer limited generalization. Learning-based solutions, in particular Model-Free Reinforcement Learning (MFRL), offer automation and adaptability but require extensive interaction time. This paper introduces a Model-Based Reinforcement Learning (MBRL) framework, MC-PILOT, which combines data-driven modeling with policy optimization for efficient and accurate PnT tasks. MC-PILOT accounts for model uncertainties and release errors, demonstrating superior performance in simulations and real-world tests with a Franka Emika Panda manipulator. The proposed approach generalizes rapidly to new targets, offering advantages over analytical and Model-Free methods.
In fast-paced, ever-changing environments, dynamic Motion Planning for Multi-Agent Systems in the presence of obstacles is a universal and unsolved problem. Be it from path planning around obstacles to the movement of robotic arms, or in planning navigation of robot teams in settings such as Robosoccer, dynamic motion planning is needed to avoid collisions while reaching the targeted destination when multiple agents occupy the same area. In continuous domains where the world changes quickly, existing classical Motion Planning algorithms such as RRT* and A* become computationally expensive to rerun at every time step. Many variations of classical and well-formulated non-learning path-planning methods have been proposed to solve this universal problem but fall short due to their limitations of speed, smoothness, optimally, etc. Deep Learning models overcome their challenges due to their ability to adapt to varying environments based on past experience. However, current learning motion planning models use discretized environments, do not account for heterogeneous agents or replanning, and build up to improve the classical motion planners' efficiency, leading to issues with scalability. To prevent collisions between heterogenous team members and collision to obstacles while trying to reach the target location, we present a learning-based dynamic navigation model and show our model working on a simple environment in the concept of a simple Robosoccer Game.
Model validity is key to the accurate and safe behavior of autonomous vehicles. Using invalid vehicle models in the different plan and control vehicle frameworks puts the stability of the vehicle, and thus its safety at stake. In this work, we analyze the validity of several popular vehicle models used in the literature with respect to a real vehicle and we prove that serious accuracy issues are encountered beyond a specific lateral acceleration point. We set a clear lateral acceleration domain in which the used models are an accurate representation of the behavior of the vehicle. We then target the necessity of using learned methods to model the vehicle's behavior. The effects of model validity on state observers are investigated. The performance of model-based observers is compared to learning-based ones. Overall, the presented work emphasizes the validity of vehicle models and presents clear operational domains in which models could be used safely.
This study demonstrates a novel use of the U-Net architecture in the field of semantic segmentation to detect landforms using preprocessed satellite imagery. The study applies the U-Net model for effective feature extraction by using Convolutional Neural Network (CNN) segmentation techniques. Dropout is strategically used for regularization to improve the model's perseverance, and the Adam optimizer is used for effective training. The study thoroughly assesses the performance of the U-Net architecture utilizing a large sample of preprocessed satellite topographical images. The model excels in semantic segmentation tasks, displaying high-resolution outputs, quick feature extraction, and flexibility to a wide range of applications. The findings highlight the U-Net architecture's substantial contribution to the advancement of machine learning and image processing technologies. The U-Net approach, which emphasizes pixel-wise categorization and comprehensive segmentation map production, is helpful in practical applications such as autonomous driving, disaster management, and land use planning. This study not only investigates the complexities of U-Net architecture for semantic segmentation, but also highlights its real-world applications in image classification, analysis, and landform identification. The study demonstrates the U-Net model's key significance in influencing the environment of modern technology.
We propose a real-time implementable motion planning technique for cooperative object transportation by nonholonomic mobile manipulator robots (MMRs) in an environment with static and dynamic obstacles. The proposed motion planning technique works in two steps. A novel visibility vertices-based path planning algorithm computes a global piece-wise linear path between the start and the goal location in the presence of static obstacles offline. It defines the static obstacle free space around the path with a set of convex polygons for the online motion planner. We employ a Nonliner Model Predictive Control (NMPC) based online motion planning technique for nonholonomic MMRs that jointly plans for the mobile base and the manipulators arm. It efficiently utilizes the locomotion capability of the mobile base and the manipulation capability of the arm. The motion planner plans feasible motion for the MMRs and generates trajectory for object transportation considering the kinodynamic constraints and the static and dynamic obstacles. The efficiency of our approach is validated by numerical simulation and hardware experiments in varied environments.
Effective task representations should facilitate compositionality, such that after learning a variety of basic tasks, an agent can perform compound tasks consisting of multiple steps simply by composing the representations of the constituent steps together. While this is conceptually simple and appealing, it is not clear how to automatically learn representations that enable this sort of compositionality. We show that learning to associate the representations of current and future states with a temporal alignment loss can improve compositional generalization, even in the absence of any explicit subtask planning or reinforcement learning. We evaluate our approach across diverse robotic manipulation tasks as well as in simulation, showing substantial improvements for tasks specified with either language or goal images.
Segmentation of 3D medical images is a critical task for accurate diagnosis and treatment planning. Convolutional neural networks (CNNs) have dominated the field, achieving significant success in 3D medical image segmentation. However, CNNs struggle with capturing long-range dependencies and global context, limiting their performance, particularly for fine and complex structures. Recent transformer-based models, such as TransUNet and nnFormer, have demonstrated promise in addressing these limitations, though they still rely on hybrid CNN-transformer architectures. This paper introduces a novel, fully convolutional-free model based on transformer architecture and self-attention mechanisms for 3D medical image segmentation. Our approach focuses on improving multi-semantic segmentation accuracy and addressing domain adaptation challenges between thick and thin slice CT images. We propose a joint loss function that facilitates effective segmentation of thin slices based on thick slice annotations, overcoming limitations in dataset availability. Furthermore, we present a benchmark dataset for multi-semantic segmentation on thin slices, addressing a gap in current medical imaging research. Our experiments demonstrate the superiority of the proposed model over traditional and hybrid architectures, offering new insights into the future of convolution-free medical image segmentation.
This work addresses the problem of active 3D mapping, where an agent must find an efficient trajectory to exhaustively reconstruct a new scene. Previous approaches mainly predict the next best view near the agent's location, which is prone to getting stuck in local areas. Additionally, existing indoor datasets are insufficient due to limited geometric complexity and inaccurate ground truth meshes. To overcome these limitations, we introduce a novel dataset AiMDoom with a map generator for the Doom video game, enabling to better benchmark active 3D mapping in diverse indoor environments. Moreover, we propose a new method we call next-best-path (NBP), which predicts long-term goals rather than focusing solely on short-sighted views. The model jointly predicts accumulated surface coverage gains for long-term goals and obstacle maps, allowing it to efficiently plan optimal paths with a unified model. By leveraging online data collection, data augmentation and curriculum learning, NBP significantly outperforms state-of-the-art methods on both the existing MP3D dataset and our AiMDoom dataset, achieving more efficient mapping in indoor environments of varying complexity.
Multi-class segmentation of the aorta in computed tomography angiography (CTA) scans is essential for diagnosing and planning complex endovascular treatments for patients with aortic dissections. However, existing methods reduce aortic segmentation to a binary problem, limiting their ability to measure diameters across different branches and zones. Furthermore, no open-source dataset is currently available to support the development of multi-class aortic segmentation methods. To address this gap, we organized the AortaSeg24 MICCAI Challenge, introducing the first dataset of 100 CTA volumes annotated for 23 clinically relevant aortic branches and zones. This dataset was designed to facilitate both model development and validation. The challenge attracted 121 teams worldwide, with participants leveraging state-of-the-art frameworks such as nnU-Net and exploring novel techniques, including cascaded models, data augmentation strategies, and custom loss functions. We evaluated the submitted algorithms using the Dice Similarity Coefficient (DSC) and Normalized Surface Distance (NSD), highlighting the approaches adopted by the top five performing teams. This paper presents the challenge design, dataset details, evaluation metrics, and an in-depth analysis of the top-performing algorithms. The annotated dataset, evaluation code, and implementations of the leading methods are publicly available to support further research. All resources can be accessed at https://aortaseg24.grand-challenge.org.
The Highway Performance Monitoring System, managed by the Federal Highway Administration, provides essential data on average annual daily traffic across U.S. roadways, but it has limited representation of medium- and heavy-duty vehicles on non-interstate roads. This gap limits research and policy analysis on the impacts of truck traffic, especially concerning air quality and public health. To address this, we use random forest regression to estimate medium- and heavy-duty vehicle traffic volumes in areas with sparse data. This results in a more comprehensive dataset, which enables the estimation of traffic density at the census block level as a proxy for traffic-related air pollution exposure. Our high-resolution spatial data products, rigorously validated, provide a more accurate representation of truck traffic and its environmental and health impacts. These datasets are valuable for transportation planning, public health research, and policy decisions aimed at mitigating the effects of truck traffic on vulnerable communities exposed to air pollution.
This paper addresses stochastic charger location and allocation (SCLA) problems under queue congestion for last-mile delivery using electric vehicles (EVs). The objective is to decide where to open charging stations and how many chargers of each type to install, subject to budgetary and waiting-time constraints. We formulate the problem as a mixed-integer non-linear program, where each station-charger pair is modeled as a multiserver queue with stochastic arrivals and service times to capture the notion of waiting in fleet operations. The model is extremely large, with billions of variables and constraints for a typical metropolitan area; and even loading the model in solver memory is difficult, let alone solving it. To address this challenge, we develop a Lagrangian-based dual decomposition framework that decomposes the problem by station and leverages parallelization on high-performance computing systems, where the subproblems are solved by using a cutting plane method and their solutions are collected at the master level. We also develop a three-step rounding heuristic to transform the fractional subproblem solutions into feasible integral solutions. Computational experiments on data from the Chicago metropolitan area with hundreds of thousands of households and thousands of candidate stations show that our approach produces high-quality solutions in cases where existing exact methods cannot even load the model in memory. We also analyze various policy scenarios, demonstrating that combining existing depots with newly built stations under multiagency collaboration substantially reduces costs and congestion. These findings offer a scalable and efficient framework for developing sustainable large-scale EV charging networks.
Analytics database workloads often contain queries that are executed repeatedly. Existing optimization techniques generally prioritize keeping optimization cost low, normally well below the time it takes to execute a single instance of a query. If a given query is going to be executed thousands of times, could it be worth investing significantly more optimization time? In contrast to traditional online query optimizers, we propose an offline query optimizer that searches a wide variety of plans and incorporates query execution as a primitive. Our offline query optimizer combines variational auto-encoders with Bayesian optimization to find optimized plans for a given query. We compare our technique to the optimal plans possible with PostgreSQL and recent RL-based systems over several datasets, and show that our technique finds faster query plans.
The growing need for companies to reduce costs and maximize profits has led to an increased focus on logistics activities. Among these, inventory management plays a crucial role in minimizing organizational expenses by optimizing the storage and transportation of materials. In this context, this study introduces an optimization model for the lot-sizing problem based on a physical system approach. By establishing that the material supply problem is isomorphic to a one-dimensional mechanical system of point particles connected by elastic elements, we leverage this analogy to derive cost optimization conditions naturally and obtain an exact solution. This approach determines lot sizes that minimize the combined ordering and inventory holding costs in a significantly shorter time, eliminating the need for heuristic methods. The optimal lot sizes are defined in terms of the parameter $ \gamma = 2C_O / C_H $, which represents the relationship between the ordering cost per order ($ C_O $) and the holding cost per period for the material required in one period ($ C_H $). This parameter fully dictates the system's behavior: when $ \gamma \leq 1 $, the optimal strategy is to place one order per period, whereas for $ \gamma > 1 $, the number of orders $ N $ is reduced relative to the planning horizon $ M $, meaning $ N < M $. By formulating the total cost function in terms of the intensive variable $ N/M $, we consolidate the entire optimization problem into a single function of $ \gamma $. This eliminates the need for complex algorithms, enabling faster and more precise purchasing decisions. The proposed model was validated through a real-world case study and benchmarked against classical algorithms, demonstrating superior cost optimization and reduced execution time. These findings underscore the potential of this approach for improving material lot-sizing strategies.
[Background] Emotional Intelligence (EI) can impact Software Engineering (SE) outcomes through improved team communication, conflict resolution, and stress management. SE workers face increasing pressure to develop both technical and interpersonal skills, as modern software development emphasizes collaborative work and complex team interactions. Despite EI's documented importance in professional practice, SE education continues to prioritize technical knowledge over emotional and social competencies. [Objective] This paper analyzes SE students' self-perceptions of their EI after a two-month cooperative learning project, using Mayer and Salovey's four-ability model to examine how students handle emotions in collaborative development. [Method] We conducted a case study with 29 SE students organized into four squads within a project-based learning course, collecting data through questionnaires and focus groups that included brainwriting and sharing circles, then analyzing the data using descriptive statistics and open coding. [Results] Students demonstrated stronger abilities in managing their own emotions compared to interpreting others' emotional states. Despite limited formal EI training, they developed informal strategies for emotional management, including structured planning and peer support networks, which they connected to improved productivity and conflict resolution. [Conclusion] This study shows how SE students perceive EI in a collaborative learning context and provides evidence-based insights into the important role of emotional competencies in SE education.
Consumer energy forecasting is essential for managing energy consumption and planning, directly influencing operational efficiency, cost reduction, personalized energy management, and sustainability efforts. In recent years, deep learning techniques, especially LSTMs and transformers, have been greatly successful in the field of energy consumption forecasting. Nevertheless, these techniques have difficulties in capturing complex and sudden variations, and, moreover, they are commonly examined only on a specific type of consumer (e.g., only offices, only schools). Consequently, this paper proposes HyperEnergy, a consumer energy forecasting strategy that leverages hypernetworks for improved modeling of complex patterns applicable across a diversity of consumers. Hypernetwork is responsible for predicting the parameters of the primary prediction network, in our case LSTM. A learnable adaptable kernel, comprised of polynomial and radial basis function kernels, is incorporated to enhance performance. The proposed HyperEnergy was evaluated on diverse consumers including, student residences, detached homes, a home with electric vehicle charging, and a townhouse. Across all consumer types, HyperEnergy consistently outperformed 10 other techniques, including state-of-the-art models such as LSTM, AttentionLSTM, and transformer.
Hadrontherapy is a promising cancer treatment method that offers better dose conformity and reduces damage to healthy tissues compared to conventional radiotherapy. However, one major challenge remaining is the precise characterization of secondary particles generated by nuclear interactions of the primary beam with tissues. Current data on secondary charged particles, such as protons and light ions, remain insufficient, particularly in the clinically relevant energy ranges. This lack of experimental data introduces uncertainties in treatment planning softwares and Monte Carlo calculations, thus compromising the accuracy of dose delivery to the patients. This work consists in the characterization of secondary charged particles generated in hadron therapy using a $\Delta$E-E telescope comprising a CeBr$_3$ crystal scintillator and a plastic scintillator. The calibration and response of this telescope to ions commonly used in clinical settings is presented in this work, highlighting adherence to Birks law for accurate energy measurements. This study is the first to optimize a $\Delta$E-E telescope combining CeBr$_3$ and plastic scintillators specifically for secondary particle detection in hadrontherapy. This represents an important step in the exploitation of the system for nuclear data acquisition, as it enables both the measurement of energy and the discrimination of secondary particles. The objective is to develop a system compatible with clinical use, allowing for the most precise possible comparison with treatment planning software calculations.
Coordinating multiple agents to collaboratively maximize submodular functions in unpredictable environments is a critical task with numerous applications in machine learning, robot planning and control. The existing approaches, such as the OSG algorithm, are often hindered by their poor approximation guarantees and the rigid requirement for a fully connected communication graph. To address these challenges, we firstly present a $\textbf{MA-OSMA}$ algorithm, which employs the multi-linear extension to transfer the discrete submodular maximization problem into a continuous optimization, thereby allowing us to reduce the strict dependence on a complete graph through consensus techniques. Moreover, $\textbf{MA-OSMA}$ leverages a novel surrogate gradient to avoid sub-optimal stationary points. To eliminate the computationally intensive projection operations in $\textbf{MA-OSMA}$, we also introduce a projection-free $\textbf{MA-OSEA}$ algorithm, which effectively utilizes the KL divergence by mixing a uniform distribution. Theoretically, we confirm that both algorithms achieve a regret bound of $\widetilde{O}(\sqrt{\frac{C_{T}T}{1-\beta}})$ against a $(\frac{1-e^{-c}}{c})$-approximation to the best comparator in hindsight, where $C_{T}$ is the deviation of maximizer sequence, $\beta$ is the spectral gap of the network and $c$ is the joint curvature of submodular objectives. This result significantly improves the $(\frac{1}{1+c})$-approximation provided by the state-of-the-art OSG algorithm. Finally, we demonstrate the effectiveness of our proposed algorithms through simulation-based multi-target tracking.
Neutrino emission offers a direct probe into the hydrodynamics and energy transport processes within a supernova. Fast-time variations in the neutrino luminosity and mean energy can provide insights into phenomena like turbulence, convection, and shock revival. In this paper, we explore the detection capabilities of large-volume neutrino telescopes such as the IceCube Neutrino Observatory and the planned IceCube-Gen2 detector in identifying generic fast-time features in the neutrino light curve. We also investigate the potential enhancement in detection sensitivity using wavelength shifters, which can improve light collection efficiency. By employing a Short-Time Fourier Transform analysis, we quantify the excess power in the frequency spectrum arising from fast-time modulations and compute the detection horizon for a range of generic models. We find that with IceCube we can already see the strongest modulation models (>50% amplitude) for progenitors located anywhere in the Milky Way. Sensitivity to weaker modulations (>20% amplitude) is possible in future detectors like IceCube-Gen2, in particular with the use of wavelength shifters. For all detector configurations, the frequency and central time of the fast-time feature at the 5$\sigma$ detection horizon can be measured with a resolution of 7.0 Hz and 17 ms respectively.
Station-Keeping short-duration high-altitude balloons (HABs) in a region of interest is a challenging path-planning problem due to partially observable, complex, and dynamic wind flows. Deep reinforcement learning is a popular strategy for solving the station-keeping problem. A custom simulation environment was developed to train and evaluate Deep Q-Learning (DQN) for short-duration HAB agents in the simulation. To train the agents on realistic winds, synthetic wind forecasts were generated from aggregated historical radiosonde data to apply horizontal kinematics to simulated agents. The synthetic forecasts were closely correlated with ECWMF ERA5 Reanalysis forecasts, providing a realistic simulated wind field and seasonal and altitudinal variances between the wind models. DQN HAB agents were then trained and evaluated across different seasonal months. To highlight differences and trends in months with vastly different wind fields, a Forecast Score algorithm was introduced to independently classify forecasts based on wind diversity, and trends between station-keeping success and the Forecast Score were evaluated across all seasons.
We propose and study a planning problem we call Sequential Fault-Intolerant Process Planning (SFIPP). SFIPP captures a reward structure common in many sequential multi-stage decision problems where the planning is deemed successful only if all stages succeed. Such reward structures are different from classic additive reward structures and arise in important applications such as drug/material discovery, security, and quality-critical product design. We design provably tight online algorithms for settings in which we need to pick between different actions with unknown success chances at each stage. We do so both for the foundational case in which the behavior of actions is deterministic, and the case of probabilistic action outcomes, where we effectively balance exploration for learning and exploitation for planning through the usage of multi-armed bandit algorithms. In our empirical evaluations, we demonstrate that the specialized algorithms we develop, which leverage additional information about the structure of the SFIPP instance, outperform our more general algorithm.
Bent monolithic active pixel sensors are the basis for the planned fully cylindrical ultra low material budget tracking detector ITS3 of the ALICE experiment. This paper presents results from testbeam campaigns using high-energy particles to verify the performance of 50 um thick bent ALPIDE chips in terms of efficiency and spatial resolution. The sensors were bent to radii of 18, 24 and 30 mm, slightly smaller than the foreseen bending radii of the future ALICE ITS3 layers. An efficiency larger than $99.9\%$ and a spatial resolution of approximately 5 um, in line with the nominal operation of flat ALPIDE sensors, is obtained at nominal operating conditions. These values are found to be independent of the bending radius and thus constitute an additional milestone in the demonstration of the feasibility of the planned ITS3 detector. In addition, a special geometry in which the beam particles graze the chip and traverse it laterally over distances of up to 3 mm is investigated.
Sampling-based methods for motion planning, which capture the structure of the robot's free space via (typically random) sampling, have gained popularity due to their scalability, simplicity, and for offering global guarantees, such as probabilistic completeness and asymptotic optimality. Unfortunately, the practicality of those guarantees remains limited as they do not provide insights into the behavior of motion planners for a finite number of samples (i.e., a finite running time). In this work, we harness lattice theory and the concept of $(\delta,\epsilon)$-completeness by Tsao et al. (2020) to construct deterministic sample sets that endow their planners with strong finite-time guarantees while minimizing running time. In particular, we introduce a highly-efficient deterministic sampling approach based on the $A_d^*$ lattice, which is the best-known geometric covering in dimensions $\leq 21$. Using our new sampling approach, we obtain at least an order-of-magnitude speedup over existing deterministic and uniform random sampling methods for complex motion-planning problems. Overall, our work provides deep mathematical insights while advancing the practical applicability of sampling-based motion planning.
Nowadays robot is supposed to demonstrate human-like perception, reasoning and behavior pattern in social or service application. However, most of the existing motion planning methods are incompatible with above requirement. A potential reason is that the existing navigation algorithms usually intend to treat people as another kind of obstacle, and hardly take the social principle or awareness into consideration. In this paper, we attempt to model the proxemics of group and blend it into the scenario perception and navigation of robot. For this purpose, a group clustering method considering both social relevance and spatial confidence is introduced. It can enable robot to identify individuals and divide them into groups. Next, we propose defining the individual proxemics within magnetic dipole model, and further established the group proxemics and scenario map through vector-field superposition. On the basis of the group clustering and proxemics modeling, we present the method to obtain the optimal observation positions (OOPs) of group. Once the OOPs grid and scenario map are established, a heuristic path is employed to generate path that guide robot cruising among the groups for interactive purpose. A series of experiments are conducted to validate the proposed methodology on the practical robot, the results have demonstrated that our methodology has achieved promising performance on group recognition accuracy and path-generation efficiency. This concludes that the group awareness evolved as an important module to make robot socially behave in the practical scenario.
XuanLong-50 (EXL-50) is the first medium-size spherical torus (ST) in China, with the toroidal field at major radius at 50 cm around 0.5T. CS-free and non-inductive current drive via electron cyclotron resonance heating (ECRH) was the main physics research issue for EXL-50. Discharges with plasma currents of 50 kA - 180 kA were routinely obtained in EXL-50, with the current flattop sustained for up to or beyond 2 s. The current drive effectiveness on EXL-50 was as high as 1 A/W for low-density discharges using 28GHz ECRH alone for heating power less than 200 kW. The plasma current reached Ip>80 kA for high-density (5*10e18m-2) discharges with 150 kW 28GHz ECRH. Higher performance discharge (Ip of about 120 kA and core density of about 1*10e19m-3) was achieved with 150 kW 50GHz ECRH. The plasma current in EXL-50 was mainly carried by the energetic electrons.Multi-fluid equilibrium model has been successfully applied to reconstruct the magnetic flux surface and the measured plasma parameters of the EXL-50 equilibrium. The physics mechanisms for the solenoid-free ECRH current drive and the energetic electrons has also been investigated. Preliminary experimental results show that 100 kW of lower hybrid current drive (LHCD) waves can drive 20 kA of plasma current. Several boron injection systems were installed and tested in EXL-50, including B2H6 gas puffing, boron powder injection, boron pellet injection. The research plan of EXL-50U, which is the upgrade machine of EXL-50, is also presented.
In this work we have considered two minimal versions of scotogenic models, where neutrinos acquire masses through a radiative mechanism. We call these two models as Majorana and Dirac scotogenic models. In the former model, neutrinos have Majorana nature, and in the later one, neutrinos are Dirac particles. These two models are related to each other in terms of additional fields and symmetries of the model. Hence, to compare these two models in future experiments, we have analyzed lepton flavor violating (LFV) processes in both of them, in the charged lepton sector. We have found that the 3-body LFV decays in both these models can get different contributions. Among all the LFV decays and after satisfying relevant constraints, we have found that $\tau\to3\mu$ can have a branching ratio as high as $10^{-10}(10^{-11})$ in the Majorana(Dirac) scotogenic model. This branching ratio can be probed in the future planned experiments.
This work introduces an automated ply partitioning strategy for large-scale laminar composite manufacturing. It specifically targets the problem of fabricating large plies from available spooled materials, while minimizing the adverse effects on part quality. The proposed method inserts fiber-aligned seams sequentially until each resulting sub-ply can be manufactured from available materials, while simultaneously enforcing constraints to avoid quality issues induced by the stacking of seams across multiple plies. Leveraging the developable nature of individual plies, the partitioning problem is cast as a sequence of one-dimensional piecewise linear optimization problems, thus allowing for efficient local optimization via linear programming. We experimentally demonstrate that coupling the local search with a greedy global search produces the same results as an exhaustive search. The resulting automated method provides an efficient and robust alternative to the existing trial-and-error approach, and can be readily integrated into state-of-the-art composite design workflows. In addition, this formulation enables the inclusion of common constraints regarding laminate thickness tolerance, sub-ply geometry, stay-out zones, material wastage, etc. The efficacy of the proposed method is demonstrated through its application to the surface of an airplane wing and to the body panels of an armored vehicle, each subject to various performance and manufacturing-related geometric constraints.
We address the convergence problem in learning the Optimal Transport (OT) map, where the OT Map refers to a map from one distribution to another while minimizing the transport cost. Semi-dual Neural OT, a widely used approach for learning OT Maps with neural networks, often generates fake solutions that fail to transfer one distribution to another accurately. We identify a sufficient condition under which the max-min solution of Semi-dual Neural OT recovers the true OT Map. Moreover, to address cases when this sufficient condition is not satisfied, we propose a novel method, OTP, which learns both the OT Map and the Optimal Transport Plan, representing the optimal coupling between two distributions. Under sharp assumptions on the distributions, we prove that our model eliminates the fake solution issue and correctly solves the OT problem. Our experiments show that the OTP model recovers the optimal transport map where existing methods fail and outperforms current OT-based models in image-to-image translation tasks. Notably, the OTP model can learn stochastic transport maps when deterministic OT Maps do not exist, such as one-to-many tasks like colorization.
Radiotherapy treatment for prostate cancer relies on computed tomography (CT) and/or magnetic resonance imaging (MRI) for segmentation of target volumes and organs at risk (OARs). Manual segmentation of these volumes is regarded as the gold standard for ground truth in machine learning applications but to acquire such data is tedious and time-consuming. A publicly available clinical dataset is presented, comprising MRI- and synthetic CT (sCT) images, target and OARs segmentations, and radiotherapy dose distributions for 432 prostate cancer patients treated with MRI-guided radiotherapy. An extended dataset with 35 patients is also included, with the addition of deep learning (DL)-generated segmentations, DL segmentation uncertainty maps, and DL segmentations manually adjusted by four radiation oncologists. The publication of these resources aims to aid research within the fields of automated radiotherapy treatment planning, segmentation, inter-observer analyses, and DL model uncertainty investigation. The dataset is hosted on the AIDA Data Hub and offers a free-to-use resource for the scientific community, valuable for the advancement of medical imaging and prostate cancer radiotherapy research.
The wide adoption of platformized work has generated remarkable advancements in the labor patterns and mobility of modern society. Underpinning such progress, gig workers are exposed to unprecedented challenges and accountabilities: lack of data transparency, social and physical isolation, as well as insufficient infrastructural safeguards. Gig2Gether presents a space designed for workers to engage in an initial experience of voluntarily contributing anecdotal and statistical data to affect policy and build solidarity across platforms by exchanging unifying and diverse experiences. Our 7-day field study with 16 active workers from three distinct platforms and work domains showed existing affordances of data-sharing: facilitating mutual support across platforms, as well as enabling financial reflection and planning. Additionally, workers envisioned future use cases of data-sharing for collectivism (e.g., collaborative examinations of algorithmic speculations) and informing policy (e.g., around safety and pay), which motivated (latent) worker desiderata of additional capabilities and data metrics. Based on these findings, we discuss remaining challenges to address and how data-sharing tools can complement existing structures to maximize worker empowerment and policy impact.
Testing and debugging quantum software pose significant challenges due to the inherent complexities of quantum mechanics, such as superposition and entanglement. One challenge is indeterminacy, a fundamental characteristic of quantum systems, which increases the likelihood of flaky tests in quantum programs. To the best of our knowledge, there is a lack of comprehensive studies on quantum flakiness in the existing literature. In this paper, we present a novel machine learning platform that leverages multiple machine learning models to automatically detect flaky tests in quantum programs. Our evaluation shows that the extreme gradient boosting and decision tree-based models outperform other models (i.e., random forest, k-nearest neighbors, and support vector machine), achieving the highest F1 score and Matthews Correlation Coefficient in a balanced dataset and an imbalanced dataset, respectively. Furthermore, we expand the currently limited dataset for researchers interested in quantum flaky tests. In the future, we plan to explore the development of unsupervised learning techniques to detect and classify quantum flaky tests more effectively. These advancements aim to improve the reliability and robustness of quantum software testing.
This paper presents a novel approach to efficiently parameterize and estimate the state of a hanging tether for path and trajectory planning of a UGV tied to a UAV in a marsupial configuration. Most implementations in the state of the art assume a taut tether or make use of the catenary curve to model the shape of the hanging tether. The catenary model is complex to compute and must be instantiated thousands of times during the planning process, becoming a time-consuming task, while the taut tether assumption simplifies the problem, but might overly restrict the movement of the platforms. In order to accelerate the planning process, this paper proposes defining an analytical model to efficiently compute the hanging tether state, and a method to get a tether state parameterization free of collisions. We exploit the existing similarity between the catenary and parabola curves to derive analytical expressions of the tether state.
We investigate the implications of matter effects to searches for axion Dark Matter on Earth. The finite momentum of axion Dark Matter is crucial to elucidating the effects of Earth on both the axion Dark Matter field value and its gradient. We find that experiments targeting axion couplings compatible with canonical solutions of the strong CP puzzle are likely not affected by Earth's matter effects. However, experiments sensitive to lighter axions with stronger couplings can be significantly affected, with a significant part of the parameter space suffering from a reduced axion field value, and therefore decreased experimental sensitivity. In contrast, the spatial gradient of the axion field can be enhanced along Earth's radial direction, with important implications for ongoing and planned experiments searching for axion Dark Matter.
We compare multiple foreground-cleaning pipelines for estimating the tensor-to-scalar ratio, $r$, using simulated maps of the planned CMB-S4 experiment within the context of the South Pole Deep Patch. To evaluate robustness, we analyze bias and uncertainty on $r$ across various foreground suites using map-based simulations. The foreground-cleaning methods include: a parametric maximum likelihood approach applied to auto- and cross-power spectra between frequency maps; a map-based parametric maximum-likelihood method; and a harmonic-space internal linear combination using frequency maps. We summarize the conceptual basis of each method to highlight their similarities and differences. To better probe the impact of foreground residuals, we implement an iterative internal delensing step, leveraging a map-based pipeline to generate a lensing $B$-mode template from the Large Aperture Telescope frequency maps. Our results show that the performance of the three approaches is comparable for simple and intermediate-complexity foregrounds, with $\sigma(r)$ ranging from 3 to 5 $\times 10^{-4}$. However, biases at the $1-2\sigma$ level appear when analyzing more complex forms of foreground emission. By extending the baseline pipelines to marginalize over foreground residuals, we demonstrate that contamination can be reduced to within statistical uncertainties, albeit with a pipeline-dependent impact on $\sigma(r)$, which translates to a detection significance between 2 and 4$\sigma$ for an input value of $r = 0.003$. These findings suggest varying levels of maturity among the tested pipelines, with the auto- and cross-spectra-based approach demonstrating the best stability and overall performance. Moreover, given the extremely low noise levels, mutual validation of independent foreground-cleaning pipelines is essential to ensure the robustness of any potential detection.
This paper presents a method that allows users to design cinematic video shots in the context of image-to-video generation. Shot design, a critical aspect of filmmaking, involves meticulously planning both camera movements and object motions in a scene. However, enabling intuitive shot design in modern image-to-video generation systems presents two main challenges: first, effectively capturing user intentions on the motion design, where both camera movements and scene-space object motions must be specified jointly; and second, representing motion information that can be effectively utilized by a video diffusion model to synthesize the image animations. To address these challenges, we introduce MotionCanvas, a method that integrates user-driven controls into image-to-video (I2V) generation models, allowing users to control both object and camera motions in a scene-aware manner. By connecting insights from classical computer graphics and contemporary video generation techniques, we demonstrate the ability to achieve 3D-aware motion control in I2V synthesis without requiring costly 3D-related training data. MotionCanvas enables users to intuitively depict scene-space motion intentions, and translates them into spatiotemporal motion-conditioning signals for video diffusion models. We demonstrate the effectiveness of our method on a wide range of real-world image content and shot-design scenarios, highlighting its potential to enhance the creative workflows in digital content creation and adapt to various image and video editing applications.
Retrosynthesis strategically plans the synthesis of a chemical target compound from simpler, readily available precursor compounds. This process is critical for synthesizing novel inorganic materials, yet traditional methods in inorganic chemistry continue to rely on trial-and-error experimentation. Emerging machine-learning approaches struggle to generalize to entirely new reactions due to their reliance on known precursors, as they frame retrosynthesis as a multi-label classification task. To address these limitations, we propose Retro-Rank-In, a novel framework that reformulates the retrosynthesis problem by embedding target and precursor materials into a shared latent space and learning a pairwise ranker on a bipartite graph of inorganic compounds. We evaluate Retro-Rank-In's generalizability on challenging retrosynthesis dataset splits designed to mitigate data duplicates and overlaps. For instance, for Cr2AlB2, it correctly predicts the verified precursor pair CrB + Al despite never seeing them in training, a capability absent in prior work. Extensive experiments show that Retro-Rank-In sets a new state-of-the-art, particularly in out-of-distribution generalization and candidate set ranking, offering a powerful tool for accelerating inorganic material synthesis.
Managing the security of employee work computers has become increasingly important as today's work model shifts to remote and hybrid work plans. In this paper, we explore the recent 2022 LastPass data breach, in which the attacker obtained sensitive customer data by exploiting a software vulnerability on a DevSecOps engineer's computer. We discuss the methodology of the attacker as well as the impact this incident had on LastPass and its customers. Next, we expand upon the impact the breach had on LastPass as well as its customers. From this, we propose solutions for preparing for and mitigating similar attacks in the future. The aim of this paper is to shed light on the LastPass incident and provide methods for companies to secure their employee base, both nationally and internationally. With a strong security structure, companies can vastly reduce the chances of falling victim to a similar attack.
Referral workflow inefficiencies, including misaligned referrals and delays, contribute to suboptimal patient outcomes and higher healthcare costs. In this study, we investigated the possibility of predicting procedural needs based on primary care diagnostic entries, thereby improving referral accuracy, streamlining workflows, and providing better care to patients. A de-identified dataset of 2,086 orthopedic referrals from the University of Texas Health at Tyler was analyzed using machine learning models built on Base General Embeddings (BGE) for semantic extraction. To ensure real-world applicability, noise tolerance experiments were conducted, and oversampling techniques were employed to mitigate class imbalance. The selected optimum and parsimonious embedding model demonstrated high predictive accuracy (ROC-AUC: 0.874, Matthews Correlation Coefficient (MCC): 0.540), effectively distinguishing patients requiring surgical intervention. Dimensionality reduction techniques confirmed the model's ability to capture meaningful clinical relationships. A threshold sensitivity analysis identified an optimal decision threshold (0.30) to balance precision and recall, maximizing referral efficiency. In the predictive modeling analysis, the procedure rate increased from 11.27% to an optimal 60.1%, representing a 433% improvement with significant implications for operational efficiency and healthcare revenue. The results of our study demonstrate that referral optimization can enhance primary and surgical care integration. Through this approach, precise and timely predictions of procedural requirements can be made, thereby minimizing delays, improving surgical planning, and reducing administrative burdens. In addition, the findings highlight the potential of clinical decision support as a scalable solution for improving patient outcomes and the efficiency of the healthcare system.
In this paper, we present an approach for controlling a team of agile fixed-wing aerial vehicles in close proximity to one another. Our approach relies on receding-horizon nonlinear model predictive control (NMPC) to plan maneuvers across an expanded flight envelope to enable inter-agent collision avoidance. To facilitate robust collision avoidance and characterize the likelihood of inter-agent collisions, we compute a statistical bound on the probability of the system leaving a tube around the planned nominal trajectory. Finally, we propose a metric for evaluating highly dynamic swarms and use this metric to evaluate our approach. We successfully demonstrated our approach through both simulation and hardware experiments, and to our knowledge, this the first time close-quarters swarming has been achieved with physical aerobatic fixed-wing vehicles.
Motion planning is a central challenge in robotics, with learning-based approaches gaining significant attention in recent years. Our work focuses on a specific aspect of these approaches: using machine-learning techniques, particularly Support Vector Machines (SVM), to evaluate whether robot configurations are collision free, an operation termed ``collision detection''. Despite the growing popularity of these methods, there is a lack of theory supporting their efficiency and prediction accuracy. This is in stark contrast to the rich theoretical results of machine-learning methods in general and of SVMs in particular. Our work bridges this gap by analyzing the sample complexity of an SVM classifier for learning-based collision detection in motion planning. We bound the number of samples needed to achieve a specified accuracy at a given confidence level. This result is stated in terms relevant to robot motion-planning such as the system's clearance. Building on these theoretical results, we propose a collision-detection algorithm that can also provide statistical guarantees on the algorithm's error in classifying robot configurations as collision-free or not.
The evolution of existing transportation systems, mainly driven by urbanization and increased availability of mobility options, such as private, profit-maximizing ride-hailing companies, calls for tools to reason about their design and regulation. To study this complex socio-technical problem, one needs to account for the strategic interactions of the stakeholders involved in the mobility ecosystem. In this paper, we present a game-theoretic framework to model multi-modal mobility systems, focusing on municipalities, service providers, and travelers. Through a user-friendly, Graphical User Interface, one can visualize system dynamics and compute equilibria for various scenarios. The framework enables stakeholders to assess the impact of local decisions (e.g., fleet size for services or taxes for private companies) on the full mobility system. Furthermore, this project aims to foster STEM interest among high school students (e.g., in the context of prior activities in Switzerland, and planned activities with the MIT museum). This initiative combines theoretical advancements, practical applications, and educational outreach to improve mobility system design.
Following in the footsteps of the LHC, the Future Circular Collider (FCC) plans to be the next multi-generational collider project. In the first stage, FCC-ee will collide intense beams of electrons and positrons at centre of mass energies between 88 and 365 GeV, making it an electroweak, flavour, Higgs and top factory. The unprecedented statistical precision requires FCC-ee experiments to limit their systematic uncertainties to the very minimum. The precise reconstruction of the interaction vertices is central to most measurements at FCC-ee, such as rare flavour physics processes and the measurement of Higgs and Z decays to bottom and charm quarks and taus. This contribution will discuss the requirements of FCC-ee vertex detectors, from the necessary impact parameter resolution via the challenging collision environment at the Z pole to the tight requirement on the material budget, which should be kept below 0.3% of a radiation length per detection layer. Next, the proposed vertex detector designs for FCC-ee are shortly presented, and an outlook is given on novel detector designs and features. The requirements for the vertexing performance translate into requirements for the sensors used for the vertex detector. As discussed in this contribution, they need to feature a spatial resolution of about 3 $\mu$m and provide timing information of O($\mu$s-ns) while keeping power consumption minimal to allow for air-cooling of the detector - minimising the detector material budget. The only type of sensor capable of aiming to fulfil such requirements are CMOS Monolithic Active Pixel Sensors (MAPS), which combine signal generation, amplification and readout into a single silicon die. Therefore, the rest of this contribution will present an overview of existing and planned MAPS technologies and prototypes aiming to fulfil the stringent FCC-ee vertex detector requirements.
Boson Stars (BSs) are macroscopic self-gravitating configurations made of complex scalar fields. These exotic compact objects (ECO) would manifest as dark Boson stars and can contribute to a certain fraction of the dark matter (DM) in the universe. In this work, we study the fundamental non-radial oscillations ($f$-modes) of massive BSs and the associated gravitational wave (GW) emission. We consider massive scalar BSs having the potential of the form $V(\phi) = \frac{1}{2}m^2|\phi|^2 + \frac{1}{4}\lambda |\phi|^4$, restricting to the strong-coupling regime ($\lambda \gg m^2/M_{Pl}^2$) where solutions resembling fermionic stars are known to exist. We first review the available parameter space for scalar DM that can form massive BSs and enlist various constraints. We fit and provide simple analytical relations connecting various macroscopic observables for BSs, which can be directly incorporated into future studies of massive BSs throughout the strong coupling regime without requiring any numerical computation. We then solve for the non-radial $l=2$ fundamental quasinormal modes ($f$-modes) for massive BSs. Scaling relations for $f$-mode equations have been reported in another work. Using these, we perform a complete study of these oscillations spanning the entire available parameter space of massive BSs and provide analytical fits for the $f$-mode characteristics. We further study the universal relations for BSs and reveal the parameter space that is sensitive to the current and future planned GW detectors. We find that different parts of the parameters space can, in principle, be probed by the LISA, LIGO, and NEMO detectors. Finally, we briefly discuss the detectability of $f$-modes from BSs that have not been explored before.
Accurate differentiation of pseudoprogression (PsP) from True Progression (TP) following radiotherapy (RT) in glioblastoma (GBM) patients is crucial for optimal treatment planning. However, this task remains challenging due to the overlapping imaging characteristics of PsP and TP. This study therefore proposes a multimodal deep-learning approach utilizing complementary information from routine anatomical MR images, clinical parameters, and RT treatment planning information for improved predictive accuracy. The approach utilizes a self-supervised Vision Transformer (ViT) to encode multi-sequence MR brain volumes to effectively capture both global and local context from the high dimensional input. The encoder is trained in a self-supervised upstream task on unlabeled glioma MRI datasets from the open BraTS2021, UPenn-GBM, and UCSF-PDGM datasets to generate compact, clinically relevant representations from FLAIR and T1 post-contrast sequences. These encoded MR inputs are then integrated with clinical data and RT treatment planning information through guided cross-modal attention, improving progression classification accuracy. This work was developed using two datasets from different centers: the Burdenko Glioblastoma Progression Dataset (n = 59) for training and validation, and the GlioCMV progression dataset from the University Hospital Erlangen (UKER) (n = 20) for testing. The proposed method achieved an AUC of 75.3%, outperforming the current state-of-the-art data-driven approaches. Importantly, the proposed approach relies on readily available anatomical MRI sequences, clinical data, and RT treatment planning information, enhancing its clinical feasibility. The proposed approach addresses the challenge of limited data availability for PsP and TP differentiation and could allow for improved clinical decision-making and optimized treatment plans for GBM patients.
This paper presents for the first time a mathematical model for evaluating the Planned Kurdistan Regional Power System (KRPS) for its ability to maintain stability under small disturbances and fluctuations during normal operating conditions. To achieve this objective, practical field data, manufacture's datasheets, related IEEE task force reports have been used to build a complete mathematical model in MATLAB/SIMULINK/SimPowerSystem environment. New modules have been established and added to the platform wherever it does not support special type of elements. The model represents accurately all the power system components involved in physical phenomena of system dynamic oscillations. The model consists of 53 transmission lines, 35 nodes and 6 generating stations. The system is simulated under different configurations and settings; the dynamic behaviors associated with each configuration are recorded and analyzed accordingly.
In this work, we present BiM-ACPPO, a bilevel multi-armed bandit-based hierarchical reinforcement learning framework for interaction-aware decision-making and planning at unsignalized intersections. Essentially, it proactively takes the uncertainties associated with surrounding vehicles (SVs) into consideration, which encompass those stemming from the driver's intention, interactive behaviors, and the varying number of SVs. Intermediate decision variables are introduced to enable the high-level RL policy to provide an interaction-aware reference, for guiding low-level model predictive control (MPC) and further enhancing the generalization ability of the proposed framework. By leveraging the structured nature of self-driving at unsignalized intersections, the training problem of the RL policy is modeled as a bilevel curriculum learning task, which is addressed by the proposed Exp3.S-based BiMAB algorithm. It is noteworthy that the training curricula are dynamically adjusted, thereby facilitating the sample efficiency of the RL training process. Comparative experiments are conducted in the high-fidelity CARLA simulator, and the results indicate that our approach achieves superior performance compared to all baseline methods. Furthermore, experimental results in two new urban driving scenarios clearly demonstrate the commendable generalization performance of the proposed method.
Radiotherapy is a crucial cancer treatment that demands precise planning to balance tumor eradication and preservation of healthy tissue. Traditional treatment planning (TP) is iterative, time-consuming, and reliant on human expertise, which can potentially introduce variability and inefficiency. We propose a novel framework to transform a large multimodal foundation model (MLM) into an action model for TP using a few-shot reinforcement learning (RL) approach. Our method leverages the MLM's extensive pre-existing knowledge of physics, radiation, and anatomy, enhancing it through a few-shot learning process. This allows the model to iteratively improve treatment plans using a Monte Carlo simulator. Our results demonstrate that this method outperforms conventional RL-based approaches in both quality and efficiency, achieving higher reward scores and more optimal dose distributions in simulations on prostate cancer data. This proof-of-concept suggests a promising direction for integrating advanced AI models into clinical workflows, potentially enhancing the speed, quality, and standardization of radiotherapy treatment planning.
This paper presents a framework to define a task with freedom and variability in its goal state. A robot could use this to observe the execution of a task and target a different goal from the observed one; a goal that is still compatible with the task description but would be easier for the robot to execute. We define the model of an environment state and an environment variation, and present experiments on how to interactively create the variation from a single task demonstration and how to use this variation to create an execution plan for bringing any environment into the goal state.
Space layout design (SLD), occurring in the early stages of the design process, nonetheless influences both the functionality and aesthetics of the ultimate architectural outcome. The complexity of SLD necessitates innovative approaches to efficiently explore vast solution spaces. While image-based generative AI has emerged as a potential solution, they often rely on pixel-based space composition methods that lack intuitive representation of architectural processes. This paper leverages deep Reinforcement Learning (RL), as it offers a procedural approach that intuitively mimics the process of human designers. Effectively using RL for SLD requires an explorative space composing method to generate desirable design solutions. We introduce "laser-wall", a novel space partitioning method that conceptualizes walls as emitters of imaginary light beams to partition spaces. This approach bridges vector-based and pixel-based partitioning methods, offering both flexibility and exploratory power in generating diverse layouts. We present two planning strategies: one-shot planning, which generates entire layouts in a single pass, and dynamic planning, which allows for adaptive refinement by continuously transforming laser-walls. Additionally, we introduce on-light and off-light wall transformations for smooth and fast layout refinement, as well as identity-less and identity-full walls for versatile room assignment. We developed SpaceLayoutGym, an open-source OpenAI Gym compatible simulator for generating and evaluating space layouts. The RL agent processes the input design scenarios and generates solutions following a reward function that balances geometrical and topological requirements. Our results demonstrate that the RL-based laser-wall approach can generate diverse and functional space layouts that satisfy both geometric constraints and topological requirements and is architecturally intuitive.
Although "climate litigation" is not an indigenous term in China, localizing it is essential to support the development of an independent environmental legal knowledge system in China. Rooted in China's judicial tradition, which emphasizes substantive rationality, traditional legal theories have primarily focused on environmental law. However, the contemporary practices in the rule of law have created an unclear trajectory for climate litigation. Research in this area has long been trapped in a paradigm that relies on lawsuits for ecological environmental damage compensation and environmental public interest litigation, leading to a significant disconnect between theoretical frameworks and practical application. With the advancement of the "dual carbon" strategic goals-carbon peaking and carbon neutrality-it has become imperative to redefine the concept of climate litigation within the Chinese context. We need to establish a theoretical framework that aligns with the "dual carbon" objectives while providing theoretical and institutional support for climate litigation, ultimately contributing to the international discourse on climate justice. Additionally, Hong Kong's proactive climate governance and robust ESG (Environmental, Social, and Governance) practices provide valuable insights for developing comprehensive climate litigation mechanisms. Based on this analysis, we propose concrete plans for building a climate litigation system in China, establishing a preventive relief system and a multi-source legal framework at the substantive level and developing climate judicial mechanisms for mitigation and adaptation at the procedural level.
Caribou is a versatile data acquisition system used in multiple collaborative frameworks (CERN EP R&D, DRD3, AIDAinnova, Tangerine) for laboratory and test-beam qualification of novel silicon pixel detector prototypes. The system is built around a common hardware, firmware and software stack shared accross different projects, thereby drastically reducing the development effort and cost. It consists of a custom Control and Readout (CaR) board and a commercial Xilinx Zynq System-on-Chip (SoC) platform. The SoC platform runs a full Yocto distribution integrating the custom software framework (Peary) and a custom FPGA firmware built within a common firmware infrastructure (Boreal). The CaR board provides a hardware environment featuring various services such as powering, slow-control, and high-speed data links for the target detector prototype. Boreal and Peary, in turn, offer firmware and software architectures that enable seamless integration of control and readout for new devices. While the first version of the system used a SoC platform based on the ZC706 evaluation board, migration to a Zynq UltraScale+ architecture is progressing towards the support of the ZCU102 board and the ultimate objective of integrating the SoC functionality directly into the CaR board, eliminating the need for separate evaluation boards. This paper describes the Caribou system, focusing on the latest project developments and showcasing progress and future plans across its hardware, firmware, and software components.
We introduce a computational framework, Bayesian Evidence calculation fOr Model Selection (BEOMS) to evaluate multiple Bayesian model selection methods in the context of determining the equation of state (EOS) for cold neutron star (NS), focusing on their performance with current and next-generation gravitational wave (GW) observatories. We conduct a systematic comparison of various EOS models by using posterior distributions obtained from EOS-agnostic Bayesian inference of binary parameters applied to GWs from a population of binary neutron star (BNS) mergers. The cumulative evidence for each model is calculated in a multi-dimensional parameter space characterized by neutron star masses and tidal deformabilities. Our findings indicate that Bayesian model selection is most effective when performed in the two-dimensional subspace of component mass and tidal deformability, requiring fewer events to distinguish between EOS models with high confidence. Furthermore, we establish a relationship between the precision of tidal deformability measurements and the accuracy of model selection, taking into account the evolving sensitivities of current and planned GW observatories. BEOMS offers computational efficiency and can be adapted to execute model selection for gravitational wave data from other sources.
Advances in artificial intelligence (AI) including foundation models (FMs), are increasingly transforming human society, with smart city driving the evolution of urban living.Meanwhile, vehicle crowdsensing (VCS) has emerged as a key enabler, leveraging vehicles' mobility and sensor-equipped capabilities. In particular, ride-hailing vehicles can effectively facilitate flexible data collection and contribute towards urban intelligence, despite resource limitations. Therefore, this work explores a promising scenario, where edge-assisted vehicles perform joint tasks of order serving and the emerging foundation model fine-tuning using various urban data. However, integrating the VCS AI task with the conventional order serving task is challenging, due to their inconsistent spatio-temporal characteristics: (i) The distributions of ride orders and data point-of-interests (PoIs) may not coincide in geography, both following a priori unknown patterns; (ii) they have distinct forms of temporal effects, i.e., prolonged waiting makes orders become instantly invalid while data with increased staleness gradually reduces its utility for model fine-tuning.To overcome these obstacles, we propose an online framework based on multi-agent reinforcement learning (MARL) with careful augmentation. A new quality-of-service (QoS) metric is designed to characterize and balance the utility of the two joint tasks, under the effects of varying data volumes and staleness. We also integrate graph neural networks (GNNs) with MARL to enhance state representations, capturing graph-structured, time-varying dependencies among vehicles and across locations. Extensive experiments on our testbed simulator, utilizing various real-world foundation model fine-tuning tasks and the New York City Taxi ride order dataset, demonstrate the advantage of our proposed method.
The widespread application of autonomous driving technology has significantly advanced the field of autonomous racing. Model Predictive Contouring Control (MPCC) is a highly effective local trajectory planning method for autonomous racing. However, the traditional MPCC method struggles with racetracks that have significant curvature changes, limiting the performance of the vehicle during autonomous racing. To address this issue, we propose a curvature-integrated MPCC (CiMPCC) local trajectory planning method for autonomous racing. This method optimizes the velocity of the local trajectory based on the curvature of the racetrack centerline. The specific implementation involves mapping the curvature of the racetrack centerline to a reference velocity profile, which is then incorporated into the cost function for optimizing the velocity of the local trajectory. This reference velocity profile is created by normalizing and mapping the curvature of the racetrack centerline, thereby ensuring efficient and performance-oriented local trajectory planning in racetracks with significant curvature. The proposed CiMPCC method has been experimented on a self-built 1:10 scale F1TENTH racing vehicle deployed with ROS platform. The experimental results demonstrate that the proposed method achieves outstanding results on a challenging racetrack with sharp curvature, improving the overall lap time by 11.4%-12.5% compared to other autonomous racing trajectory planning methods. Our code is available at https://github.com/zhouhengli/CiMPCC.
End-effector trajectory tracking algorithms find joint motions that drive robot manipulators to track reference trajectories. In practical scenarios, anytime algorithms are preferred for their ability to quickly generate initial motions and continuously refine them over time. In this paper, we present an algorithmic framework that adapts common graph-based trajectory tracking algorithms to be anytime and enhances their efficiency and effectiveness. Our key insight is to identify guide paths that approximately track the reference trajectory and strategically bias sampling toward the guide paths. We demonstrate the effectiveness of the proposed framework by restructuring two existing graph-based trajectory tracking algorithms and evaluating the updated algorithms in three experiments.
Recent advances in diffusion models hold significant potential in robotics, enabling the generation of diverse and smooth trajectories directly from raw representations of the environment. Despite this promise, applying diffusion models to motion planning remains challenging due to their difficulty in enforcing critical constraints, such as collision avoidance and kinematic feasibility. These limitations become even more pronounced in Multi-Robot Motion Planning (MRMP), where multiple robots must coordinate in shared spaces. To address this challenge, this work proposes Simultaneous MRMP Diffusion (SMD), a novel approach integrating constrained optimization into the diffusion sampling process to produce collision-free, kinematically feasible trajectories. Additionally, the paper introduces a comprehensive MRMP benchmark to evaluate trajectory planning algorithms across scenarios with varying robot densities, obstacle complexities, and motion constraints. Experimental results show SMD consistently outperforms classical and learning-based motion planners, achieving higher success rates and efficiency in complex multi-robot environments.
Model-based reinforcement learning algorithms that combine model-based planning and learned value/policy prior have gained significant recognition for their high data efficiency and superior performance in continuous control. However, we discover that existing methods that rely on standard SAC-style policy iteration for value learning, directly using data generated by the planner, often result in \emph{persistent value overestimation}. Through theoretical analysis and experiments, we argue that this issue is deeply rooted in the structural policy mismatch between the data generation policy that is always bootstrapped by the planner and the learned policy prior. To mitigate such a mismatch in a minimalist way, we propose a policy regularization term reducing out-of-distribution (OOD) queries, thereby improving value learning. Our method involves minimum changes on top of existing frameworks and requires no additional computation. Extensive experiments demonstrate that the proposed approach improves performance over baselines such as TD-MPC2 by large margins, particularly in 61-DoF humanoid tasks. View qualitative results at https://darthutopian.github.io/tdmpc_square/.
Strongly lensed binary neutron star (NS-NS) mergers are expected to be observed once LIGO/Virgo/Kagra reaches the planned A+ or proposed A\# sensitivity. We demonstrate that the relative transverse velocity of the source-lens system can be constrained by comparing the phase of the two associated gravitational wave (GW) images, using both semi-analytical and numerical Bayesian methods. For A+ sensitivity, a one-sigma NS-NS merger signal in magnification $(\mu=200)$ and redshift $(z_{\rm S}=1)$ will carry a marginally detectable dephasing signature for a source transverse velocity of $\sim 1800$ km/s. This is comparable to the velocity dispersion of large galaxy clusters. Assuming the same population distribution, the most likely source parameters of $\mu=100$ and $z_{\rm S}=1.4$ are always expected to showcase detectable dephasing imprints for A\# sensitivity, provided they are moving with transverse velocities larger than $\sim 2000$ km/s. We conclude that a first measurement of the relative transverse velocity of a source via GW dephasing methods is likely only a few years away.
In this paper, we explore how token unmasking order influences generative quality in masked diffusion models (MDMs). We derive an expanded evidence lower bound (ELBO) that introduces a planner to select which tokens to unmask at each step. Our analysis reveals that alternative unmasking strategies can enhance generation performance. Building on this, we propose Path Planning (P2), a sampling framework that uses a pre-trained BERT model or the denoiser itself to guide unmasking decisions. P2 generalizes all known MDM sampling strategies and significantly improves performance across diverse domains, including language generation (in-context learning, code generation, story infilling, mathematical reasoning, reverse curse correction) and biological sequence generation (protein and RNA sequences).
Online planning and execution of minimum-time maneuvers on three-dimensional (3D) circuits is an open challenge in autonomous vehicle racing. In this paper, we present an artificial race driver (ARD) to learn the vehicle dynamics, plan and execute minimum-time maneuvers on a 3D track. ARD integrates a novel kineto-dynamical (KD) vehicle model for trajectory planning with economic nonlinear model predictive control (E-NMPC). We use a high-fidelity vehicle simulator (VS) to compare the closed-loop ARD results with a minimum-lap-time optimal control problem (MLT-VS), solved offline with the same VS. Our ARD sets lap times close to the MLT-VS, and the new KD model outperforms a literature benchmark. Finally, we study the vehicle trajectories, to assess the re-planning capabilities of ARD under execution errors. A video with the main results is available as supplementary material.
The rapid rise in electric vehicle (EV) adoption presents significant challenges in managing the vast number of retired EV batteries. Research indicates that second-life batteries (SLBs) from EVs typically retain considerable residual capacity, offering extended utility. These batteries can be effectively repurposed for use in EV charging stations (EVCS), providing a cost-effective alternative to new batteries and reducing overall planning costs. Integrating battery energy storage systems (BESS) with SLBs into EVCS is a promising strategy to alleviate system overload. However, efficient operation of EVCS with integrated BESS is hindered by uncertainties such as fluctuating EV arrival and departure times and variable power prices from the grid. This paper presents a deep reinforcement learning-based (DRL) planning framework for EV charging stations with BESS, leveraging SLBs. We employ the advanced soft actor-critic (SAC) approach, training the model on a year's worth of data to account for seasonal variations, including weekdays and holidays. A tailored reward function enables effective offline training, allowing real-time optimization of EVCS operations under uncertainty.
Volumetric Modulated Arc Therapy (VMAT) revolutionizes cancer treatment by precisely delivering radiation while sparing healthy tissues. Fluence maps generation, crucial in VMAT planning, traditionally involves complex and iterative, and thus time consuming processes. These fluence maps are subsequently leveraged for leaf-sequence. The deep-learning approach presented in this article aims to expedite this by directly predicting fluence maps from patient data. We developed a 3D network which we trained in a supervised way using a combination of L1 and L2 losses, and RT plans generated by Eclipse and from the REQUITE dataset, taking the RT dose map as input and the fluence maps computed from the corresponding RT plans as target. Our network predicts jointly the 180 fluence maps corresponding to the 180 control points (CP) of single arc VMAT plans. In order to help the network, we pre-process the input dose by computing the projections of the 3D dose map to the beam's eye view (BEV) of the 180 CPs, in the same coordinate system as the fluence maps. We generated over 2000 VMAT plans using Eclipse to scale up the dataset size. Additionally, we evaluated various network architectures and analyzed the impact of increasing the dataset size. We are measuring the performance in the 2D fluence maps domain using image metrics (PSNR, SSIM), as well as in the 3D dose domain using the dose-volume histogram (DVH) on a validation dataset. The network inference, which does not include the data loading and processing, is less than 20ms. Using our proposed 3D network architecture as well as increasing the dataset size using Eclipse improved the fluence map reconstruction performance by approximately 8 dB in PSNR compared to a U-Net architecture trained on the original REQUITE dataset. The resulting DVHs are very close to the one of the input target dose.
Computational models of atrial electrophysiology (EP) are increasingly utilized for applications such as the development of advanced mapping systems, personalized clinical therapy planning, and the generation of virtual cohorts and digital twins. These models have the potential to establish robust causal links between simulated in silico behaviors and observed human atrial EP, enabling safer, cost-effective, and comprehensive exploration of atrial dynamics. However, current state-of-the-art approaches lack the fidelity and scalability required for regulatory-grade applications, particularly in creating high-quality virtual cohorts or patient-specific digital twins. Challenges include anatomically accurate model generation, calibration to sparse and uncertain clinical data, and computational efficiency within a streamlined workflow. This study addresses these limitations by introducing novel methodologies integrated into an automated end-to-end workflow for generating high-fidelity digital twin snapshots and virtual cohorts of atrial EP. These innovations include: (i) automated multi-scale generation of volumetric biatrial models with detailed anatomical structures and fiber architecture; (ii) a robust method for defining space-varying atrial parameter fields; (iii) a parametric approach for modeling inter-atrial conduction pathways; and (iv) an efficient forward EP model for high-fidelity electrocardiogram computation. We evaluated this workflow on a cohort of 50 atrial fibrillation patients, producing high-quality meshes suitable for reaction-eikonal and reaction-diffusion models and demonstrating the ability to simulate atrial ECGs under parametrically controlled conditions. These advancements represent a critical step toward scalable, precise, and clinically applicable digital twin models and virtual cohorts, enabling enhanced patient-specific predictions and therapeutic planning.
Most existing methods for motion planning of mobile robots involve generating collision-free trajectories. However, these methods focusing solely on contact avoidance may limit the robots' locomotion and can not be applied to tasks where contact is inevitable or intentional. To address these issues, we propose a novel contact-aware motion planning (CAMP) paradigm for robotic systems. Our approach incorporates contact between robots and movable objects as complementarity constraints in optimization-based trajectory planning. By leveraging augmented Lagrangian methods (ALMs), we efficiently solve the optimization problem with complementarity constraints, producing spatial-temporal optimal trajectories of the robots. Simulations demonstrate that, compared to the state-of-the-art method, our proposed CAMP method expands the reachable space of mobile robots, resulting in a significant improvement in the success rate of two types of fundamental tasks: navigation among movable objects (NAMO) and rearrangement of movable objects (RAMO). Real-world experiments show that the trajectories generated by our proposed method are feasible and quickly deployed in different tasks.
Designing a reliable target is already a challenge for MW-class facilities today and has led several major accelerator facilities to operate at lower than design power due to target concerns. With present plans to increase beam power for next generation accelerator facilities in the next decade, timely R and D in support of robust high power targets is critical to secure the full physics benefits of ambitious accelerator power upgrades. A comprehensive R and D program must be implemented to address the many complex challenges faced by multi MW beam intercepting devices. This roadmap is envisioned to be helpful to the DOE-OHEP office when planning and prioritizing future R and D activities as well as leveraging synergies across the Office of Science. The roadmap will be extremely beneficial to the broader (external to DOE HEP) HPT community by communicating OHEP s high level strategy and objectives for HPT R and D and highlighting possible opportunities for collaboration.
Modular automated driving systems commonly handle prediction and planning as sequential, separate tasks, thereby prohibiting cooperative maneuvers. To enable cooperative planning, this work introduces a prediction model that models the conditional dependencies between trajectories. For this, predictions are generated by a microscopic traffic simulation, with the individual traffic participants being controlled by a realistic behavior model trained via Adversarial Inverse Reinforcement Learning. By assuming various candidate trajectories for the automated vehicle, we generate predictions conditioned on each of them. Furthermore, our approach allows the candidate trajectories to adapt dynamically during the prediction rollout. Several example scenarios are available at https://conditionalpredictionbysimulation.github.io/.
The application of artificial intelligence (AI) has brought key shifts in conventional tactical software development, including code generation, testing and debugging, and deployment. Waterfall and Agile development approaches, which have been used for a long time, also widely employ manual and well-planned steps. However, with the help of automated tools and models such as OpenAI Codex and GPT-4, many aspects of the Software Development Life Cycle (SDLC) have been made possible. This paper examines the technical aspect of integrating AI into prior traditional software development life cycle methodologies, emphasizing code automation, intelligent testing frameworks, AI-based debugging, and continuous integration and deployment pipelines. The analysis is also based on the advantages of utilizing AI for optimizations in efficiency, accuracy, and development speed alongside issues like over-dependence on AI, ethical questions, and technical constraints. Based on the case and example given in this paper, it is clearly shown that the self-improvement of AI in software development makes the process more dynamic, autonomous, and optimized.
Vision-Language Models (VLMs) are known to struggle with spatial reasoning and visual alignment. To help overcome these limitations, we introduce iVISPAR, an interactive multi-modal benchmark designed to evaluate the spatial reasoning capabilities of VLMs acting as agents. iVISPAR is based on a variant of the sliding tile puzzle-a classic problem that demands logical planning, spatial awareness, and multi-step reasoning. The benchmark supports visual 2D, 3D, and text-based input modalities, enabling comprehensive assessments of VLMs' planning and reasoning skills. We evaluate a broad suite of state-of-the-art open-source and closed-source VLMs, comparing their performance while also providing optimal path solutions and a human baseline to assess the task's complexity and feasibility for humans. Results indicate that while some VLMs perform well on simple spatial tasks, they encounter difficulties with more complex configurations and problem properties. Notably, while VLMs generally perform better in 2D vision compared to 3D or text-based representations, they consistently fall short of human performance, illustrating the persistent challenge of visual alignment. This highlights critical gaps in current VLM capabilities, highlighting their limitations in achieving human-level cognition.
In Group Trip Planning (GTP) Query Problem, we are given a city road network where a number of Points of Interest (PoI) have been marked with their respective categories (e.g., Cafeteria, Park, Movie Theater, etc.). A group of agents want to visit one PoI from every category from their respective starting location and once finished, they want to reach their respective destinations. This problem asks which PoI from every category should be chosen so that the aggregated travel cost of the group is minimized. This problem has been studied extensively in the last decade, and several solution approaches have been proposed. However, to the best of our knowledge, none of the existing studies have considered the different modalities of the journey, which makes the problem more practical. To bridge this gap, we introduce and study the GTP Query Problem with Multimodal Journey in this paper. Along with the other inputs of the GTP Query Problem, we are also given the different modalities of the journey that are available and their respective cost. Now, the problem is not only to select the PoIs from respective categories but also to select the modality of the journey. For this problem, we have proposed an efficient solution approach, which has been analyzed to understand their time and space requirements. A large number of experiments have been conducted using real-life datasets and the results have been reported. From the results, we observe that the PoIs and modality of journey recommended by the proposed solution approach lead to much less time and cost than the baseline methods.
Medical image classification is a vital research area that utilizes advanced computational techniques to improve disease diagnosis and treatment planning. Deep learning models, especially Convolutional Neural Networks (CNNs), have transformed this field by providing automated and precise analysis of complex medical images. This study introduces a hybrid deep learning model that integrates a pre-trained ResNet101 with a custom CNN to classify kidney CT images into four categories: normal, stone, cyst, and tumor. The proposed model leverages feature fusion to enhance classification accuracy, achieving 99.73% training accuracy and 100% testing accuracy. Using a dataset of 12,446 CT images and advanced feature mapping techniques, the hybrid CNN model outperforms standalone ResNet101. This architecture delivers a robust and efficient solution for automated kidney disease diagnosis, providing improved precision, recall, and reduced testing time, making it highly suitable for clinical applications.
We show that contact-rich motion planning is also sparsity-rich when viewed as polynomial optimization (POP). We can exploit not only the correlative and term sparsity patterns that are general to all POPs, but also specialized sparsity patterns from the robot kinematic structure and the separability of contact modes. Such sparsity enables the design of high-order but sparse semidefinite programming (SDPs) relaxations--building upon Lasserre's moment and sums of squares hierarchy--that (i) can be solved in seconds by off-the-shelf SDP solvers, and (ii) compute near globally optimal solutions to the nonconvex contact-rich planning problems with small certified suboptimality. Through extensive experiments both in simulation (Push Bot, Push Box, Push Box with Obstacles, and Planar Hand) and real world (Push T), we demonstrate the power of using convex SDP relaxations to generate global contact-rich motion plans. As a contribution of independent interest, we release the Sparse Polynomial Optimization Toolbox (SPOT)--implemented in C++ with interfaces to both Python and Matlab--that automates sparsity exploitation for robotics and beyond.
Simulating human clients in mental health counseling is crucial for training and evaluating counselors (both human or simulated) in a scalable manner. Nevertheless, past research on client simulation did not focus on complex conversation tasks such as mental health counseling. In these tasks, the challenge is to ensure that the client's actions (i.e., interactions with the counselor) are consistent with with its stipulated profiles and negative behavior settings. In this paper, we propose a novel framework that supports consistent client simulation for mental health counseling. Our framework tracks the mental state of a simulated client, controls its state transitions, and generates for each state behaviors consistent with the client's motivation, beliefs, preferred plan to change, and receptivity. By varying the client profile and receptivity, we demonstrate that consistent simulated clients for different counseling scenarios can be effectively created. Both our automatic and expert evaluations on the generated counseling sessions also show that our client simulation method achieves higher consistency than previous methods.
Flight delay is a significant issue affecting air travel. The runway system, frequently falling short of demand, serves as a bottleneck. As demand increases, runway capacity expansion becomes imperative to mitigate congestion. However, the decision to expand runway capacity is challenging due to inherent uncertainties in demand forecasts. This paper presents a novel approach to modeling air traffic demand growth as a jump diffusion process, incorporating two layers of uncertainty: Geometric Brownian Motion (GBM) for continuous variability and a Poisson process to capture the impact of crisis events, such as natural disasters or public health emergencies, on decision-making. We propose a real options model to jointly evaluate the interrelated factors of optimal runway capacity and investment timing under uncertainty, with investment timing linked to trigger demand. The findings suggest that increased uncertainty indicates more conservative decision-making. Furthermore, the relationship between optimal investment timing and expansion size is complex: if the expansion size remains unchanged, the trigger demand decreases as the demand growth rate increases; if the expansion size experiences a jump, the trigger demand also exhibits a sharp rise. This work provides valuable insights for airport authorities for informed capacity expansion decision-making.
Intelligent agents working in real-world environments must be able to learn about the environment and its capabilities which enable them to take actions to change to the state of the world to complete a complex multi-step task in a photorealistic environment. Learning about the environment is especially important to perform various multiple-step tasks without having to redefine an agent's action set for different tasks or environment settings. In our work, we augment an existing task and motion planning framework with learned affordance models of objects in the world to enable planning and executing multi-step tasks using learned models. Each task can be seen as changing the current state of the world to a given goal state. The affordance models provide us with what actions are possible and how to perform those actions in any given state. A symbolic planning algorithm uses this information and the starting and goal state to create a feasible plan to reach the desired goal state to complete a given task. We demonstrate our approach in a virtual 3D photorealistic environment, AI2-Thor, and evaluate it on real-world tasks. Our results show that our agent quickly learns how to interact with the environment and is well prepared to perform tasks such as "Moving an object out of the way to reach the desired location."
Research on ultra-high dose rate (UHDR) radiation therapy has indicated its potential to spare normal tissue while maintaining equivalent tumor control compared to conventional treatments. First clinical trials are underway. The randomized phase II/III FEATHER clinical trial at the Paul Scherrer Institute in collaboration with the University of Zurich Animal Hospital is one of the first curative domestic animal trials to be attempted, and it is designed to provide a good example for human trials. However, the lack of standardized quality assurance (QA) guidelines for FLASH clinical trials presents a significant challenge in trial design. This work aims to demonstrate the development and testing of QA and reporting procedures implemented in the FEATHER clinical trial. We have expanded the clinical QA program to include UHDR-specific QA and additional patient-specific QA. Furthermore, we have modified the monitor readout to enable time-resolved measurements, allowing delivery log files to be used for dose and dose rate recalculations. Finally, we developed a reporting strategy encompassing relevant parameters for retrospective studies. We evaluated our QA and reporting procedures with simulated treatments. This testing confirmed that our QA procedures effectively ensure the correct and safe delivery of the planned dose. Additionally, we demonstrated that we could reconstruct the delivered dose and dose rate using the delivery log files. We developed and used in practice a comprehensive QA and reporting protocol for a FLASH clinical trial at the Paul Scherrer Institute. This work aims to establish guidelines and standardize reporting practices for future advancements in the FLASH-RT field.
Integrating Unmanned Aerial Vehicles (UAVs) with Unmanned Ground Vehicles (UGVs) provides an effective solution for persistent surveillance in disaster management. UAVs excel at covering large areas rapidly, but their range is limited by battery capacity. UGVs, though slower, can carry larger batteries for extended missions. By using UGVs as mobile recharging stations, UAVs can extend mission duration through periodic refueling, leveraging the complementary strengths of both systems. To optimize this energy-aware UAV-UGV cooperative routing problem, we propose a planning framework that determines optimal routes and recharging points between a UAV and a UGV. Our solution employs a deep reinforcement learning (DRL) framework built on an encoder-decoder transformer architecture with multi-head attention mechanisms. This architecture enables the model to sequentially select actions for visiting mission points and coordinating recharging rendezvous between the UAV and UGV. The DRL model is trained to minimize the age periods (the time gap between consecutive visits) of mission points, ensuring effective surveillance. We evaluate the framework across various problem sizes and distributions, comparing its performance against heuristic methods and an existing learning-based model. Results show that our approach consistently outperforms these baselines in both solution quality and runtime. Additionally, we demonstrate the DRL policy's applicability in a real-world disaster scenario as a case study and explore its potential for online mission planning to handle dynamic changes. Adapting the DRL policy for priority-driven surveillance highlights the model's generalizability for real-time disaster response.
Neural Signed Distance Fields (SDFs) provide a differentiable environment representation to readily obtain collision checks and well-defined gradients for robot navigation tasks. However, updating neural SDFs as the scene evolves entails re-training, which is tedious, time consuming, and inefficient, making it unsuitable for robot navigation with limited field-of-view in dynamic environments. Towards this objective, we propose a compositional framework of neural SDFs to solve robot navigation in indoor environments using only an onboard RGB-D sensor. Our framework embodies a dual mode procedure for trajectory optimization, with different modes using complementary methods of modeling collision costs and collision avoidance gradients. The primary stage queries the robot body's SDF, swept along the route to goal, at the obstacle point cloud, enabling swift local optimization of trajectories. The secondary stage infers the visible scene's SDF by aligning and composing the SDF representations of its constituents, providing better informed costs and gradients for trajectory optimization. The dual mode procedure combines the best of both stages, achieving a success rate of 98%, 14.4% higher than baseline with comparable amortized plan time on iGibson 2.0. We also demonstrate its effectiveness in adapting to real-world indoor scenarios.
Often software engineering classes have the student concentrate on designing and planning the project but stop short of actual student team development of code. This leads to criticism by employers of new graduates that they are missing skills in working in teams and coordinating multiple overlapping changes to a code base. Additionally, students that are not actively experiencing team development are unprepared to understand and modify existing legacy-code bases written by others. This paper presents a new approach to teaching undergraduate software engineering that emphasizes not only software engineering methodology but also experiencing development as a member of a team and modifying a legacy code base. Our innovative software engineering course begins with learning the fundamentals of software engineering, followed by examining an existing framework of a social media application. The students are then grouped into multiple software teams, each focusing on a different aspect of the app. The separate teams must define requirements, design, and provide documentation on the services. Using an Agile development approach, the teams incrementally add to the code base and demonstrate features as the application evolves. Subsequent iterations of the class pick up the prior students code base, providing experience working with a legacy code base. Preliminary results of using this approach at the university are presented in this paper including quantitative analysis. Analysis of student software submissions to the cloud-based code repository shows student engagement and contributions over the span of the course. Positive student evaluations show the effectiveness of applying the principles of software engineering to the development of a complex solution in a team environment. Keywords: Software engineering, teaching, college computer science, innovative methods, agile.
This paper presents a novel contingency planning framework that integrates learning-based multi-modal predictions of traffic participants into Branch Model Predictive Control (MPC). Leveraging reachability analysis, we address the computational challenges associated with Branch MPC by organizing the multitude of predictions into driving corridors. Analyzing the overlap between these corridors, their number can be reduced through pruning and clustering while ensuring safety since all prediction modes are preserved. These processed corridors directly correspond to the distinct branches of the scenario tree and provide an efficient constraint representation for the Branch MPC. We further utilize the reachability for determining maximum feasible decision postponing times, ensuring that branching decisions remain executable. Qualitative and quantitative evaluations demonstrate significantly reduced computational complexity and enhanced safety and comfort.
Partially Observable Markov Decision Processes (POMDPs) provide a robust framework for decision-making under uncertainty in applications such as autonomous driving and robotic exploration. Their extension, $\rho$POMDPs, introduces belief-dependent rewards, enabling explicit reasoning about uncertainty. Existing online $\rho$POMDP solvers for continuous spaces rely on fixed belief representations, limiting adaptability and refinement - critical for tasks such as information-gathering. We present $\rho$POMCPOW, an anytime solver that dynamically refines belief representations, with formal guarantees of improvement over time. To mitigate the high computational cost of updating belief-dependent rewards, we propose a novel incremental computation approach. We demonstrate its effectiveness for common entropy estimators, reducing computational cost by orders of magnitude. Experimental results show that $\rho$POMCPOW outperforms state-of-the-art solvers in both efficiency and solution quality.
The use of Self-Sovereign Identity (SSI) systems for digital identity management is gaining traction and interest. Countries such as Bhutan have already implemented an SSI infrastructure to manage the identity of their citizens. The EU, thanks to the revised eIDAS regulation, is opening the door for SSI vendors to develop SSI systems for the planned EU digital identity wallet. These developments, which fall within the sovereign domain, raise questions about individual privacy. The purpose of this article is to help SSI solution designers make informed choices to ensure that the designed solution is privacy-friendly. The observation is that the range of possible solutions is very broad, from DID and DID resolution methods to verifiable credential types, publicly available information (e.g. in a blockchain), type of infrastructure, etc. As a result, the article proposes (1) to group the elementary building blocks of a SSI system into 5 structuring layers, (2) to analyze for each layer the privacy implications of using the chosen building block, and (3) to provide a design assistance dashboard that gives the complete picture of the SSI, and shows the interdependencies between architectural choices and technical building blocks, allowing designers to make informed choices and graphically achieve a SSI solution that meets their need for privacy.
Teleoperation enables remote human support of automated vehicles in scenarios where the automation is not able to find an appropriate solution. Remote assistance concepts, where operators provide discrete inputs to aid specific automation modules like planning, is gaining interest due to its reduced workload on the human remote operator and improved safety. However, these concepts are challenging to implement and maintain due to their deep integration and interaction with the automated driving system. In this paper, we propose a solution to facilitate the implementation of remote assistance concepts that intervene on planning level and extend the operational design domain of the vehicle at runtime. Using arbitration graphs, a modular decision-making framework, we integrate remote assistance into an existing automated driving system without modifying the original software components. Our simulative implementation demonstrates this approach in two use cases, allowing operators to adjust planner constraints and enable trajectory generation beyond nominal operational design domains.
Segmentation of brain tumors is a critical step in treatment planning, yet manual segmentation is both time-consuming and subjective, relying heavily on the expertise of radiologists. In Sub-Saharan Africa, this challenge is magnified by overburdened medical systems and limited access to advanced imaging modalities and expert radiologists. Automating brain tumor segmentation using deep learning offers a promising solution. Convolutional Neural Networks (CNNs), especially the U-Net architecture, have shown significant potential. However, a major challenge remains: achieving generalizability across different datasets. This study addresses this gap by developing a deep learning ensemble that integrates UNet3D, V-Net, and MSA-VNet models for the semantic segmentation of gliomas. By initially training on the BraTS-GLI dataset and fine-tuning with the BraTS-SSA dataset, we enhance model performance. Our ensemble approach significantly outperforms individual models, achieving DICE scores of 0.8358 for Tumor Core, 0.8521 for Whole Tumor, and 0.8167 for Enhancing Tumor. These results underscore the potential of ensemble methods in improving the accuracy and reliability of automated brain tumor segmentation, particularly in resource-limited settings.
Context. Technical Debt (TD), defined as software constructs that are beneficial in the short term but may hinder future change, is a frequently used term in software development practice. Nevertheless, practitioners do not always fully understand its definition and, in particular, conceptual model. Previous research highlights that communication about TD is challenging, especially with non-technical stakeholders. Discussions on this topic often cause conflicts due to misunderstandings related to other stakeholders' perspectives. Goal. We designed a board game to emulate TD concepts to make them tangible to all stakeholders, including non-technical ones. The game aims to encourage discussions about TD in an emulated and safe environment, thereby avoiding real-life conflicts. Method. To evaluate the game's effectiveness, we surveyed 46 practitioners from diverse domains, positions, and experience levels who played the game in 13 sessions following extensive testing during its development. In addition to the players' general feedback, we examined situations where players recognized new insights about TD or connected game scenarios to real-life experiences. Results. Overall, the feedback on the game and its enjoyment factor were highly positive. While developers and software architects often connected game situations to their real-world experiences, non-technical stakeholders, such as scrum masters, product owners, and less experienced developers, encountered multiple new insights on TD. Numerous players have shifted their attitudes toward TD and have outlined a plan to modify their behavior regarding TD management. Conclusions. Although the game may not lead to long-term behavior change among stakeholders, participants' feedback provides evidence that it might serve as a valuable starting point for team discussions on technical debt management.
Lateral Spine Image (LSI) analysis is important for medical diagnosis, treatment planning, and detailed spinal health assessments. Although modalities like Computed Tomography and Digital X-ray Imaging are commonly used, Dual Energy X-ray Absorptiometry (DXA) is often preferred due to lower radiation exposure, seamless capture, and cost-effectiveness. Accurate Vertebral Landmark Localization (VLL) on LSIs is important to detect spinal conditions like kyphosis and lordosis, as well as assessing Abdominal Aortic Calcification (AAC) using Inter-Vertebral Guides (IVGs). Nonetheless, few automated VLL methodologies have concentrated on DXA LSIs. We present VerteNet, a hybrid CNN-Transformer model featuring a novel dual-resolution attention mechanism in self and cross-attention domains, referred to as Dual Resolution Self-Attention (DRSA) and Dual Resolution Cross-Attention (DRCA). These mechanisms capture the diverse frequencies in DXA images by operating at two different feature map resolutions. Additionally, we design a Multi-Context Feature Fusion Block (MCFB) that efficiently integrates the features using DRSA and DRCA. We train VerteNet on 620 DXA LSIs from various machines and achieve superior results compared to existing methods. We also design an algorithm that utilizes VerteNet's predictions in estimating the Region of Interest (ROI) to detect potential abdominal aorta cropping, where inadequate soft tissue hinders calcification assessment. Additionally, we present a small proof-of-concept study to show that IVGs generated from VLL information can improve inter-reader correlation in AAC scoring, addressing two key areas of disagreement in expert AAC-24 scoring: IVG placement and quality control for full abdominal aorta assessment. The code for this work can be found at https://github.com/zaidilyas89/VerteNet.
Existing predictive maintenance (PdM) methods typically focus solely on whether to replace system components without considering the costs incurred by inspection. However, a well-considered approach should be able to minimize Remaining Useful Life (RUL) at engine replacement while maximizing inspection interval. To achieve this, multi-agent reinforcement learning (MARL) can be introduced. However, due to the sequential and mutually constraining nature of these 2 objectives, conventional MARL is not applicable. Therefore, this paper introduces a novel framework and develops a Sequential Multi-objective Multi-agent Proximal Policy Optimization (SMOMA-PPO) algorithm. Furthermore, to provide comprehensive and effective degradation information to RL agents, we also employed Gated Recurrent Unit, quantile regression, and probability distribution fitting to develop a GRU-based RUL Prediction (GRP) model. Experiments demonstrate that the GRP method significantly improves the accuracy of RUL predictions in the later stages of system operation compared to existing methods. When incorporating its output into SMOMA-PPO, we achieve at least a 15% reduction in average RUL without unscheduled replacements (UR), nearly a 10% increase in inspection interval, and an overall decrease in maintenance costs. Importantly, our approach offers a new perspective for addressing multi-objective maintenance planning with sequential constraints, effectively enhancing system reliability and reducing maintenance expenses.
This paper introduces a learning-based visual planner for agile drone flight in cluttered environments. The proposed planner generates collision-free waypoints in milliseconds, enabling drones to perform agile maneuvers in complex environments without building separate perception, mapping, and planning modules. Learning-based methods, such as behavior cloning (BC) and reinforcement learning (RL), demonstrate promising performance in visual navigation but still face inherent limitations. BC is susceptible to compounding errors due to limited expert imitation, while RL struggles with reward function design and sample inefficiency. To address these limitations, this paper proposes an inverse reinforcement learning (IRL)-based framework for high-speed visual navigation. By leveraging IRL, it is possible to reduce the number of interactions with simulation environments and improve capability to deal with high-dimensional spaces while preserving the robustness of RL policies. A motion primitive-based path planning algorithm collects an expert dataset with privileged map data from diverse environments, ensuring comprehensive scenario coverage. By leveraging both the acquired expert and learner dataset gathered from the agent's interactions with the simulation environments, a robust reward function and policy are learned across diverse states. While the proposed method is trained in a simulation environment only, it can be directly applied to real-world scenarios without additional training or tuning. The performance of the proposed method is validated in both simulation and real-world environments, including forests and various structures. The trained policy achieves an average speed of 7 m/s and a maximum speed of 8.8 m/s in real flight experiments. To the best of our knowledge, this is the first work to successfully apply an IRL framework for high-speed visual navigation of drones.
In this paper, we address the challenge of long-horizon visual planning tasks using Hierarchical Reinforcement Learning (HRL). Our key contribution is a Discrete Hierarchical Planning (DHP) method, an alternative to traditional distance-based approaches. We provide theoretical foundations for the method and demonstrate its effectiveness through extensive empirical evaluations. Our agent recursively predicts subgoals in the context of a long-term goal and receives discrete rewards for constructing plans as compositions of abstract actions. The method introduces a novel advantage estimation strategy for tree trajectories, which inherently encourages shorter plans and enables generalization beyond the maximum tree depth. The learned policy function allows the agent to plan efficiently, requiring only $\log N$ computational steps, making re-planning highly efficient. The agent, based on a soft-actor critic (SAC) framework, is trained using on-policy imagination data. Additionally, we propose a novel exploration strategy that enables the agent to generate relevant training examples for the planning modules. We evaluate our method on long-horizon visual planning tasks in a 25-room environment, where it significantly outperforms previous benchmarks at success rate and average episode length. Furthermore, an ablation study highlights the individual contributions of key modules to the overall performance.
As autonomous driving systems (ADSes) become increasingly complex and integral to daily life, the importance of understanding the nature and mitigation of software bugs in these systems has grown correspondingly. Addressing the challenges of software maintenance in autonomous driving systems (e.g., handling real-time system decisions and ensuring safety-critical reliability) is crucial due to the unique combination of real-time decision-making requirements and the high stakes of operational failures in ADSes. The potential of automated tools in this domain is promising, yet there remains a gap in our comprehension of the challenges faced and the strategies employed during manual debugging and repair of such systems. In this paper, we present an empirical study that investigates bug-fix patterns in ADSes, with the aim of improving reliability and safety. We have analyzed the commit histories and bug reports of two major autonomous driving projects, Apollo and Autoware, from 1,331 bug fixes with the study of bug symptoms, root causes, and bug-fix patterns. Our study reveals several dominant bug-fix patterns, including those related to path planning, data flow, and configuration management. Additionally, we find that the frequency distribution of bug-fix patterns varies significantly depending on their nature and types and that certain categories of bugs are recurrent and more challenging to exterminate. Based on our findings, we propose a hierarchy of ADS bugs and two taxonomies of 15 syntactic bug-fix patterns and 27 semantic bug-fix patterns that offer guidance for bug identification and resolution. We also contribute a benchmark of 1,331 ADS bug-fix instances.
Autonomous Underwater Vehicles (AUVs) encounter significant energy, control and navigation challenges in complex underwater environments, particularly during close-proximity operations, such as launch and recovery (LAR), where fluid interactions and wake effects present additional navigational and energy challenges. Traditional path planning methods fail to incorporate these detailed wake structures, resulting in increased energy consumption, reduced control stability, and heightened safety risks. This paper presents a novel wake-informed, 3D path planning approach that fully integrates localized wake effects and global currents into the planning algorithm. Two variants of the A* algorithm - a current-informed planner and a wake-informed planner - are created to assess its validity and two neural network models are then trained to approximate these planners for real-time applications. Both the A* planners and NN models are evaluated using important metrics such as energy expenditure, path length, and encounters with high-velocity and turbulent regions. The results demonstrate a wake-informed A* planner consistently achieves the lowest energy expenditure and minimizes encounters with high-velocity regions, reducing energy consumption by up to 11.3%. The neural network models are observed to offer computational speedup of 6 orders of magnitude, but exhibit 4.51 - 19.79% higher energy expenditures and 9.81 - 24.38% less optimal paths. These findings underscore the importance of incorporating detailed wake structures into traditional path planning algorithms and the benefits of neural network approximations to enhance energy efficiency and operational safety for AUVs in complex 3D domains.
Stellar oscillations and granulation in red giants are both powered by convection. Studying the wavelength dependence of their amplitudes can provide useful insights on the driving mechanism. It is also important for plans to carry out asteroseismology with the Nancy Grace Roman Space Telescope, which will operate in the near infrared, to check the dependence of oscillations and granulation on the observational wavelength. In this work, we aim to understand how the oscillation and granulation power in red giants depend on the wavelength and study how existing predictions compare with observations. We measure the mean oscillation and granulation power of 279 Kepler red giants, from the power density spectra derived using Kepler PDCSAP and TESS-SPOC light curves. We find that selection of light curves is important for the study of amplitudes, since different light curve products from TESS show different values of amplitudes. We show that the oscillation and granulation power ratios between TESS and Kepler match the theoretical prediction, confirming that both decrease as we move to redder wavelengths. We also see that the mean ratios of oscillations and granulation agree, suggesting that oscillation and granulation have the same wavelength dependence. We also find that the mean height-to-background ratio for Kepler agrees with previous results and shows good agreement with TESS. These results suggest that the granulation signals would not severely affect the detection of oscillations. We checked the dependence of these ratio between Kepler and TESS on stellar parameters, and see no trends.
Bird's-eye view (BEV) perception for autonomous driving has garnered significant attention in recent years, in part because BEV representation facilitates the fusion of multi-sensor data. This enables a variety of perception tasks including BEV segmentation, a concise view of the environment that can be used to plan a vehicle's trajectory. However, this representation is not fully supported by existing datasets, and creation of new datasets can be a time-consuming endeavor. To address this problem, in this paper we introduce SimBEV, an extensively configurable and scalable randomized synthetic data generation tool that incorporates information from multiple sources to capture accurate BEV ground truth data, supports a comprehensive array of sensors, and enables a variety of perception tasks including BEV segmentation and 3D object detection. We use SimBEV to create the SimBEV dataset, a large collection of annotated perception data from diverse driving scenarios.
Human-robot cooperative navigation is challenging in environments with incomplete information. We introduce CoNav-Maze, a simulated robotics environment where a robot navigates using local perception while a human operator provides guidance based on an inaccurate map. The robot can share its camera views to improve the operator's understanding of the environment. To enable efficient human-robot cooperation, we propose Information Gain Monte Carlo Tree Search (IG-MCTS), an online planning algorithm that balances autonomous movement and informative communication. Central to IG-MCTS is a neural human perception dynamics model that estimates how humans distill information from robot communications. We collect a dataset through a crowdsourced mapping task in CoNav-Maze and train this model using a fully convolutional architecture with data augmentation. User studies show that IG-MCTS outperforms teleoperation and instruction-following baselines, achieving comparable task performance with significantly less communication and lower human cognitive load, as evidenced by eye-tracking metrics.
While generative robot policies have demonstrated significant potential in learning complex, multimodal behaviors from demonstrations, they still exhibit diverse failures at deployment-time. Policy steering offers an elegant solution to reducing the chance of failure by using an external verifier to select from low-level actions proposed by an imperfect generative policy. Here, one might hope to use a Vision Language Model (VLM) as a verifier, leveraging its open-world reasoning capabilities. However, off-the-shelf VLMs struggle to understand the consequences of low-level robot actions as they are represented fundamentally differently than the text and images the VLM was trained on. In response, we propose FOREWARN, a novel framework to unlock the potential of VLMs as open-vocabulary verifiers for runtime policy steering. Our key idea is to decouple the VLM's burden of predicting action outcomes (foresight) from evaluation (forethought). For foresight, we leverage a latent world model to imagine future latent states given diverse low-level action plans. For forethought, we align the VLM with these predicted latent states to reason about the consequences of actions in its native representation--natural language--and effectively filter proposed plans. We validate our framework across diverse robotic manipulation tasks, demonstrating its ability to bridge representational gaps and provide robust, generalizable policy steering. Videos can be found on the project website: https://yilin-wu98.github.io/forewarn/.
Effective network planning and sensing in wireless networks require resource-intensive site surveys for data collection. An alternative is Radio-Frequency (RF) signal spatial propagation modeling, which computes received signals given transceiver positions in a scene (e.g.s a conference room). We identify a fundamental trade-off between scalability and fidelity in the state-of-the-art method. To address this issue, we explore leveraging 3D Gaussian Splatting (3DGS), an advanced technique for the image synthesis of 3D scenes in real-time from arbitrary camera poses. By integrating domain-specific insights, we design three components for adapting 3DGS to the RF domain, including Gaussian-based RF scene representation, gradient-guided RF attribute learning, and RF-customized CUDA for ray tracing. Building on them, we develop RFSPM, an end-to-end framework for scalable RF signal Spatial Propagation Modeling. We evaluate RFSPM in four field studies and two applications across RFID, BLE, LoRa, and 5G, covering diverse frequencies, antennas, signals, and scenes. The results show that RFSPM matches the fidelity of the state-of-the-art method while reducing data requirements, training GPU-hours, and inference latency by up to 9.8\,$\times$, 18.6\,$\times$, and 84.4\,$\times$, respectively.
In the era of generative AI, integrating video generation models into robotics opens new possibilities for the general-purpose robot agent. This paper introduces imitation learning with latent video planning (VILP). We propose a latent video diffusion model to generate predictive robot videos that adhere to temporal consistency to a good degree. Our method is able to generate highly time-aligned videos from multiple views, which is crucial for robot policy learning. Our video generation model is highly time-efficient. For example, it can generate videos from two distinct perspectives, each consisting of six frames with a resolution of 96x160 pixels, at a rate of 5 Hz. In the experiments, we demonstrate that VILP outperforms the existing video generation robot policy across several metrics: training costs, inference speed, temporal consistency of generated videos, and the performance of the policy. We also compared our method with other imitation learning methods. Our findings indicate that VILP can rely less on extensive high-quality task-specific robot action data while still maintaining robust performance. In addition, VILP possesses robust capabilities in representing multi-modal action distributions. Our paper provides a practical example of how to effectively integrate video generation models into robot policies, potentially offering insights for related fields and directions. For more details, please refer to our open-source repository https://github.com/ZhengtongXu/VILP.
Leading AI developers and startups are increasingly deploying agentic AI systems that can plan and execute complex tasks with limited human involvement. However, there is currently no structured framework for documenting the technical components, intended uses, and safety features of agentic systems. To fill this gap, we introduce the AI Agent Index, the first public database to document information about currently deployed agentic AI systems. For each system that meets the criteria for inclusion in the index, we document the system's components (e.g., base model, reasoning implementation, tool use), application domains (e.g., computer use, software engineering), and risk management practices (e.g., evaluation results, guardrails), based on publicly available information and correspondence with developers. We find that while developers generally provide ample information regarding the capabilities and applications of agentic systems, they currently provide limited information regarding safety and risk management practices. The AI Agent Index is available online at https://aiagentindex.mit.edu/
Active breath-hold techniques effectively mitigate respiratory motion but pose challenges for patients who are ineligible for the procedure. Conventional treatment planning relies on multiple energy layers, extending delivery time due to slow layer switching. We propose to use pin ridge filters (pRFs), initially developed for FLASH radiotherapy, to construct a single energy beam plan and minimize dose delivery time. The conventional ITV--based free--breathing treatment plan served as the reference. A GTV--based IMPT--DS plan with a downstream energy modulation strategy was developed based on a new beam model that was commissioned using the maximum energy of the IMPT plan. Consequently, a nested iterative pencil beam direction (PBD) spot reduction process removed low--weighted spots along each PBD, generating pRFs with coarser resolution. Finally, the IMPT--DS plan was then converted into an IMPT--pRF plan, using a monoenergetic beam with optimized spot positions and weights. This approach was validated on lung and liver SBRT cases (10 Gy RBE x 5). For the lung case, the mean lung--GTV dose decreased from 10.3 Gy to 6.9 Gy, with delivery time reduced from 188.79 to 36.16 seconds. The largest time reduction was at 150{\deg}, from 47.4 to 3.99 seconds. For the liver case, the mean liver--GTV dose decreased from 5.7 Gy to 3.8 Gy, with delivery time reduced from 111.13 to 30.54 seconds. The largest time reduction was at 180{\deg}, from 38.57 to 3.94 seconds. This method significantly reduces dose delivery time and organ at risk dose. Further analysis is needed to validate its clinical feasibility.
The ability to accurately produce geometries with specified properties is perhaps the most important characteristic of a manufacturing process. 3D printing is marked by exceptional design freedom and complexity but is also prone to geometric and other defects that must be resolved for it to reach its full potential. Ultimately, this will require both astute design decisions and timely parameter adjustments to maintain stability that is challenging even with expert human operators. While machine learning is widely investigated in 3D printing, existing methods typically overlook spatial features that vary across prints and thus find it difficult to produce desired geometries. Here, we encode volumetric representations of printed parts into neural fields and apply a new regularization strategy, based on minimizing the partial derivative of the field's output with respect to a single, non-learnable parameter. By thus encouraging small input changes to yield only small output variations, we encourage smooth interpolation between observed volumes and hence realistic geometry predictions. This framework therefore allows the extraction of 'imagined' 3D shapes, revealing how a part would look if manufactured under previously unseen parameters. The resulting continuous field is used for data-driven optimization to maximize geometric fidelity between expected and produced geometries, reducing post-processing, material waste, and production costs. By optimizing process parameters dynamically, our approach enables advanced planning strategies, potentially allowing manufacturers to better realize complex and feature-rich designs.
Continuing advances in frontier model research are paving the way for widespread deployment of AI agents. Meanwhile, global interest in building large, complex systems in software, manufacturing, energy and logistics has never been greater. Although AI driven system engineering holds tremendous promise, the static benchmarks dominating agent evaluations today fail to capture the crucial skills required for implementing dynamic systems, such as managing uncertain trade-offs and ensuring proactive adaptability. This position paper advocates for training and evaluating AI agents' system engineering abilities through automation-oriented sandbox games-particularly Factorio. By directing research efforts in this direction, we can equip AI agents with the specialized reasoning and long-horizon planning necessary to design, maintain, and optimize tomorrow's most demanding engineering projects.
Generating a collision-free robot motion is crucial for safe applications in real-world settings. This requires an accurate model of all obstacle shapes within the constrained robot cell, which is particularly challenging and time-consuming. The difficulty is heightened in flexible production lines, where the environment model must be updated each time the robot cell is modified. Furthermore, sensor-based methods often necessitate costly hardware and calibration procedures, and can be influenced by environmental factors (e.g., light conditions or reflections). To address these challenges, we present a novel data-driven approach to modeling a cluttered workspace, leveraging solely the robot internal joint encoders to capture exploratory motions. By computing the corresponding swept volume, we generate a (conservative) mesh of the environment that is subsequently used for collision checking within established path planning and control methods. Our method significantly reduces the complexity and cost of classical environment modeling by removing the need for CAD files and external sensors. We validate the approach with the KUKA LBR iisy collaborative robot in a pick-and-place scenario. In less than three minutes of exploratory robot motions and less than four additional minutes of computation time, we obtain an accurate model that enables collision-free motions. Our approach is intuitive, easy-to-use, making it accessible to users without specialized technical knowledge. It is applicable to all types of industrial robots or cobots.
Previous humanoid robot research works treat the robot as a bipedal mobile manipulation platform, where only the feet and hands contact the environment. However, we humans use all body parts to interact with the world, e.g., we sit in chairs, get up from the ground, or roll on the floor. Contacting the environment using body parts other than feet and hands brings significant challenges in both model-predictive control and reinforcement learning-based methods. An unpredictable contact sequence makes it almost impossible for model-predictive control to plan ahead in real time. The success of the zero-shot sim-to-real reinforcement learning method for humanoids heavily depends on the acceleration of GPU-based rigid-body physical simulator and simplification of the collision detection. Lacking extreme torso movement of the humanoid research makes all other components non-trivial to design, such as termination conditions, motion commands and reward designs. To address these potential challenges, we propose a general humanoid motion framework that takes discrete motion commands and controls the robot's motor action in real time. Using a GPU-accelerated rigid-body simulator, we train a humanoid whole-body control policy that follows the high-level motion command in the real world in real time, even with stochastic contacts and extremely large robot base rotation and not-so-feasible motion command. More details at https://project-instinct.github.io
Computational prediction of enzymatic reactions represents a crucial challenge in sustainable chemical synthesis across various scientific domains, ranging from drug discovery to materials science and green chemistry. These syntheses rely on proteins that selectively catalyze complex molecular transformations. These protein catalysts exhibit remarkable substrate adaptability, with the same protein often catalyzing different chemical transformations depending on its molecular partners. Current approaches to protein representation in reaction prediction either ignore protein structure entirely or rely on static embeddings, failing to capture how proteins dynamically adapt their behavior to different substrates. We present Docking-Aware Attention (DAA), a novel architecture that generates dynamic, context-dependent protein representations by incorporating molecular docking information into the attention mechanism. DAA combines physical interaction scores from docking predictions with learned attention patterns to focus on protein regions most relevant to specific molecular interactions. We evaluate our method on enzymatic reaction prediction, where it outperforms previous state-of-the-art methods, achieving 62.2\% accuracy versus 56.79\% on complex molecules and 55.54\% versus 49.45\% on innovative reactions. Through detailed ablation studies and visualizations, we demonstrate how DAA generates interpretable attention patterns that adapt to different molecular contexts. Our approach represents a general framework for context-aware protein representation in biocatalysis prediction, with potential applications across enzymatic synthesis planning. We open-source our implementation and pre-trained models to facilitate further research.
We present MauveSim, the instrument simulator software for Mauve, the latest mission from Blue Skies Space dedicated to time-domain stellar astronomy. The tool is designed to generate simulated stellar spectra, enabling the assessment of various scientific objectives, as well as determining limiting magnitudes and conducting signal-to-noise (S/N) analyses. MauveSim functions as an end-to-end simulator that takes an input stellar spectrum-either observed or synthetic-and produces a simulated observation based on the instrument's performance and characteristics. The results of MauveSim have been validated against instrument performance data from extensive ground testing campaigns, ensuring that the software reflects the most up-to-date understanding of the payload performance. Accessible to all scientists involved in the mission, MauveSim serves as a crucial tool for target selection and observation planning.
This study proposes a new model based on a classic S-curve that describes deployment and stabilization at maximum capacity. In addition, the model extends to the post-growth plateau, where technological capacity is renewed according to the distribution of equipment lifespans. We obtain two qualitatively different results. In the case of "fast" deployment, characterized by a short deployment time in relation to the average equipment lifetime, production is subject to significant oscillations. In the case of "slow" deployment, production increases monotonically until it reaches a renewal plateau. These results are counterintuitively validated by two case studies: nuclear power plants as a fast deployment and smartphones as a slow deployment. These results are important for long-term industrial planning, as they enable us to anticipate future business cycles. Our study demonstrates that business cycles can originate endogenously from industrial dynamics of installation and renewal, contrasting with traditional views attributing fluctuations to exogenous macroeconomic factors. These endogenous cycles interact with broader trends, potentially being modulated, amplified, or attenuated by macroeconomic conditions. This dynamic of deployment and renewal is relevant for long-life infrastructure technologies, such as those supporting the renewable energy sector and has major policy implications for industry players.
Traffic assignment analyzes traffic flows in road networks that emerge due to traveler interaction. Traditionally, travelers are assumed to use private cars, so road costs grow with the number of users due to congestion. However, in sustainable transit systems, travelers share vehicles s.t. more users on a road lead to higher sharing potential and reduced cost per user. Thus, we invert the usual avoidant traffic assignment (ATA) and instead consider synergistic traffic assignment (STA) where road costs decrease with use. We find that STA is significantly different from ATA from a game-theoretical point of view. We show that a simple iterative best-response method with simultaneous updates converges to an equilibrium state. This enables efficient computation of equilibria using optimized speedup techniques for shortest-path queries. In contrast, ATA requires slower sequential updates or more complicated iteration schemes that only approximate an equilibrium. Experiments with a realistic scenario for the city of Stuttgart indicate that STA indeed quickly converges to an equilibrium. We envision STA as a part of software-defined transportation systems that dynamically adapt to current travel demand. As a first demonstration, we show that an STA equilibrium can be used to incorporate traveler synergism in a simple bus line planning algorithm to potentially greatly reduce the required vehicle resources.
We investigated the generation of the $\alpha$ and $\beta$ effects in a rotating spherical plasma system with oppositely polarized kinetic helicity in the northern and southern hemispheres and examined their contributions to the induction of magnetic fields. We found that the $\alpha$ effect is relatively small, and its sign depends on the polarization of kinetic helicity. In contrast, the $\beta$ effect remains negative regardless of the sign of kinetic helicity. Despite its small magnitude, the $\alpha$ effect plays a crucial role in determining the polarity of helical magnetic structures, while a negative $\beta$ indicates energy diffusion from turbulent regions into the large-scale magnetic field. We derived the $\alpha$ and $\beta$ effects with oppositely polarized kinetic helicity using different approaches, incorporating large-scale magnetic data and turbulent kinetic data. These were used to reproduce the large-scale magnetic field and compare it with DNS results. In the kinematic regime, where the magnetic field strength is weak, our results align well; however, in regions with strong nonlinear magnetic effects, the magnetic field reproduced using turbulent kinetic data diverges. This divergence is attributed to insufficient quenching of the $\beta$ effect, suggesting that including the second-moment terms of velocity in the magnetic field effect would improve the accuracy of the $\beta$ coefficient. In this study, we considered the case of a rotating plasma sphere with $Pr_M = 1$ and low Reynolds numbers. However, in reality, Reynolds numbers are much higher, and $Pr_M$ is much less than 1, which necessitates further studies on this topic. We plan to address this in future research.
Reinforcement learning (RL) has been a promising essence in future 5G-beyond and 6G systems. Its main advantage lies in its robust model-free decision-making in complex and large-dimension wireless environments. However, most existing RL frameworks rely on online interaction with the environment, which might not be feasible due to safety and cost concerns. Another problem with online RL is the lack of scalability of the designed algorithm with dynamic or new environments. This work proposes a novel, resilient, few-shot meta-offline RL algorithm combining offline RL using conservative Q-learning (CQL) and meta-learning using model-agnostic meta-learning (MAML). The proposed algorithm can train RL models using static offline datasets without any online interaction with the environments. In addition, with the aid of MAML, the proposed model can be scaled up to new unseen environments. We showcase the proposed algorithm for optimizing an unmanned aerial vehicle (UAV) 's trajectory and scheduling policy to minimize the age-of-information (AoI) and transmission power of limited-power devices. Numerical results show that the proposed few-shot meta-offline RL algorithm converges faster than baseline schemes, such as deep Q-networks and CQL. In addition, it is the only algorithm that can achieve optimal joint AoI and transmission power using an offline dataset with few shots of data points and is resilient to network failures due to unprecedented environmental changes.
Traditionally, query optimizers rely on cost models to choose the best execution plan from several candidates, making precise cost estimates critical for efficient query execution. In recent years, cost models based on machine learning have been proposed to overcome the weaknesses of traditional cost models. While these models have been shown to provide better prediction accuracy, only limited efforts have been made to investigate how well Learned Cost Models (LCMs) actually perform in query optimization and how they affect overall query performance. In this paper, we address this by a systematic study evaluating LCMs on three of the core query optimization tasks: join ordering, access path selection, and physical operator selection. In our study, we compare seven state-of-the-art LCMs to a traditional cost model and, surprisingly, find that the traditional model often still outperforms LCMs in these tasks. We conclude by highlighting major takeaways and recommendations to guide future research toward making LCMs more effective for query optimization.
Short-term phonetic accommodation is a fundamental driver behind accent change, but how does real-time input from another speaker's voice shape the speech planning representations of an interlocutor? We advance a computational model of change in phonetic representations during phonetic accommodation, grounded in dynamic neural field equations for movement planning and memory dynamics. We test the model's ability to capture empirical patterns from an experimental study where speakers shadowed a model talker with a different accent from their own. The experimental data shows vowel-specific degrees of convergence during shadowing, followed by return to baseline (or minor divergence) post-shadowing. The model can reproduce these phenomena by modulating the magnitude of inhibitory memory dynamics, which may reflect resistance to accommodation due to phonological and/or sociolinguistic pressures. We discuss the implications of these results for the relation between short-term phonetic accommodation and longer-term patterns of sound change.
Photoplethysmography (PPG)-based foundation models are gaining traction due to the widespread use of PPG in biosignal monitoring and their potential to generalize across diverse health applications. In this paper, we introduce Pulse-PPG, the first open-source PPG foundation model trained exclusively on raw PPG data collected over a 100-day field study with 120 participants. Existing PPG foundation models are either open-source but trained on clinical data or closed-source, limiting their applicability in real-world settings. We evaluate Pulse-PPG across multiple datasets and downstream tasks, comparing its performance against a state-of-the-art foundation model trained on clinical data. Our results demonstrate that Pulse-PPG, trained on uncurated field data, exhibits superior generalization across clinical and mobile health applications in both lab and field settings. This suggests that exposure to real-world variability enables the model to learn fine-grained representations, making it more adaptable across tasks. Furthermore, pre-training on field data surprisingly outperforms its pre-training on clinical data in many tasks, reinforcing the importance of training on real-world, diverse datasets. To encourage further advancements in robust foundation models leveraging field data, we plan to release Pulse-PPG, providing researchers with a powerful resource for developing more generalizable PPG-based models.
Contact-implicit motion planning-embedding contact sequencing as implicit complementarity constraints-holds the promise of leveraging continuous optimization to discover new contact patterns online. Nevertheless, the resulting optimization, being an instance of Mathematical Programming with Complementary Constraints, fails the classical constraint qualifications that are crucial for the convergence of popular numerical solvers. We present robust contact-implicit motion planning with sequential convex programming (CRISP), a solver that departs from the usual primal-dual algorithmic framework but instead only focuses on the primal problem. CRISP solves a convex quadratic program with an adaptive trust region radius at each iteration, and its convergence is evaluated by a merit function using weighted penalty. We (i) provide sufficient conditions on CRISP's convergence to first-order stationary points of the merit function; (ii) release a high-performance C++ implementation of CRISP with a generic nonlinear programming interface; and (iii) demonstrate CRISP's surprising robustness in solving contact-implicit planning with naive initialization. In fact, CRISP solves several contact-implicit problems with all-zero initialization.
In this paper, we proposed a method to optimize adaptive proton FLASH therapy (ADP FLASH) using modularized pin ridge filters (pRFs) by recycling module pins from the initial plan while reducing pRF adjustments in adaptive FLASH planning. Initially, single energy (250 MeV) FLASH pRF plans were created using pencil beam directions (PBDs) from initial IMPT plans on the planning CT (pCT). PBDs are classified as new/changed ($\Delta$E > > 5 MeV) or unchanged by comparing spot maps for targets between pCT and re-CT. We used an iterative least square regression model to identify recyclable PBDs with minimal relative changes to spot MU weighting. Two PBDs with the least square error were retrieved per iteration and added to the background plan, and the remaining PBDs were reoptimized for the adaptive plan in subsequent iterations. The method was validated on three liver SBRT cases (50 Gy in 5 fractions) by comparing various dosimetric parameters across initial pRF plans on pCT, reCT and the ADP FLASH pRF plans on reCT. V100 for initial pRF plans on pCT, reCT, and ADP FLASH pRF plans for the three cases were as follows: (93.7%, 89.2%, 91.4%), (93.5%, 60.2%, 91.7%), (97.3%, 69.9%, 98.8%). We observe a decline in plan quality when applying the initial pRF to the reCT, whereas the ADP FLASH pRF approach restores quality comparable to the initial pRF on the pCT. FLASH effect of the initial pRF and ADP pRF plans were evaluated with a dose and dose rate threshold of 1Gy and 40Gy/s, respectively, using the FLASH effectiveness model. The proposed method recycled 91.2%, 71%, and 64.7% of PBDs from initial pRF plans for the three cases while maintaining all clinical goals and preserving FLASH effects across all cases.
Many approaches to multi-robot coordination are susceptible to failure due to communication loss and uncertainty in estimation. We present a real-time communication-free distributed algorithm for navigating robots to their desired goals certified by control barrier functions, that model and control the onboard sensing behavior to keep neighbors in the limited field of view for position estimation. The approach is robust to temporary tracking loss and directly synthesizes control in real time to stabilize visual contact through control Lyapunov-barrier functions. The main contributions of this paper are a continuous-time robust trajectory generation and control method certified by control barrier functions for distributed multi-robot systems and a discrete optimization procedure, namely, MPC-CBF, to approximate the certified controller. In addition, we propose a linear surrogate of high-order control barrier function constraints and use sequential quadratic programming to solve MPC-CBF efficiently. We demonstrate results in simulation with 10 robots and physical experiments with 2 custom-built UAVs. To the best of our knowledge, this work is the first of its kind to generate a robust continuous-time trajectory and controller concurrently, certified by control barrier functions utilizing piecewise splines.
Effective integration of AI agents into daily life requires them to understand and adapt to individual human preferences, particularly in collaborative roles. Although recent studies on embodied intelligence have advanced significantly, they typically adopt generalized approaches that overlook personal preferences in planning. We address this limitation by developing agents that not only learn preferences from few demonstrations but also learn to adapt their planning strategies based on these preferences. Our research leverages the observation that preferences, though implicitly expressed through minimal demonstrations, can generalize across diverse planning scenarios. To systematically evaluate this hypothesis, we introduce Preference-based Planning (PbP) benchmark, an embodied benchmark featuring hundreds of diverse preferences spanning from atomic actions to complex sequences. Our evaluation of SOTA methods reveals that while symbol-based approaches show promise in scalability, significant challenges remain in learning to generate and execute plans that satisfy personalized preferences. We further demonstrate that incorporating learned preferences as intermediate representations in planning significantly improves the agent's ability to construct personalized plans. These findings establish preferences as a valuable abstraction layer for adaptive planning, opening new directions for research in preference-guided plan generation and execution.
In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual learning. In autonomous driving, VQA plays a vital role in enabling the system to understand and reason about its surroundings. However, traditional models often struggle with catastrophic forgetting when sequentially exposed to new driving tasks, such as perception, prediction, and planning, each requiring different forms of knowledge. To address this challenge, we present a novel continual learning framework that combines VLMs with selective memory replay and knowledge distillation, reinforced by task-specific projection layer regularization. The knowledge distillation allows a previously trained model to act as a "teacher" to guide the model through subsequent tasks, minimizing forgetting. Meanwhile, task-specific projection layers calculate the loss based on the divergence of feature representations, ensuring continuity in learning and reducing the shift between tasks. Evaluated on the DriveLM dataset, our framework shows substantial performance improvements, with gains ranging from 21.40% to 32.28% across various metrics. These results highlight the effectiveness of combining continual learning with VLMs in enhancing the resilience and reliability of VQA systems in autonomous driving. We will release our source code.
Enabling legged robots to perform non-prehensile loco-manipulation with large and heavy objects is crucial for enhancing their versatility. However, this is a challenging task, often requiring sophisticated planning strategies or extensive task-specific reward shaping, especially in unstructured scenarios with obstacles. In this work, we present CAIMAN, a novel framework for learning loco-manipulation that relies solely on sparse task rewards. We leverage causal action influence to detect states where the robot is in control over other entities in the environment, and use this measure as an intrinsically motivated objective to enable sample-efficient learning. We employ a hierarchical control strategy, combining a low-level locomotion policy with a high-level policy that prioritizes task-relevant velocity commands. Through simulated and real-world experiments, including object manipulation with obstacles, we demonstrate the framework's superior sample efficiency, adaptability to diverse environments, and successful transfer to hardware without fine-tuning. The proposed approach paves the way for scalable, robust, and autonomous loco-manipulation in real-world applications.
Chronic liver disease represents a significant health challenge worldwide and accurate prognostic evaluations are essential for personalized treatment plans. Recent evidence suggests that integrating multimodal data, such as computed tomography imaging, radiomic features, and clinical information, can provide more comprehensive prognostic information. However, modalities have an inherent heterogeneity, and incorporating additional modalities may exacerbate the challenges of heterogeneous data fusion. Moreover, existing multimodal fusion methods often struggle to adapt to richer medical modalities, making it difficult to capture inter-modal relationships. To overcome these limitations, We present the Triple-Modal Interaction Chronic Liver Network (TMI-CLNet). Specifically, we develop an Intra-Modality Aggregation module and a Triple-Modal Cross-Attention Fusion module, which are designed to eliminate intra-modality redundancy and extract cross-modal information, respectively. Furthermore, we design a Triple-Modal Feature Fusion loss function to align feature representations across modalities. Extensive experiments on the liver prognosis dataset demonstrate that our approach significantly outperforms existing state-of-the-art unimodal models and other multi-modal techniques. Our code is available at https://github.com/Mysterwll/liver.git.
Travel demand prediction is crucial for optimizing transportation planning, resource allocation, and infrastructure development, ensuring efficient mobility and economic sustainability. This study introduces a Neurosymbolic Artificial Intelligence (Neurosymbolic AI) framework that integrates decision tree (DT)-based symbolic rules with neural networks (NNs) to predict travel demand, leveraging the interpretability of symbolic reasoning and the predictive power of neural learning. The framework utilizes data from diverse sources, including geospatial, economic, and mobility datasets, to build a comprehensive feature set. DTs are employed to extract interpretable if-then rules that capture key patterns, which are then incorporated as additional features into a NN to enhance its predictive capabilities. Experimental results show that the combined dataset, enriched with symbolic rules, consistently outperforms standalone datasets across multiple evaluation metrics, including Mean Absolute Error (MAE), \(R^2\), and Common Part of Commuters (CPC). Rules selected at finer variance thresholds (e.g., 0.0001) demonstrate superior effectiveness in capturing nuanced relationships, reducing prediction errors, and aligning with observed commuter patterns. By merging symbolic and neural learning paradigms, this Neurosymbolic approach achieves both interpretability and accuracy.
Monte Carlo Tree Search (MCTS) has proven highly effective in solving complex planning tasks by balancing exploration and exploitation using Upper Confidence Bound for Trees (UCT). However, existing work have not considered MCTS-based lifelong planning, where an agent faces a non-stationary series of tasks -- e.g., with varying transition probabilities and rewards -- that are drawn sequentially throughout the operational lifetime. This paper presents LiZero for Lipschitz lifelong planning using MCTS. We propose a novel concept of adaptive UCT (aUCT) to transfer knowledge from a source task to the exploration/exploitation of a new task, depending on both the Lipschitz continuity between tasks and the confidence of knowledge in in Monte Carlo action sampling. We analyze LiZero's acceleration factor in terms of improved sampling efficiency and also develop efficient algorithms to compute aUCT in an online fashion by both data-driven and model-based approaches, whose sampling complexity and error bounds are also characterized. Experiment results show that LiZero significantly outperforms existing MCTS and lifelong learning baselines in terms of much faster convergence (3$\sim$4x) to optimal rewards. Our results highlight the potential of LiZero to advance decision-making and planning in dynamic real-world environments.
Efficient real-time trajectory planning and control for fixed-wing unmanned aerial vehicles is challenging due to their non-holonomic nature, complex dynamics, and the additional uncertainties introduced by unknown aerodynamic effects. In this paper, we present a fast and efficient real-time trajectory planning and control approach for fixed-wing unmanned aerial vehicles, leveraging the differential flatness property of fixed-wing aircraft in coordinated flight conditions to generate dynamically feasible trajectories. The approach provides the ability to continuously replan trajectories, which we show is useful to dynamically account for the curvature constraint as the aircraft advances along its path. Extensive simulations and real-world experiments validate our approach, showcasing its effectiveness in generating trajectories even in challenging conditions for small FW such as wind disturbances.
World models are crucial for enabling agents to simulate and plan within environments, yet existing approaches struggle with long-term dependencies and inconsistent predictions. We introduce EDELINE, a novel framework that integrates diffusion models with linear-time state space modelsto enhance memory retention and temporal consistency. EDELINE employs a recurrent embedding module based on Mamba SSMs for processing unbounded sequences, a unified architecture for joint reward and termination prediction, and dynamic loss harmonization to balance multi-task learning. Our results across multiple benchmarks demonstrate EDELINE's superiority and robustness over prior baselines in long-horizon tasks.
Current software stacks for real-world applications of autonomous driving leverage map information to ensure reliable localization, path planning, and motion prediction. An important field of research is the generation of point cloud maps, referring to the topic of simultaneous localization and mapping (SLAM). As most recent developments do not include global position data, the resulting point cloud maps suffer from internal distortion and missing georeferencing, preventing their use for map-based localization approaches. Therefore, we propose FlexCloud for an automatic georeferencing of point cloud maps created from SLAM. Our approach is designed to work modularly with different SLAM methods, utilizing only the generated local point cloud map and its odometry. Using the corresponding GNSS positions enables direct georeferencing without additional control points. By leveraging a 3D rubber-sheet transformation, we can correct distortions within the map caused by long-term drift while maintaining its structure. Our approach enables the creation of consistent, globally referenced point cloud maps from data collected by a mobile mapping system (MMS). The source code of our work is available at https://github.com/TUMFTM/FlexCloud.
Join order optimization is among the most crucial query optimization problems, and its central position is also evident in the new research field where quantum computing is applied to database optimization and data management. In the field, join order optimization is the most studied database problem, usually tackled with a quadratic unconstrained binary optimization model, which is solved with various meta-heuristics such as quantum annealing, quantum approximate optimization algorithm, or variational quantum eigensolver. In this work, we continue developing quantum computing techniques for join order optimization by presenting three novel quantum optimization algorithms. These algorithms are based on a higher-order unconstrained binary optimization model, which is a generalization of the quadratic model and has not previously been applied to database problems. Theoretically, these optimization problems naturally map to universal quantum computers and quantum annealers. Compared to previous research, two of our algorithms are the first quantum algorithms to precisely model the join order cost function. We prove theoretical bounds by showing that these two methods encode the same plans as the dynamic programming algorithm without cross-products, which provides the optimal result up to cross-products. The third algorithm reaches at least as good plans as the greedy algorithm without cross-products. These results set an important theoretical connection between the classical and quantum algorithms for join order selection, which has not been studied in the previous research. To demonstrate our algorithms' practical usability, we have conducted an experimental evaluation on thousands of clique, cycle, star, tree, and chain query graphs using quantum and classical solvers.
Background: Real-time treatment planning in IMRT is challenging due to complex beam interactions. AI has improved automation, but existing models require large, high-quality datasets and lack universal applicability. Deep reinforcement learning (DRL) offers a promising alternative by mimicking human trial-and-error planning. Purpose: Develop a stochastic policy-based DRL agent for automatic treatment planning with efficient training, broad applicability, and robustness against adversarial attacks using Fast Gradient Sign Method (FGSM). Methods: Using the Actor-Critic with Experience Replay (ACER) architecture, the agent tunes treatment planning parameters (TPPs) in inverse planning. Training is based on prostate cancer IMRT cases, using dose-volume histograms (DVHs) as input. The model is trained on a single patient case, validated on two independent cases, and tested on 300+ plans across three datasets. Plan quality is assessed using ProKnow scores, and robustness is tested against adversarial attacks. Results: Despite training on a single case, the model generalizes well. Before ACER-based planning, the mean plan score was 6.20$\pm$1.84; after, 93.09% of cases achieved a perfect score of 9, with a mean of 8.93$\pm$0.27. The agent effectively prioritizes optimal TPP tuning and remains robust against adversarial attacks. Conclusions: The ACER-based DRL agent enables efficient, high-quality treatment planning in prostate cancer IMRT, demonstrating strong generalizability and robustness.
Accurate weather forecasts are important for disaster prevention, agricultural planning, and water resource management. Traditional numerical weather prediction (NWP) methods offer physically interpretable high-accuracy predictions but are computationally expensive and fail to fully leverage rapidly growing historical data. In recent years, deep learning methods have made significant progress in weather forecasting, but challenges remain, such as balancing global and regional high-resolution forecasts, excessive smoothing in extreme event predictions, and insufficient dynamic system modeling. To address these issues, this paper proposes a global-regional nested weather forecasting framework based on graph neural networks (GNNs). By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region to capture local high-frequency features. We introduce an adaptive information propagation mechanism, using dynamic gating units to deeply integrate node and edge features for more accurate extreme event forecasting. For high-resolution regional forecasts, we propose a neural nested grid method to mitigate boundary information loss. Experimental results show that the proposed method performs excellently across global to regional scales and short-term to long-term forecasts, especially in extreme event predictions (e.g., typhoons), significantly improving forecast accuracy. Our codes are available at https://github.com/YuanGao-YG/OneForecast.
Machine learning has shown promise in reducing bias in numerical weather model predictions of wind gusts. Yet, they underperform to predict high gusts even with additional observations due to the right-skewed distribution of gusts. Uncertainty quantification (UQ) addresses this by identifying when predictions are reliable or needs cautious interpretation. Using data from 61 extratropical storms in the Northeastern USA, we introduce evidential neural network (ENN) as a novel approach for UQ in gust predictions, leveraging atmospheric variables from the Weather Research and Forecasting (WRF) model as features and gust observations as targets. Explainable artificial intelligence (XAI) techniques demonstrated that key predictive features also contributed to higher uncertainty. Estimated uncertainty correlated with storm intensity and spatial gust gradients. ENN allowed constructing gust prediction intervals without requiring an ensemble. From an operational perspective, providing gust forecasts with quantified uncertainty enhances stakeholders' confidence in risk assessment and response planning for extreme gust events.
The most sensitive direct neutrino mass searches today are based on measurement of the endpoint of the beta spectrum of tritium to infer limits on the mass of the unobserved recoiling neutrino. To avoid the smearing associated with the distribution of molecular final states in the T-He molecule, the next generation of these experiments will need to employ atomic (T) rather than molecular (T$_{2}$) tritium sources. Following production, atomic T can be trapped in gravitational and / or magnetic bottles for beta spectrum experiments, if and only if it can first be cooled to millikelvin temperatures. Accomplishing this cooling presents substantial technological challenges. The Project 8 collaboration is developing a technique based on magnetic evaporative cooling along a beamline (MECB) for the purpose of cooling T to feed a magneto-gravitational trap that also serves as a cyclotron radiation emission spectroscope. Initial tests of the approach are planned in a pathfinder apparatus using atomic Li. This paper presents a method for analyzing the dynamics of the MECB technique, and applies these calculations to the design of systems for cooling and slowing of atomic Li and T. A scheme is outlined that could provide a current of T at the millikelvin temperatures required for the Project 8 neutrino mass search.
We address path-planning for a mobile agent to navigate in an unknown environment with minimum exposure to a spatially and temporally varying threat field. The threat field is estimated using pointwise noisy measurements from a mobile sensor network. For this problem, we present a new information gain measure for optimal sensor placement that quantifies reduction in uncertainty in the path cost rather than the environment state. This measure, which we call the context-relevant mutual information (CRMI), couples the sensor placement and path-planning problem. We propose an iterative coupled sensor configuration and path-planning (CSCP) algorithm. At each iteration, this algorithm places sensors to maximize CRMI, updates the threat estimate using new measurements, and recalculates the path with minimum expected exposure to the threat. The iterations converge when the path cost variance, which is an indicator of risk, reduces below a desired threshold. We show that CRMI is submodular, and therefore, greedy optimization provides near-optimal sensor placements while maintaining computational efficiency of the CSCP algorithm. Distance-based sensor reconfiguration costs are introduced in a modified CRMI measure, which we also show to be submodular. Through numerical simulations, we demonstrate that the principal advantage of this algorithm is that near-optimal low-variance paths are achieved using far fewer sensor measurements as compared to a standard sensor placement method.
Pre-biopsy magnetic resonance imaging (MRI) is increasingly used to target suspicious prostate lesions. This has led to artificial intelligence (AI) applications improving MRI-based detection of clinically significant prostate cancer (CsPCa). However, MRI-detected lesions must still be mapped to transrectal ultrasound (TRUS) images during biopsy, which results in missing CsPCa. This study systematically evaluates a multimodal AI framework integrating MRI and TRUS image sequences to enhance CsPCa identification. The study included 3110 patients from three cohorts across two institutions who underwent prostate biopsy. The proposed framework, based on the 3D UNet architecture, was evaluated on 1700 test cases, comparing performance to unimodal AI models that use either MRI or TRUS alone. Additionally, the proposed model was compared to radiologists in a cohort of 110 patients. The multimodal AI approach achieved superior sensitivity (80%) and Lesion Dice (42%) compared to unimodal MRI (73%, 30%) and TRUS models (49%, 27%). Compared to radiologists, the multimodal model showed higher specificity (88% vs. 78%) and Lesion Dice (38% vs. 33%), with equivalent sensitivity (79%). Our findings demonstrate the potential of multimodal AI to improve CsPCa lesion targeting during biopsy and treatment planning, surpassing current unimodal models and radiologists; ultimately improving outcomes for prostate cancer patients.
Classical planning asks for a sequence of operators reaching a given goal. While the most common case is to compute a plan, many scenarios require more than that. However, quantitative reasoning on the plan space remains mostly unexplored. A fundamental problem is to count plans, which relates to the conditional probability on the plan space. Indeed, qualitative and quantitative approaches are well-established in various other areas of automated reasoning. We present the first study to quantitative and qualitative reasoning on the plan space. In particular, we focus on polynomially bounded plans. On the theoretical side, we study its complexity, which gives rise to rich reasoning modes. Since counting is hard in general, we introduce the easier notion of facets, which enables understanding the significance of operators. On the practical side, we implement quantitative reasoning for planning. Thereby, we transform a planning task into a propositional formula and use knowledge compilation to count different plans. This framework scales well to large plan spaces, while enabling rich reasoning capabilities such as learning pruning functions and explainable planning.
Hand-drawn maps can be used to convey navigation instructions between humans and robots in a natural and efficient manner. However, these maps can often contain inaccuracies such as scale distortions and missing landmarks which present challenges for mobile robot navigation. This paper introduces a novel Hand-drawn Map Navigation (HAM-Nav) architecture that leverages pre-trained vision language models (VLMs) for robot navigation across diverse environments, hand-drawing styles, and robot embodiments, even in the presence of map inaccuracies. HAM-Nav integrates a unique Selective Visual Association Prompting approach for topological map-based position estimation and navigation planning as well as a Predictive Navigation Plan Parser to infer missing landmarks. Extensive experiments were conducted in photorealistic simulated environments, using both wheeled and legged robots, demonstrating the effectiveness of HAM-Nav in terms of navigation success rates and Success weighted by Path Length. Furthermore, a user study in real-world environments highlighted the practical utility of hand-drawn maps for robot navigation as well as successful navigation outcomes.
Traversing rough terrain requires dynamic bipeds to stabilize themselves through foot placement without stepping in unsafe areas. Planning these footsteps online is challenging given non-convexity of the safe terrain, and imperfect perception and state estimation. This paper addresses these challenges with a full-stack perception and control system for achieving underactuated walking on discontinuous terrain. First, we develop model-predictive footstep control (MPFC), a single mixed-integer quadratic program which assumes a convex polygon terrain decomposition to optimize over discrete foothold choice, footstep position, ankle torque, template dynamics, and footstep timing at over 100 Hz. We then propose a novel approach for generating convex polygon terrain decompositions online. Our perception stack decouples safe-terrain classification from fitting planar polygons, generating a temporally consistent terrain segmentation in real time using a single CPU thread. We demonstrate the performance of our perception and control stack through outdoor experiments with the underactuated biped Cassie, achieving state of the art perceptive bipedal walking on discontinuous terrain. Supplemental Video: https://youtu.be/eCOD1bMi638
Coronary artery stenosis, characterized by the narrowing of the lumen, significantly affects blood flow and contributes to the progression of cardiovascular diseases. This study investigates the hemodynamics of coronary artery models with varying stenosis configurations, all maintaining an 80% lumen reduction, to determine how differences in morphology influence flow behavior and mechanical stresses. We employed computational fluid dynamics to analyze five idealized geometries with (10% & 70%), (20% & 60%), (30% & 50%), (40% & 40%), and (0% & 80%) stenosis configurations. Through physiological pulsatile flow conditions, we evaluated key hemodynamic pattern including velocity profiles, wall shear stress, and pressure distribution. Our results reveal that despite the same degree of lumen reduction, each stenosis configuration produced distinct flow patterns and hemodynamic profiles. Asymmetric configurations, such as 10% & 70% and 20% & 60%, exhibited pronounced flow disruptions and higher wall shear stress at the stenosis throats, while symmetric configurations, such as 40% & 40%, demonstrated more uniform flow and reduced vortex. Our findings challenge the practice of generalizing results across stenosis configurations without accounting for morphological variations, which is prevalent in many CFD studies using idealized models. This study emphasizes the importance of considering stenosis-specific morphology in CFD analyses and clinical interpretations to enhance the accuracy of diagnostic tools, improve personalized treatment planning, and guide the design of medical devices such as stents.
In this paper, we develop a new planning method that extends the capabilities of the true online TD to allow an agent to efficiently replay all or part of its past experience, online in the sequence that they appear with, either in each step or sparsely according to the usual {\lambda} parameter. In this new method that we call True Online TD-Replan({\lambda}), the {\lambda} parameter plays a new role in specifying the density of the replay process in addition to the usual role of specifying the depth of the target's updates. We demonstrate that, for problems that benefit from experience replay, our new method outperforms true online TD({\lambda}), albeit quadratic in complexity due to its replay capabilities. In addition, we demonstrate that our method outperforms other methods with similar quadratic complexity such as Dyna Planning and TD({\lambda})-Replan algorithms. We test our method on two benchmarking environments, a random walk problem that uses simple binary features and a myoelectric control domain that uses both simple sEMG features and deeply extracted features to showcase its capabilities.
The rapid and constant increase in urban population has led to a drastic rise in urban solid waste production with worrying consequences for the environment and society. In many cities, an efficient waste management combined with a suitable design of vehicle routes (VR) can lead to benefits in the environmental, economic, and social impacts. The general population is becoming increasingly aware of the need for the separation of the various categories of municipal solid waste. The numerous materials collected include glass, PET or batteries, and electric components, which are sorted at the eco-points. The management of eco-points gives rise to several problems that can be formulated analytically. The location and number of eco-point containers, the determination of the fleet size for picking up the collected waste, and the design of itineraries are all intertwined, and present computationally difficult problems, and therefore must be solved in a sequential way. In this paper, a mathematical model has been formulated, based on the Bin Packing (BP) and VR schemes, for the deployment of routes of mobile containers in the selective collection of urban solid waste. A heuristic algorithm has also been developed, which considers two different configurations of the containers to solve the proposed mathematical programming model. The results obtained from the numerical simulations show the validation of the proposed methodology carried out for the benchmark of the Sioux Falls network and the specific real case study.
Purpose: We present a virtual model to optimize point of entry (POE) in lung biopsy planning systems. Our model allows to compute the quality of a biopsy sample taken from potential POE, taking into account the margin of error that arises from discrepancies between the orientation in the planning simulation and the actual orientation during the operation. Additionally, the study examines the impact of the characteristics of the lesion. Methods: The quality of the biopsy is given by a heatmap projected onto the skeleton of a patient-specific model of airways. The skeleton provides a 3D representation of airways structure, while the heatmap intensity represents the potential amount of tissue that it could be extracted from each POE. This amount of tissue is determined by the intersection of the lesion with a cone that represents the uncertainty area in the introduction of biopsy instruments. The cone, lesion, and skeleton are modelled as graphical objects that define a 3D scene of the intervention. Results: We have simulated different settings of the intervention scene from a single anatomy extracted from a CT scan and two lesions with regular and irregular shapes. The different scenarios are simulated by systematic rotation of each lesion placed at different distances from airways. Analysis of the heatmaps for the different settings show a strong impact of lesion orientation for irregular shape and the distance for both shapes. Conclusion: The proposed heatmaps help to visually assess the optimal POE and identify whether multiple optimal POEs exist in different zones of the bronchi. They also allow us to model the maximum allowable error in navigation systems and study which variables have the greatest influence on the success of the operation. Additionally, they help determine at what point this influence could potentially jeopardize the operation.
Full-stack autonomous driving system spans diverse technological domains-including perception, planning, and control-that each require in-depth research. Moreover, validating such technologies of the system necessitates extensive supporting infrastructure, from simulators and sensors to high-definition maps. These complexities with barrier to entry pose substantial limitations for individual developers and research groups. Recently, open-source autonomous driving software platforms have emerged to address this challenge by providing autonomous driving technologies and practical supporting infrastructure for implementing and evaluating autonomous driving functionalities. Among the prominent open-source platforms, Autoware and Apollo are frequently adopted in both academia and industry. While previous studies have assessed each platform independently, few have offered a quantitative and detailed head-to-head comparison of their capabilities. In this paper, we systematically examine the core modules of Autoware and Apollo and evaluate their middleware performance to highlight key differences. These insights serve as a practical reference for researchers and engineers, guiding them in selecting the most suitable platform for their specific development environments and advancing the field of full-stack autonomous driving system.
Air pollution (AP) poses a great threat to human health, and people are paying more attention than ever to its prediction. Accurate prediction of AP helps people to plan for their outdoor activities and aids protecting human health. In this paper, long-short term memory (LSTM) recurrent neural networks (RNNs) have been used to predict the future concentration of air pollutants (APS) in Macau. Additionally, meteorological data and data on the concentration of APS have been utilized. Moreover, in Macau, some air quality monitoring stations (AQMSs) have less observed data in quantity, and, at the same time, some AQMSs recorded less observed data of certain types of APS. Therefore, the transfer learning and pre-trained neural networks have been employed to assist AQMSs with less observed data to build a neural network with high prediction accuracy. The experimental sample covers a period longer than 12-year and includes daily measurements from several APS as well as other more classical meteorological values. Records from five stations, four out of them are AQMSs and the remaining one is an automatic weather station, have been prepared from the aforesaid period and eventually underwent to computational intelligence techniques to build and extract a prediction knowledge-based system. As shown by experimentation, LSTM RNNs initialized with transfer learning methods have higher prediction accuracy; it incurred shorter training time than randomly initialized recurrent neural networks.
Quadrotors can carry slung loads to hard-to-reach locations at high speed. Since a single quadrotor has limited payload capacities, using a team of quadrotors to collaboratively manipulate a heavy object is a scalable and promising solution. However, existing control algorithms for multi-lifting systems only enable low-speed and low-acceleration operations due to the complex dynamic coupling between quadrotors and the load, limiting their use in time-critical missions such as search and rescue. In this work, we present a solution to significantly enhance the agility of cable-suspended multi-lifting systems. Unlike traditional cascaded solutions, we introduce a trajectory-based framework that solves the whole-body kinodynamic motion planning problem online, accounting for the dynamic coupling effects and constraints between the quadrotors and the load. The planned trajectory is provided to the quadrotors as a reference in a receding-horizon fashion and is tracked by an onboard controller that observes and compensates for the cable tension. Real-world experiments demonstrate that our framework can achieve at least eight times greater acceleration than state-of-the-art methods to follow agile trajectories. Our method can even perform complex maneuvers such as flying through narrow passages at high speed. Additionally, it exhibits high robustness against load uncertainties and does not require adding any sensors to the load, demonstrating strong practicality.
The rapid development of digital stages has greatly compounded the dispersal of untrue data, dissolving certainty and judgment in society, especially among the Bengali-speaking community. Our ponder addresses this critical issue by presenting an interesting strategy that utilizes a profound learning innovation, particularly the Gated Repetitive Unit (GRU), to recognize fake news within the Bangla dialect. The strategy of our proposed work incorporates intensive information preprocessing, which includes lemmatization, tokenization, and tending to course awkward nature by oversampling. This comes about in a dataset containing 58,478 passages. We appreciate the creation of a demonstration based on GRU (Gated Repetitive Unit) that illustrates remarkable execution with a noteworthy precision rate of 94%. This ponder gives an intensive clarification of the methods included in planning the information, selecting the show, preparing it, and assessing its execution. The performance of the model is investigated by reliable metrics like precision, recall, F1 score, and accuracy. The commitment of the work incorporates making a huge fake news dataset in Bangla and a demonstration that has outperformed other Bangla fake news location models.
A cuspidal robot can move from one inverse kinematics (IK) solution to another without crossing a singularity. Multiple industrial robots are cuspidal. They tend to have a beautiful mechanical design, but they pose path planning challenges. A task-space path may have a valid IK solution for each point along the path, but a continuous joint-space path may depend on the choice of the IK solution or even be infeasible. This paper presents new analysis, path planning, and optimization methods to enhance the utility of cuspidal robots. We first demonstrate an efficient method to identify cuspidal robots and show, for the first time, that the ABB GoFa and certain robots with three parallel joint axes are cuspidal. We then propose a new path planning method for cuspidal robots by finding all IK solutions for each point along a task-space path and constructing a graph to connect each vertex corresponding to an IK solution. Graph edges are weighted based on the optimization metric, such as minimizing joint velocity. The optimal feasible path is the shortest path in the graph. This method can find non-singular paths as well as smooth paths which pass through singularities. Finally, this path planning method is incorporated into a path optimization algorithm. Given a fixed workspace toolpath, we optimize the offset of the toolpath in the robot base frame while ensuring continuous joint motion. Code examples are available in a publicly accessible repository.
Purpose: VT is a life-threatening arrhythmia commonly treated with catheter ablation; however, some cases remain refractory to conventional treatment. STAR has emerged as a non-invasive option for such patients. While photon-based STAR has shown efficacy, proton therapy offers potential advantages due to its superior dose conformity and sparing of critical OARs, including the heart itself. This study aims to investigate and compare the dosimetry between proton and photon therapy for VT, focusing on target coverage and OAR sparing. Methods: We performed a retrospective study on a cohort of 34 VT patients who received photon STAR. Proton STAR plans were generated using robust optimization in RayStation to deliver the same prescription dose of 25 Gy in a single fraction while minimizing dose to OARs. Dosimetric metrics, including D99, D95, Dmean, and D0.03cc, were extracted for critical OARs and VAS. Shapiro-Wilk tests were used to assess normality, followed by paired t-tests or Wilcoxon signed-rank tests for statistical comparisons between modalities, with Bonferroni correction applied for multiple comparisons. Results: Proton and photon plans achieved comparable target coverage, with VAS D95 of 24.1 +/- 1.2 Gy vs. 24.7 +/- 1.0 Gy (p=0.294). Proton therapy significantly reduced OAR doses, including heart Dmean (3.6 +/- 1.5 Gy vs. 5.5 +/- 2.0 Gy, p<0.001), lungs Dmean (1.6 +/- 1.5 Gy vs. 2.1 +/- 1.4 Gy, p<0.001), and esophagus Dmean (0.3 +/- 0.6 Gy vs. 1.6 +/- 1.3 Gy, p<0.001), while maintaining optimal target coverage. Conclusion: Proton therapy for STAR demonstrates significant dosimetric advantages in sparing the heart and other critical OARs compared to photon therapy for VT, while maintaining equivalent target coverage. These findings highlight the potential of proton therapy to reduce treatment-related toxicity and improve outcomes for VT patients.
This paper presents a novel hybrid approach to solving real-world drone routing problems by leveraging the capabilities of quantum computing. The proposed method, coined Quantum for Drone Routing (Q4DR), integrates the two most prominent paradigms in the field: quantum gate-based computing, through the Eclipse Qrisp programming language; and quantum annealers, by means of D-Wave System's devices. The algorithm is divided into two different phases: an initial clustering phase executed using a Quantum Approximate Optimization Algorithm (QAOA), and a routing phase employing quantum annealers. The efficacy of Q4DR is demonstrated through three use cases of increasing complexity, each incorporating real-world constraints such as asymmetric costs, forbidden paths, and itinerant charging points. This research contributes to the growing body of work in quantum optimization, showcasing the practical applications of quantum computing in logistics and route planning.
Modern science emerged from reasoning over repeatedly-observed planetary motions. We present Gravity-Bench-v1, an environment-based benchmark that challenges AI agents on tasks that parallel this historical development. Gravity-Bench-v1 evaluates agents on the discovery of physics concealed within a dynamic environment, using rigorous gravitational dynamics simulations. Gravity-Bench includes out-of-distribution cases, i.e. with physics that deviates from the real world, to evaluate true scientific generalization capabilities. Agents must plan to collect data within an experimental budget and must perform a dynamic form of data analysis and reasoning to solve tasks efficiently. Our benchmark admits an open-ended space of solutions. PhD-level solutions for each task are provided, to calibrate AI performance against human expertise. Technically at an upper-undergraduate level, our benchmark proves challenging to baseline AI agents. Gravity-Bench-v1 and planned extensions should help map out AI progress towards scientific discovery capabilities.
Cluster-randomized trials (CRTs) are a well-established class of designs for evaluating large-scale, community-based research questions. An essential task in planning these trials is determining the required number of clusters and cluster sizes to achieve sufficient statistical power for detecting a clinically relevant effect size. Compared to methods for evaluating the average treatment effect (ATE) for the entire study population, there is more recent development of sample size methods for testing the heterogeneity of treatment effects (HTEs), i.e., modification of treatment effects by subpopulation characteristics, in CRTs. For confirmatory analyses of HTEs in CRTs, effect modifiers must be pre-specified, and ideally, accompanied by sample size or power calculations to ensure the trial has adequate power for the planned analyses. Power analysis for HTE analyses is more complex than for ATEs due to the additional design parameters that must be specified. Power and sample size formulas for HTE analyses have been separately derived under several cluster-randomized designs, including single and multi-period parallel designs, crossover designs, and stepped-wedge designs, as well as under continuous and binary outcomes. This tutorial provides a consolidated reference guide for these methods and enhances their accessibility through the development of an online R Shiny calculator. We further discuss key considerations for researchers conducting sample size and power calculations for testing pre-specified HTE hypotheses in CRTs, including the essential role of advance estimates of intracluster correlation coefficients for both outcomes and covariates on power. The sample size methodology and calculator functionality are demonstrated through real CRT examples.
Path planning with strong environmental adaptability plays a crucial role in robotic navigation in unstructured outdoor environments, especially in the case of low-quality location and map information. The path planning ability of a robot depends on the identification of the traversability of global and local ground areas. In real-world scenarios, the complexity of outdoor open environments makes it difficult for robots to identify the traversability of ground areas that lack a clearly defined structure. Moreover, most existing methods have rarely analyzed the integration of local and global traversability identifications in unstructured outdoor scenarios. To address this problem, we propose a novel method, Dual-BEV Nav, first introducing Bird's Eye View (BEV) representations into local planning to generate high-quality traversable paths. Then, these paths are projected onto the global traversability map generated by the global BEV planning model to obtain the optimal waypoints. By integrating the traversability from both local and global BEV, we establish a dual-layer BEV heuristic planning paradigm, enabling long-distance navigation in unstructured outdoor environments. We test our approach through both public dataset evaluations and real-world robot deployments, yielding promising results. Compared to baselines, the Dual-BEV Nav improved temporal distance prediction accuracy by up to $18.7\%$. In the real-world deployment, under conditions significantly different from the training set and with notable occlusions in the global BEV, the Dual-BEV Nav successfully achieved a 65-meter-long outdoor navigation. Further analysis demonstrates that the local BEV representation significantly enhances the rationality of the planning, while the global BEV probability map ensures the robustness of the overall planning.
This paper argues that model-free reinforcement learning (RL) agents, while lacking explicit planning mechanisms, exhibit behaviours that can be analogised to System 1 ("thinking fast") processes in human cognition. Unlike model-based RL agents, which operate akin to System 2 ("thinking slow") reasoning by leveraging internal representations for planning, model-free agents react to environmental stimuli without anticipatory modelling. We propose a novel framework linking the dichotomy of System 1 and System 2 to the distinction between model-free and model-based RL. This framing challenges the prevailing assumption that intentionality and purposeful behaviour require planning, suggesting instead that intentionality can manifest in the structured, reactive behaviours of model-free agents. By drawing on interdisciplinary insights from cognitive psychology, legal theory, and experimental jurisprudence, we explore the implications of this perspective for attributing responsibility and ensuring AI safety. These insights advocate for a broader, contextually informed interpretation of intentionality in RL systems, with implications for their ethical deployment and regulation.
The complexity of multi-layered, data-intensive systems demands frameworks that ensure flexibility, scalability, and efficiency. DATCloud is a model-driven framework designed to facilitate the modeling, validation, and refinement of multi-layered architectures, addressing scalability, modularity, and real-world requirements. By adhering to ISO/IEC/IEEE 42010 standards, DATCloud leverages structural and behavioral meta-models and graphical domain-specific languages (DSLs) to enhance reusability and stakeholder communication. Initial validation through the VASARI system at the Uffizi Gallery demonstrates a 40% reduction in modeling time and a 32% improvement in flexibility compared to manual methods. While effective, DATCloud is a work in progress, with plans to integrate advanced code generation, simulation tools, and domain-specific extensions to further enhance its capabilities for applications in healthcare, smart cities, and other data-intensive domains.
Rapid progress in text-to-motion generation has been largely driven by diffusion models. However, existing methods focus solely on temporal modeling, thereby overlooking frequency-domain analysis. We identify two key phases in motion denoising: the **semantic planning stage** and the **fine-grained improving stage**. To address these phases effectively, we propose **Fre**quency **e**nhanced **t**ext-**to**-**m**otion diffusion model (**Free-T2M**), incorporating stage-specific consistency losses that enhance the robustness of static features and improve fine-grained accuracy. Extensive experiments demonstrate the effectiveness of our method. Specifically, on StableMoFusion, our method reduces the FID from **0.189** to **0.051**, establishing a new SOTA performance within the diffusion architecture. These findings highlight the importance of incorporating frequency-domain insights into text-to-motion generation for more precise and robust results.
Diffusion-based motion planners are becoming popular due to their well-established performance improvements, stemming from sample diversity and the ease of incorporating new constraints directly during inference. However, a primary limitation of the diffusion process is the requirement for a substantial number of denoising steps, especially when the denoising process is coupled with gradient-based guidance. In this paper, we introduce, diffusion in the parametric space of trajectories, where the parameters are represented as Bernstein coefficients. We show that this representation greatly improves the effectiveness of the cost function guidance and the inference speed. We also introduce a novel stitching algorithm that leverages the diversity in diffusion-generated trajectories to produce collision-free trajectories with just a single cost function-guided model. We demonstrate that our approaches outperform current SOTA diffusion-based motion planners for manipulators and provide an ablation study on key components.
We present an iterative approach for planning and controlling motions of underactuated robots with uncertain dynamics. At its core, there is a learning process which estimates the perturbations induced by the model uncertainty on the active and passive degrees of freedom. The generic iteration of the algorithm makes use of the learned data in both the planning phase, which is based on optimization, and the control phase, where partial feedback linearization of the active dofs is performed on the model updated on-line. The performance of the proposed approach is shown by comparative simulations and experiments on a Pendubot executing various types of swing-up maneuvers. Very few iterations are typically needed to generate dynamically feasible trajectories and the tracking control that guarantees their accurate execution, even in the presence of large model uncertainties.
Purpose: To investigate the impact of delivery techniques and planning parameters on interplay effect in lung SBRT. Methods: A dynamic virtual patient model containing normal structures and a tumor with adjustable sizes, locations, and 3D breathing motion was utilized. SBRT plans were developed using both step-and-shoot IMRT and VMAT with different planning parameters (energy, isocenter location, PTV margin, and PTV dose heterogeneity). 4D doses were calculated by simulating synchronized delivery of SBRT to the virtual patient model with random initial positions of tumor motion. The expected dose (average) and the standard deviation of the 4D doses were obtained. The relative difference between the expected GTV minimal/mean (GTVMin/GTVMean) dose and the planned ITVMin/ITVMean dose (denoted by %E/P), and between the GTVMin and the prescription dose (DRx) were computed. Results: The %E/P for GTVMean was significantly lower for IMRT than VMAT (0.5% +/- 7.7% v.s. 3.5% +/- 5.0%, p=0.04). The expected GTVMin was lower than DRx in 9.4% of all IMRT plans versus 3.1% in VMAT. The worst-case scenario, 4D GTVMin was 14.1% lower than the ITVMin. Choices of PTV margin or dose heterogeneity to be achieved in PTV can result in significant difference (p<0.05) in motion interplay depending on delivery techniques. Conclusion: Motion interplay may cause the expected GTVMin to be less than the planned ITV minimal dose and DRx for both IMRT and VMAT plans. The differences between the expected GTV dose and the ITV dose depended on the delivery technique and planning parameters. Overall, VMAT is less prone to motion interplay than IMRT.
Large language models based Multi Agent Systems (MAS) have demonstrated promising performance for enhancing the efficiency and accuracy of code generation tasks. However,most existing methods follow a conventional sequence of planning, coding, and debugging,which contradicts the growth-driven nature of human learning process. Additionally,the frequent information interaction between multiple agents inevitably involves high computational costs. In this paper,we propose Cogito,a neurobiologically inspired multi-agent framework to enhance the problem-solving capabilities in code generation tasks with lower cost. Specifically,Cogito adopts a reverse sequence: it first undergoes debugging, then coding,and finally planning. This approach mimics human learning and development,where knowledge is acquired progressively. Accordingly,a hippocampus-like memory module with different functions is designed to work with the pipeline to provide quick retrieval in similar tasks. Through this growth-based learning model,Cogito accumulates knowledge and cognitive skills at each stage,ultimately forming a Super Role an all capable agent to perform the code generation task. Extensive experiments against representative baselines demonstrate the superior performance and efficiency of Cogito. The code is publicly available at https://anonymous.4open.science/r/Cogito-0083.
In complex manipulation tasks, e.g., manipulation by pivoting, the motion of the object being manipulated has to satisfy path constraints that can change during the motion. Therefore, a single grasp may not be sufficient for the entire path, and the object may need to be regrasped. Additionally, geometric data for objects from a sensor are usually available in the form of point clouds. The problem of computing grasps and regrasps from point-cloud representation of objects for complex manipulation tasks is a key problem in endowing robots with manipulation capabilities beyond pick-and-place. In this paper, we formalize the problem of grasping/regrasping for complex manipulation tasks with objects represented by (partial) point clouds and present an algorithm to solve it. We represent a complex manipulation task as a sequence of constant screw motions. Using a manipulation plan skeleton as a sequence of constant screw motions, we use a grasp metric to find graspable regions on the object for every constant screw segment. The overlap of the graspable regions for contiguous screws are then used to determine when and how many times the object needs to be regrasped. We present experimental results on point cloud data collected from RGB-D sensors to illustrate our approach.
We would like a robot to navigate to a goal location while minimizing state uncertainty. To aid the robot in this endeavor, maps provide a prior belief over the location of objects and regions of interest. To localize itself within the map, a robot identifies mapped landmarks using its sensors. However, as the time between map creation and robot deployment increases, portions of the map can become stale, and landmarks, once believed to be permanent, may disappear. We refer to the propensity of a landmark to disappear as landmark evanescence. Reasoning about landmark evanescence during path planning, and the associated impact on localization accuracy, requires analyzing the presence or absence of each landmark, leading to an exponential number of possible outcomes of a given motion plan. To address this complexity, we develop BRULE, an extension of the Belief Roadmap. During planning, we replace the belief over future robot poses with a Gaussian mixture which is able to capture the effects of landmark evanescence. Furthermore, we show that belief updates can be made efficient, and that maintaining a random subset of mixture components is sufficient to find high quality solutions. We demonstrate performance in simulated and real-world experiments. Software is available at https://bit.ly/BRULE.
This paper presents a new trajectory replanner for grasping irregular objects. Unlike conventional grasping tasks where the object's geometry is assumed simple, we aim to achieve a "dynamic grasp" of the irregular objects, which requires continuous adjustment during the grasping process. To effectively handle irregular objects, we propose a trajectory optimization framework that comprises two phases. Firstly, in a specified time limit of 10s, initial offline trajectories are computed for a seamless motion from an initial configuration of the robot to grasp the object and deliver it to a pre-defined target location. Secondly, fast online trajectory optimization is implemented to update robot trajectories in real-time within 100 ms. This helps to mitigate pose estimation errors from the vision system. To account for model inaccuracies, disturbances, and other non-modeled effects, trajectory tracking controllers for both the robot and the gripper are implemented to execute the optimal trajectories from the proposed framework. The intensive experimental results effectively demonstrate the performance of our trajectory planning framework in both simulation and real-world scenarios.
Soft-growing robots (i.e., vine robots) are a promising class of soft robots that allow for navigation and growth in tightly confined environments. However, these robots remain challenging to model and control due to the complex interplay of the inflated structure and inextensible materials, which leads to obstacles for autonomous operation and design optimization. Although there exist simulators for these systems that have achieved qualitative and quantitative success in matching high-level behavior, they still often fail to capture realistic vine robot shapes using simplified parameter models and have difficulties in high-throughput simulation necessary for planning and parameter optimization. We propose a differentiable simulator for these systems, enabling the use of the simulator "in-the-loop" of gradient-based optimization approaches to address the issues listed above. With the more complex parameter fitting made possible by this approach, we experimentally validate and integrate a closed-form nonlinear stiffness model for thin-walled inflated tubes based on a first-principles approach to local material wrinkling. Our simulator also takes advantage of data-parallel operations by leveraging existing differentiable computation frameworks, allowing multiple simultaneous rollouts. We demonstrate the feasibility of using a physics-grounded nonlinear stiffness model within our simulator, and how it can be an effective tool in sim-to-real transfer. We provide our implementation open source.
One of the primary objectives of the SPHEREx mission is to understand the origin of molecules such as H2O, CO2, and other volatile compounds at the early stages of planetary system formation. Because the vast majority of these compounds -- typically exceeding 95% -- exist in the solid phase rather than the gaseous phase in the systems of concern here, the observing strategy planned to characterize them is slightly unusual. Specifically, SPHEREx will target highly obscured sources throughout the Milky Way, and observe the species of concern in absorption against background illumination. SPHEREx spectrophotometry will yield ice column density measurements for millions of obscured Milky Way sources of all ages and types. By correlating those column densities with source ages, the SPHEREx mission will shed light on whether those molecules were formed in situ along with their nascent stellar systems, or whether instead they formed elsewhere and were introduced into those systems after their formation. To that end, this work describes version 7$.$1 of the SPHEREx Target List of Ice Sources (SPLICES) for the community. It contains about 8$.$6 million objects brighter than W2~12 Vega mag over much of the sky, principally within a broad strip running the length of the Milky Way midplane, but also within high-latitude molecular clouds and even the Magellanic Clouds.
Transportation plays a critical role in supply chain networks, directly impacting cost efficiency, delivery reliability, and environmental sustainability. This study provides an enhanced optimization model for transportation planning, emphasizing environmental sustainability and cost-efficiency. An Integer Linear Programming (ILP) model was developed to minimize the total transportation costs by considering organizational and third-party vehicles' operational and rental costs while incorporating constraints on carbon emissions. The model incorporates multi-modal transportation routing and emission caps to select the optimized number of organizational and rental vehicles of different modes in each route to ensure adherence to sustainability goals. Key innovations include adding carbon emission constraints and optimizing route selection to reduce overall emissions. The model was implemented using the Gurobi solver, and numerical analysis reveals a trade-off between cost minimization and carbon footprint reduction. The results indicate that adopting tight environmental policies increases the costs by around 8% on average while more than 95% of the vehicles utilized will be rented. These insights provide actionable guidance for industries aiming to enhance both economic performance and environmental responsibility.
As industries increasingly adopt large robotic fleets, there is a pressing need for computationally efficient, practical, and optimal conflict-free path planning for multiple robots. Conflict-Based Search (CBS) is a popular method for multi-agent path finding (MAPF) due to its completeness and optimality; however, it is often impractical for real-world applications, as it is computationally intensive to solve and relies on assumptions about agents and operating environments that are difficult to realize. This article proposes a solution to overcome computational challenges and practicality issues of CBS by utilizing structural-semantic topometric maps. Instead of running CBS over large grid-based maps, the proposed solution runs CBS over a sparse topometric map containing structural-semantic cells representing intersections, pathways, and dead ends. This approach significantly accelerates the MAPF process and reduces the number of conflict resolutions handled by CBS while operating in continuous time. In the proposed method, robots are assigned time ranges to move between topometric regions, departing from the traditional CBS assumption that a robot can move to any connected cell in a single time step. The approach is validated through real-world multi-robot path-finding experiments and benchmarking simulations. The results demonstrate that the proposed MAPF method can be applied to real-world non-holonomic robots and yields significant improvement in computational efficiency compared to traditional CBS methods while improving conflict detection and resolution in cases of corridor symmetries.
The contributions of this short technical note are two-fold. Firstly, we introduce a modified version of a generalized Bellman-Ford algorithm calculating the value function of optimal control problems defined on hyper-graphs. Those Bellman-Ford algorithms can be used in particular for the synthesis of near-optimal controllers by the principle of symbolic control. Our modification causes less nodes of the hyper-graph being iterated during the execution compared to our initial version of the algorithm published in 2020. Our second contribution lies in the field of Plan recognition applied to drone missions driven by symbolic controllers. We address and resolve the Plan and Goal Recognition monitor's dependence on a pre-defined initial guess for a drone's task allocation and mission execution. To validate the enhanced implementation, we use a more challenging scenario for UAV-based aerial firefighting, demonstrating the practical applicability and robustness of the system architecture.
We present a massively parallel solver that accelerates DC loadflow computations for power grid topology optimization tasks. Our approach leverages low-rank updates of the Power Transfer Distribution Factors (PTDFs) to represent substation splits, line outages, and reconfigurations without ever refactorizing the system. Furthermore, we implement the core routines on Graphics Processing Units (GPUs), thereby exploiting their high-throughput architecture for linear algebra. A two-level decomposition separates changes in branch topology from changes in nodal injections, enabling additional speed-ups by an in-the-loop brute force search over injection variations at minimal additional cost. We demonstrate billion-loadflow-per-second performance on power grids of varying sizes in workload settings which are typical for gradient-free topology optimization such as Reinforcement Learning or Quality Diversity methods. While adopting the DC approximation sacrifices some accuracy and prohibits the computation of voltage magnitudes, we show that this sacrifice unlocks new scales of computational feasibility, offering a powerful tool for large-scale grid planning and operational topology optimization.
We present a method for solving a large-scale stochastic capacity expansion problem which explicitly considers reliability constraints, in particular constraints on expected energy not served. Our method tackles this problem by a Lagrange relaxation of the expected energy not served constraints. We solve the relaxed formulation in an iterative manner, using a subgradient-based method. Each iteration requires the solution of a stochastic capacity expansion problem, for which we implement a subgradient decomposition scheme in a high-performance computing infrastructure. We apply the proposed methodology on the Economic Viability Assessment model that is used by ENTSO-E in the annual European Resource Adequacy Assessment, extended to include explicit reliability constraints. The approach is able to solve this model achieving a 1.3% optimality gap. We compare our approach against accounting for reliability through penalizing load shedding at VOLL, and find that the former results in 1.6% savings in total cost. We are also able to quantify the cost savings from allowing some load curtailment in the capacity planning process, which ranges from 1.6 to 6% in the cases analyzed.
Construction robotics increasingly relies on natural language processing for task execution, creating a need for robust methods to interpret commands in complex, dynamic environments. While existing research primarily focuses on what tasks robots should perform, less attention has been paid to how these tasks should be executed safely and efficiently. This paper presents a novel probabilistic framework that uses sentiment analysis from natural language commands to dynamically adjust robot navigation policies in construction environments. The framework leverages Building Information Modeling (BIM) data and natural language prompts to create adaptive navigation strategies that account for varying levels of environmental risk and uncertainty. We introduce an object-aware path planning approach that combines exponential potential fields with a grid-based representation of the environment, where the potential fields are dynamically adjusted based on the semantic analysis of user prompts. The framework employs Bayesian inference to consolidate multiple information sources: the static data from BIM, the semantic content of natural language commands, and the implied safety constraints from user prompts. We demonstrate our approach through experiments comparing three scenarios: baseline shortest-path planning, safety-oriented navigation, and risk-aware routing. Results show that our method successfully adapts path planning based on natural language sentiment, achieving a 50\% improvement in minimum distance to obstacles when safety is prioritized, while maintaining reasonable path lengths. Scenarios with contrasting prompts, such as "dangerous" and "safe", demonstrate the framework's ability to modify paths. This approach provides a flexible foundation for integrating human knowledge and safety considerations into construction robot navigation.
In recent years, there has been a growing interest in using machine learning (ML) in query optimization to select more efficient plans. Existing learning-based query optimizers use certain model architectures to convert tree-structured query plans into representations suitable for downstream ML tasks. As the design of these architectures significantly impacts cost estimation, we propose a tree model architecture based on Bidirectional Graph Neural Networks (Bi-GNN) aggregated by Gated Recurrent Units (GRUs) to achieve more accurate cost estimates. The inherent uncertainty of data and model parameters also leads to inaccurate cost estimates, resulting in suboptimal plans and less robust query performance. To address this, we implement a novel learning-to-rank cost model that effectively quantifies the uncertainty in cost estimates using approximate probabilistic ML. This model adaptively integrates quantified uncertainty with estimated costs and learns from comparing pairwise plans, achieving more robust performance. In addition, we propose the first explainability technique specifically designed for learning-based cost models. This technique explains the contribution of any subgraphs in the query plan to the final predicted cost, which can be integrated and trained with any learning-based cost model to significantly boost the model's explainability. By incorporating these innovations, we propose a cost model for a Robust and Explainable Query Optimizer, Reqo, that improves the accuracy, robustness, and explainability of cost estimation, outperforming state-of-the-art approaches in all three dimensions.
Rationale and Objectives: Early prediction of pathological complete response (pCR) can facilitate personalized treatment for breast cancer patients. To improve prediction accuracy at the early time point of neoadjuvant chemotherapy, we proposed a two-stage dual-task learning strategy to train a deep neural network for early prediction of pCR using early-treatment magnetic resonance images. Methods: We developed and validated the two-stage dual-task learning strategy using the dataset from the national-wide, multi-institutional I-SPY2 clinical trial, which included dynamic contrast-enhanced magnetic resonance images acquired at three time points: pretreatment (T0), after 3 weeks (T1), and after 12 weeks of treatment (T2). First, we trained a convolutional long short-term memory network to predict pCR and extract the latent space image features at T2. At the second stage, we trained a dual-task network to simultaneously predict pCR and the image features at T2 using images from T0 and T1. This allowed us to predict pCR earlier without using images from T2. Results: The conventional single-stage single-task strategy gave an area under the receiver operating characteristic curve (AUROC) of 0.799 for pCR prediction using all the data at time points T0 and T1. By using the proposed two-stage dual-task learning strategy, the AUROC was improved to 0.820. Conclusions: The proposed two-stage dual-task learning strategy can improve model performance significantly (p=0.0025) for predicting pCR at the early stage (3rd week) of neoadjuvant chemotherapy. The early prediction model can potentially help physicians to intervene early and develop personalized plans at the early stage of chemotherapy.
Deep learning models for autonomous driving, encompassing perception, planning, and control, depend on vast datasets to achieve their high performance. However, their generalization often suffers due to domain-specific data distributions, making an effective scene-based categorization of samples necessary to improve their reliability across diverse domains. Manual captioning, though valuable, is both labor-intensive and time-consuming, creating a bottleneck in the data annotation process. Large Visual Language Models (LVLMs) present a compelling solution by automating image analysis and categorization through contextual queries, often without requiring retraining for new categories. In this study, we evaluate the capabilities of LVLMs, including GPT-4 and LLaVA, to understand and classify urban traffic scenes on both an in-house dataset and the BDD100K. We propose a scalable captioning pipeline that integrates state-of-the-art models, enabling a flexible deployment on new datasets. Our analysis, combining quantitative metrics with qualitative insights, demonstrates the effectiveness of LVLMs to understand urban traffic scenarios and highlights their potential as an efficient tool for data-driven advancements in autonomous driving.
Eclipses and pulsations are the two primary ways in which the physical properties of stars can be deduced and used to improve our understanding of stellar theory. An obvious idea is to combine these two analyses into the study of pulsating stars in eclipsing binaries. This is the aim of the SWIPE project. This paper summarises the scientific arguments, current status and future plans of the project.
Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure, and inability to learn continually. We present the initial design for an AI system, Agential AI (AAI), in principle operating independently or on top of statistical methods, designed to overcome these issues. AAI's core is a learning method that models temporal dynamics with guarantees of completeness, minimality, and continual learning, using component-level variation and selection to learn the structure of the environment. It integrates this with a behavior algorithm that plans on a learned model and encapsulates high-level behavior patterns. Preliminary experiments on a simple environment show AAI's effectiveness and potential.
Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated model errors during these rollouts can distort the data distribution, negatively impacting policy learning and hindering long-term planning. Thus, the accumulation of model errors is a key bottleneck in current MBRL methods. We propose Infoprop, a model-based rollout mechanism that separates aleatoric from epistemic model uncertainty and reduces the influence of the latter on the data distribution. Further, Infoprop keeps track of accumulated model errors along a model rollout and provides termination criteria to limit data corruption. We demonstrate the capabilities of Infoprop in the Infoprop-Dyna algorithm, reporting state-of-the-art performance in Dyna-style MBRL on common MuJoCo benchmark tasks while substantially increasing rollout length and data quality.
In the last years the pervasive use of sensors, as they exist in smart devices, e.g., phones, watches, medical devices, has increased dramatically the availability of personal data. However, existing research on data collection primarily focuses on the objective view of reality, as provided, for instance, by sensors, often neglecting the integration of subjective human input, as provided, for instance, by user answers to questionnaires. This limits substantially the exploitability of the collected data. In this paper we present a methodology and a platform specifically designed for the collection of a combination of large-scale sensor data and qualitative human feedback. The methodology has been designed to be deployed on top, and enriches the functionalities of, an existing data collection APP, called iLog, which has been used in large scale, worldwide data collection experiments. The main goal is to put the key actors involved in an experiment, i.e., the researcher in charge, the participant, and iLog in better control of the experiment itself, thus enabling a much improved quality and richness of the data collected. The novel functionalities of the resulting platform are: (i) a time-wise representation of the situational context within which the data collection is performed, (ii) an explicit representation of the temporal context within which the data collection is performed, (iii) a calendar-based dashboard for the real-time monitoring of the data collection context(s), and, finally, (iv) a mechanism for the run-time revision of the data collection plan. The practicality and utility of the proposed functionalities are demonstrated by showing how they apply to a case study involving 350 University students.
Among generative neural models, flow matching techniques stand out for their simple applicability and good scaling properties. Here, velocity fields of curves connecting a simple latent and a target distribution are learned. Then the corresponding ordinary differential equation can be used to sample from a target distribution, starting in samples from the latent one. This paper reviews from a mathematical point of view different techniques to learn the velocity fields of absolutely continuous curves in the Wasserstein geometry. We show how the velocity fields can be characterized and learned via i) transport plans (couplings) between latent and target distributions, ii) Markov kernels and iii) stochastic processes, where the latter two include the coupling approach, but are in general broader. Besides this main goal, we show how flow matching can be used for solving Bayesian inverse problems, where the definition of conditional Wasserstein distances plays a central role. Finally, we briefly address continuous normalizing flows and score matching techniques, which approach the learning of velocity fields of curves from other directions.
We conducted observing system simulation experiments (OSSEs) for radio occultation measurements (RO) among small satellites, which are expected to be useful for future Venus missions. The effectiveness of the observations based on realistic orbit calculations was evaluated by reproduction of the "cold collar", a unique thermal structure in the polar atmosphere of Venus. Pseudo-temperature observations for the OSSEs were provided from the Venus atmospheric GCM in which the cold collar was reproduced by the thermal forcing. The vertical temperature distributions between 40 and 90 km altitudes at observation points were assimilated. The result showed that the cold collar was most clearly reproduced in the case where the temperature field in high-latitudes was observed twice a day, suggesting that the proposed observation is quite effective to improve the polar atmospheric structure at least. Although the cold collar was also reproduced in the OSSEs for Longwave Infrared Camera (LIR) observations, the result seemed unrealistic and inefficient compared to that obtained in the RO OSSEs. The present study shows that the OSSEs can be used to evaluate observation plans and instruments in terms of reproducibility of specific atmospheric phenomena, and applied to future missions targeting planetary atmospheres.
We consider the trajectory replanning problem for a large-scale swarm in a cluttered environment. Our path planner replans for robots by utilizing a hierarchical approach, dividing the workspace, and computing collision-free paths for robots within each cell in parallel. Distributed trajectory optimization generates a deadlock-free trajectory for efficient execution and maintains the control feasibility even when the optimization fails. Our hierarchical approach combines the benefits of both centralized and decentralized methods, achieving a high task success rate while providing real-time replanning capability. Compared to decentralized approaches, our approach effectively avoids deadlocks and collisions, significantly increasing the task success rate. We demonstrate the real-time performance of our algorithm with up to 142 robots in simulation, and a representative 24 physical Crazyflie nano-quadrotor experiment.
The area of research includes: control theory, dynamic systems, parameters of the external environment, mode, integral indicators, strategy. The general problem of assessing the state of large economic objects (enterprises) is revealed. There is no unified assessment a control of through strategic planning. The article proposes an integral indicator method for a unified assessment of the enterprise. The enterprise is formalized as a digital copy. The digital copy includes all business processes at any given time. The digital copy is presented as a multidimensional dynamic system. Dimension of multidimensional dynamic system is 1.2 parameters This allows you to estimate the modes operation of the enterprise in the normal mode and in the mode for control of strategic planning.
Cardinality estimation remains a fundamental challenge in query optimization, often resulting in sub-optimal execution plans and degraded performance. While errors in cardinality estimation are inevitable, existing methods for identifying sub-optimal plans -- such as metrics like Q-error, P-error, or L1-error -- are limited to post-execution analysis, requiring complete knowledge of true cardinalities and failing to prevent the execution of sub-optimal plans in real-time. This paper introduces PLANSIEVE, a novel framework that identifies sub-optimal plans during query optimization. PLANSIEVE operates by analyzing the relative order of sub-plans generated by the optimizer based on estimated and true cardinalities. It begins with surrogate cardinalities from any third-party estimator and incrementally refines these surrogates as the system processes more queries. Experimental results on the augmented JOB-LIGHT-SCALE and STATS-CEB-SCALE workloads demonstrate that PLANSIEVE achieves an accuracy of up to 88.7\% in predicting sub-optimal plans.
Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in reasoning and task planning for embodied agents, their ability to comprehend physical phenomena remains extremely limited. To close this gap, we introduce PhysBench, a comprehensive benchmark designed to evaluate VLMs' physical world understanding capability across a diverse set of tasks. PhysBench contains 10,002 entries of interleaved video-image-text data, categorized into four major domains: physical object properties, physical object relationships, physical scene understanding, and physics-based dynamics, further divided into 19 subclasses and 8 distinct capability dimensions. Our extensive experiments, conducted on 75 representative VLMs, reveal that while these models excel in common-sense reasoning, they struggle with understanding the physical world -- likely due to the absence of physical knowledge in their training data and the lack of embedded physical priors. To tackle the shortfall, we introduce PhysAgent, a novel framework that combines the generalization strengths of VLMs with the specialized expertise of vision models, significantly enhancing VLMs' physical understanding across a variety of tasks, including an 18.4\% improvement on GPT-4o. Furthermore, our results demonstrate that enhancing VLMs' physical world understanding capabilities can help embodied agents such as MOKA. We believe that PhysBench and PhysAgent offer valuable insights and contribute to bridging the gap between VLMs and physical world understanding.
HERITRACE is a data editor designed for galleries, libraries, archives and museums, aimed at simplifying data curation while enabling non-technical domain experts to manage data intuitively without losing its semantic integrity. While the semantic nature of RDF can pose a barrier to data curation due to its complexity, HERITRACE conceals this intricacy while preserving the advantages of semantic representation. The system natively supports provenance management and change tracking, ensuring transparency and accountability throughout the curation process. Although HERITRACE functions effectively out of the box, it offers a straightforward customization interface for technical staff, enabling adaptation to the specific data model required by a given collection. Current applications include the ParaText project, and its adoption is already planned for OpenCitations. Future developments will focus on integrating the RDF Mapping Language (RML) to enhance compatibility with non-RDF data formats, further expanding its applicability in digital heritage management.
Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored to specific benchmarks, relying on carefully tuned hyperparameters and algorithmic choices. Recently, powerful model-based RL methods have shown impressive general results across benchmarks but come at the cost of increased complexity and slow run times, limiting their broader applicability. In this paper, we attempt to find a unifying model-free deep RL algorithm that can address a diverse class of domains and problem settings. To achieve this, we leverage model-based representations that approximately linearize the value function, taking advantage of the denser task objectives used by model-based RL while avoiding the costs associated with planning or simulated trajectories. We evaluate our algorithm, MR.Q, on a variety of common RL benchmarks with a single set of hyperparameters and show a competitive performance against domain-specific and general baselines, providing a concrete step towards building general-purpose model-free deep RL algorithms.
One approach for multilingual data-to-text generation is to translate grammatical configurations upfront from the source language into each target language. These configurations are then used by a surface realizer and in document planning stages to generate output. In this paper, we describe a rule-based NLG implementation of this approach where the configuration is translated by Neural Machine Translation (NMT) combined with a one-time human review, and introduce a cross-language grammar dependency model to create a multilingual NLG system that generates text from the source data, scaling the generation phase without a human in the loop. Additionally, we introduce a method for human post-editing evaluation on the automatically translated text. Our evaluation on the SportSett:Basketball dataset shows that our NLG system performs well, underlining its grammatical correctness in translation tasks.
Scene and object reconstruction is an important problem in robotics, in particular in planning collision-free trajectories or in object manipulation. This paper compares two strategies for the reconstruction of nonvisible parts of the object surface from a single RGB-D camera view. The first method, named DeepSDF predicts the Signed Distance Transform to the object surface for a given point in 3D space. The second method, named MirrorNet reconstructs the occluded objects' parts by generating images from the other side of the observed object. Experiments performed with objects from the ShapeNet dataset, show that the view-dependent MirrorNet is faster and has smaller reconstruction errors in most categories.
Multi-agent reinforcement learning (MARL) has been widely adopted in high-performance computing and complex data-driven decision-making in the wireless domain. However, conventional MARL schemes face many obstacles in real-world scenarios. First, most MARL algorithms are online, which might be unsafe and impractical. Second, MARL algorithms are environment-specific, meaning network configuration changes require model retraining. This letter proposes a novel meta-offline MARL algorithm that combines conservative Q-learning (CQL) and model agnostic meta-learning (MAML). CQL enables offline training by leveraging pre-collected datasets, while MAML ensures scalability and adaptability to dynamic network configurations and objectives. We propose two algorithm variants: independent training (M-I-MARL) and centralized training decentralized execution (M-CTDE-MARL). Simulation results show that the proposed algorithm outperforms conventional schemes, especially the CTDE approach that achieves 50 % faster convergence in dynamic scenarios than the benchmarks. The proposed framework enhances scalability, robustness, and adaptability in wireless communication systems by optimizing UAV trajectories and scheduling policies.
Using agent-based social simulations can enhance our understanding of urban planning, public health, and economic forecasting. Realistic synthetic populations with numerous attributes strengthen these simulations. The Wasserstein Generative Adversarial Network, trained on census data like EU-SILC, can create robust synthetic populations. These methods, aided by external statistics or EU-SILC weights, generate spatial synthetic populations for agent-based models. The increased access to high-quality micro-data has sparked interest in synthetic populations, which preserve demographic profiles and analytical strength while ensuring privacy and preventing discrimination. This study uses national data from Finland and Greece for Helsinki and Thessaloniki to explore balanced spatial synthetic population generation. Results show challenges related to balancing data with or without aggregated statistics for the target population and the general under-representation of fringe profiles by deep generative methods. The latter can lead to discrimination in agent-based simulations.
Publicly available satellite imagery, such as Sentinel- 2, often lacks the spatial resolution required for accurate analysis of remote sensing tasks including urban planning and disaster response. Current super-resolution techniques are typically trained on limited datasets, leading to poor generalization across diverse geographic regions. In this work, we propose a novel super-resolution framework that enhances generalization by incorporating geographic context through location embeddings. Our framework employs Generative Adversarial Networks (GANs) and incorporates techniques from diffusion models to enhance image quality. Furthermore, we address tiling artifacts by integrating information from neighboring images, enabling the generation of seamless, high-resolution outputs. We demonstrate the effectiveness of our method on the building segmentation task, showing significant improvements over state-of-the-art methods and highlighting its potential for real-world applications.
Individuals who are differently-able in vision cannot proceed with their day-to-day activities as smoothly as other people do. Especially independent walking is a hard target to achieve with their visual impairment. Assistive electronic travel aids equipped with different types of sensors are designed for visually impaired persons to assist their safe navigation. The amount of research on combining multiple sensors in assistive navigation aids for visually impaired navigation is limited. Most work is targeted at sensor integration but not at sensor fusion. This paper aims to address how sensor fusion and integration will be used to improve the sub-processes of visually impaired navigation and the way to evaluate the sensor fusion-based approach for visually impaired navigation which consists of several contributions to field sensor fusion in visually impaired navigation such as a novel homogeneous sensor fusion algorithm based on extended Kalman filter, a novel heterogeneous sensor integration approach, and a complementary sensor fusion algorithm based on error state extended Kaman filter. Overall this research presents a novel navigational framework to integrate obstacle detection, obstacle recognition, localization, motion planning, and current context awareness with sensor fusion.
Open-plan offices are well-known to be adversely affected by acoustic issues. This study aims to model acoustic dissatisfaction using measurements of room acoustics, sound environment during occupancy, and occupant surveys (n = 349) in 28 offices representing a diverse range of workplace parameters. As latent factors, the contribution of $\textit{lack of privacy}$ (LackPriv) was 25% higher than $\textit{noise disturbance}$ (NseDstrb) in predicting $\textit{acoustic dissatisfaction}$ (AcDsat). Room acoustic metrics based on sound pressure level (SPL) decay of speech ($L_{\text{p,A,s,4m}}$ and $r_{\text{C}}$) were better in predicting these factors than distraction distance ($r_{\text{D}}$) based on speech transmission index. This contradicts previous findings, and the trends for SPL-based metrics in predicting AcDsat and LackPriv go against expectations based on ISO 3382-3. For sound during occupation, $L_{\text{A,90}}$ and psychoacoustic loudness ($N_{\text{90}}$) predicted AcDsat, and a SPL fluctuation metric ($M_{\text{A,eq}}$) predicted LackPriv. However, these metrics were weaker predictors than ISO 3382-3 metrics. Medium-sized offices exhibited higher dissatisfaction than larger ($\geq$50 occupants) offices. Dissatisfaction varied substantially across parameters including ceiling heights, number of workstations, and years of work, but not between offices with fixed seating compared to more flexible and activity-based working configurations. Overall, these findings highlight the complexities in characterizing occupants' perceptions using instrumental acoustic measurements.
Rapid advances in 3D model scanning have enabled the mass digitization of dental clay models. However, most clinicians and researchers continue to use manual morphometric analysis methods on these models such as landmarking. This is a significant step in treatment planning for craniomaxillofacial conditions. We aimed to develop and test a geometric deep learning model that would accurately and reliably label landmarks on a complicated and specialized patient population -- infants, as accurately as a human specialist without a large amount of training data. Our developed pipeline demonstrated an accuracy of 94.44% with an absolute mean error of 1.676 +/- 0.959 mm on a set of 100 models acquired from newborn babies with cleft lip and palate. Our proposed pipeline has the potential to serve as a fast, accurate, and reliable quantifier of maxillary arch morphometric features, as well as an integral step towards a future fully automated dental treatment pipeline.
Techniques for preclinical intensity modulated radiation therapy are being developed to improve translation by replicating the clinical paradigm. This study presents the first treatment planning comparison between small animal IMRT (SA-IMRT) and three-dimensional conformal radiotherapy (CRT) in a model application, oxygen-guided dose painting of tumor hypoxia, using actual mouse data. A novel compensator-based platform was employed to generate SA-IMRT and CRT plans with 2-15 beam angles for seventeen mice with fibrosarcoma tumors. The whole tumor received a dose of 22.5 Gy, with a simultaneous integrated boost of 13 Gy to hypoxic voxels identified via electron paramagnetic resonance imaging. Plan quality was assessed using the Paddick conformity index (CI), uniformity, and dose volume histograms. For 3-angles, SA-IMRT yielded significantly improved dose conformity (median hypoxic CI =0.45 versus 0.17), tumor dose uniformity (11.0% versus 14.3%), and dosimetric spread between boost and non-boost targets (D50% difference = 13.0 Gy [ideal], 13.1 Gy [SA-IMRT], 7. 3 Gy [CRT]). No significant improvement in CI was associated with >3 beam angles (Wilcoxon signed-rank test, p < 0.05). This study demonstrates that SA-IMRT provides significant improvements in radiation plan quality and yields dose distributions that more closely mimic the clinical setting relative to current CRT approaches.
Charged lepton flavor violation (CLFV) is expected in a diverse set of new physics scenarios. The current generation of experiments probe CLFV in the muon sector in three complementary channels: $\mu^-N \rightarrow e^- N$ (Mu2e, COMET), $\mu^+ \rightarrow e^+ \gamma$ (MEG-II), and $\mu^+ \rightarrow e^+e^+e^-$s (Mu3e). These experiments aim to enhance existing limits by several orders-of-magnitude in the coming decade and offer discovery potential to many new physics models. The proposed Advanced Muon Facility (AMF) would be a multi-purpose muon facility based at Fermilab and introduces an innovative approach based on a muon storage ring to enable a full suite of muon CLFV experiments. AMF would host CLFV experiments with sensitivities orders-of-magnitude beyond the present era. In the event of a signal in these currently planned experiments, AMF would enable additional measurements to elucidate the nature of the new physics observed. The design and R$\&$D for AMF is in its infancy. This article outlines the motivations for AMF, detailing on-going R$\&$D efforts, and highlighting potential synergies with the proposed muon collider.
Fiducial marker positions in projection image of cone-beam computed tomography (CBCT) scans have been studied to evaluate daily residual motion during breath-hold radiation therapy. Fiducial marker migration posed challenges in accurately locating markers, prompting the development of a novel algorithm that reconstructs volumetric probability maps of marker locations from filtered gradient maps of projections. This guides the development of a Python-based algorithm to detect fiducial markers in projection images using Meta AI's Segment Anything Model 2 (SAM 2). Retrospective data from a pancreatic cancer patient with two fiducial markers were analyzed. The three-dimensional (3D) marker positions from simulation computed tomography (CT) were compared to those reconstructed from CBCT images, revealing a decrease in relative distances between markers over time. Fiducial markers were successfully detected in 2777 out of 2786 projection frames. The average standard deviation of superior-inferior (SI) marker positions was 0.56 mm per breath-hold, with differences in average SI positions between two breath-holds in the same scan reaching up to 5.2 mm, and a gap of up to 7.3 mm between the end of the first and beginning of the second breath-hold. 3D marker positions were calculated using projection positions and confirmed marker migration. This method effectively calculates marker probability volume and enables accurate fiducial marker tracking during treatment without requiring any specialized equipment, additional radiation doses, or manual initialization and labeling. It has significant potential for automatically assessing daily residual motion to adjust planning margins, functioning as an adaptive radiation therapy tool.
This paper introduces a novel complexity-informed approach to cybersecurity management, addressing the challenges found within complex cyber defences. We adapt and extend the complexity theory to cybersecurity and develop a quantitative framework that empowers decision-makers with strategies to de-complexify defences, identify improvement opportunities, and resolve bottlenecks. Our approach also provides a solid foundation for critical cybersecurity decisions, such as tooling investment or divestment, workforce capacity planning, and optimisation of processes and capabilities. Through a case study, we detail and validate a systematic method for assessing and managing the complexity within cybersecurity defences. The complexity-informed approach based on MITRE ATT&CK, is designed to complement threat-informed defences. Threat-informed methods focus on understanding and countering adversary tactics, while the complexity-informed approach optimises the underlying defence infrastructure, thereby optimising the overall efficiency and effectiveness of cyber defences.
Achieving human-like driving behaviors in complex open-world environments is a critical challenge in autonomous driving. Contemporary learning-based planning approaches such as imitation learning methods often struggle to balance competing objectives and lack of safety assurance,due to limited adaptability and inadequacy in learning complex multi-modal behaviors commonly exhibited in human planning, not to mention their strong reliance on the fallback strategy with predefined rules. We propose a novel transformer-based Diffusion Planner for closed-loop planning, which can effectively model multi-modal driving behavior and ensure trajectory quality without any rule-based refinement. Our model supports joint modeling of both prediction and planning tasks under the same architecture, enabling cooperative behaviors between vehicles. Moreover, by learning the gradient of the trajectory score function and employing a flexible classifier guidance mechanism, Diffusion Planner effectively achieves safe and adaptable planning behaviors. Evaluations on the large-scale real-world autonomous planning benchmark nuPlan and our newly collected 200-hour delivery-vehicle driving dataset demonstrate that Diffusion Planner achieves state-of-the-art closed-loop performance with robust transferability in diverse driving styles.
This paper analyzes the 1/3 Financial Rule, a method of allocating income equally among debt repayment, savings, and living expenses. Through mathematical modeling, game theory, behavioral finance, and technological analysis, we examine the rule's potential for supporting household financial stability and reducing bankruptcy risk. The research develops theoretical foundations using utility maximization theory, demonstrating how equal allocation emerges as a solution under standard economic assumptions. The game-theoretic analysis explores the rule's effectiveness across different household structures, revealing potential strategic advantages in financial decision-making. We investigate psychological factors influencing financial choices, including cognitive biases and neurobiological mechanisms that impact economic behavior. Technological approaches, such as AI-driven personalization, blockchain tracking, and smart contract applications, are examined for their potential to support financial planning. Empirical validation using U.S. Census data and longitudinal studies assesses the rule's performance across various household types. Stress testing under different economic conditions provides insights into its adaptability and resilience. The research integrates mathematical analysis with behavioral insights and technological perspectives to develop a comprehensive approach to household financial management.
Scientific optimization problems are usually concerned with balancing multiple competing objectives, which come as preferences over both the outcomes of an experiment (e.g. maximize the reaction yield) and the corresponding input parameters (e.g. minimize the use of an expensive reagent). Typically, practical and economic considerations define a hierarchy over these objectives, which must be reflected in algorithms for sample-efficient experiment planning. Herein, we introduce BoTier, a composite objective that can flexibly represent a hierarchy of preferences over both experiment outcomes and input parameters. We provide systematic benchmarks on synthetic and real-life surfaces, demonstrating the robust applicability of BoTier across a number of use cases. Importantly, BoTier is implemented in an auto-differentiable fashion, enabling seamless integration with the BoTorch library, thereby facilitating adoption by the scientific community.
Multimodal Retrieval Augmented Generation (MRAG) systems, while promising for enhancing Multimodal Large Language Models (MLLMs), often rely on rigid, single-step retrieval methods. This limitation hinders their ability to effectively address real-world scenarios that demand adaptive information acquisition and query refinement. To overcome this, we introduce the novel task of Multimodal Retrieval Augmented Generation Planning (MRAG Planning), focusing on optimizing MLLM performance while minimizing computational overhead. We present CogPlanner, a versatile framework inspired by human cognitive processes. CogPlanner iteratively refines queries and selects retrieval strategies, enabling both parallel and sequential modeling approaches. To rigorously evaluate MRAG Planning, we introduce CogBench, a new benchmark specifically designed for this task. CogBench facilitates the integration of lightweight CogPlanner with resource-efficient MLLMs. Our experimental findings demonstrate that CogPlanner surpasses existing MRAG baselines, achieving significant improvements in both accuracy and efficiency with minimal computational overhead.
White matter bundle segmentation is crucial for studying brain structural connectivity, neurosurgical planning, and neurological disorders. White Matter Segmentation remains challenging due to structural similarity in streamlines, subject variability, symmetry in 2 hemispheres, etc. To address these challenges, we propose TractoGPT, a GPT-based architecture trained on streamline, cluster, and fusion data representations separately. TractoGPT is a fully-automatic method that generalizes across datasets and retains shape information of the white matter bundles. Experiments also show that TractoGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores. We use TractoInferno and 105HCP datasets and validate generalization across dataset.
Digital Surface Models (DSMs) are essential for accurately representing Earth's topography in geospatial analyses. DSMs capture detailed elevations of natural and manmade features, crucial for applications like urban planning, vegetation studies, and 3D reconstruction. However, DSMs derived from stereo satellite imagery often contain voids or missing data due to occlusions, shadows, and lowsignal areas. Previous studies have primarily focused on void filling for digital elevation models (DEMs) and Digital Terrain Models (DTMs), employing methods such as inverse distance weighting (IDW), kriging, and spline interpolation. While effective for simpler terrains, these approaches often fail to handle the intricate structures present in DSMs. To overcome these limitations, we introduce Dfilled, a guided DSM void filling method that leverages optical remote sensing images through edge-enhancing diffusion. Dfilled repurposes deep anisotropic diffusion models, which originally designed for super-resolution tasks, to inpaint DSMs. Additionally, we utilize Perlin noise to create inpainting masks that mimic natural void patterns in DSMs. Experimental evaluations demonstrate that Dfilled surpasses traditional interpolation methods and deep learning approaches in DSM void filling tasks. Both quantitative and qualitative assessments highlight the method's ability to manage complex features and deliver accurate, visually coherent results.
In online advertising, advertisers commonly utilize auto-bidding services to bid for impression opportunities. A typical objective of the auto-bidder is to optimize the advertiser's cumulative value of winning impressions within specified budget constraints. However, such a problem is challenging due to the complex bidding environment faced by diverse advertisers. To address this challenge, we introduce ABPlanner, a few-shot adaptable budget planner designed to improve budget-constrained auto-bidding. ABPlanner is based on a hierarchical bidding framework that decomposes the bidding process into shorter, manageable stages. Within this framework, ABPlanner allocates the budget across all stages, allowing a low-level auto-bidder to bids based on the budget allocation plan. The adaptability of ABPlanner is achieved through a sequential decision-making approach, inspired by in-context reinforcement learning. For each advertiser, ABPlanner adjusts the budget allocation plan episode by episode, using data from previous episodes as prompt for current decisions. This enables ABPlanner to quickly adapt to different advertisers with few-shot data, providing a sample-efficient solution. Extensive simulation experiments and real-world A/B testing validate the effectiveness of ABPlanner, demonstrating its capability to enhance the cumulative value achieved by auto-bidders.
Woodworkers have to navigate multiple considerations when planning a project, including available resources, skill-level, and intended effort. Do it yourself (DIY) woodworkers face these challenges most acutely because of tight material constraints and a desire for custom designs tailored to specific spaces. To address these needs, we present XR-penter, an extended reality (XR) application that supports in situ, material-aware woodworking for casual makers. Our system enables users to design virtual scrap wood assemblies directly in their workspace, encouraging sustainable practices through the use of discarded materials. Users register physical material as virtual twins, manipulate these twins into an assembly in XR, and preview cuts needed for fabrication. We conducted a case study and feedback sessions to demonstrate how XR-penter supports improvisational workflows in practice, the type of woodworker who would benefit most from our system, and insights on integrating similar spatial and material considerations into future work.
Remote sensing image segmentation is pivotal for earth observation, underpinning applications such as environmental monitoring and urban planning. Due to the limited annotation data available in remote sensing images, numerous studies have focused on data augmentation as a means to alleviate overfitting in deep learning networks. However, some existing data augmentation strategies rely on simple transformations that may not sufficiently enhance data diversity or model generalization capabilities. This paper proposes a novel augmentation strategy, Clustered-Patch-Mixed Mosaic (CP2M), designed to address these limitations. CP2M integrates a Mosaic augmentation phase with a clustered patch mix phase. The former stage constructs a new sample from four random samples, while the latter phase uses the connected component labeling algorithm to ensure the augmented data maintains spatial coherence and avoids introducing irrelevant semantics when pasting random patches. Our experiments on the ISPRS Potsdam dataset demonstrate that CP2M substantially mitigates overfitting, setting new benchmarks for segmentation accuracy and model robustness in remote sensing tasks.
The rapid adoption of distributed energy resources (DERs) has outpaced grid modernization, leading to capacity limitations that challenge their further integration. Hosting Capacity Assessment (HCA) is a critical tool for evaluating how much DER capacity a grid can handle without breaching operational limits. HCA serves multiple goals: enabling higher DER penetration, accelerating grid connection times, guiding infrastructure upgrades or flexible resource deployment, ensuring equitable policies, and improving grid flexibility while minimizing curtailment. HCA lacks a universal definition, varying by modelling approaches, uncertainty considerations, and objectives. This paper addresses five key questions to standardize and enhance HCA practices. First, it classifies HCA objectives associated with different stakeholders such as system operators, consumers, market operators and consumers. Second, it examines model attributes, including modelling sophistication, data requirements, and uncertainty handling, thus balancing complexity with computational efficiency. Third, it explores HCA applications, such as planning grid investments or operational decisions, and summarizes use cases associated with HCA. Fourth, it emphasizes the need for periodic updates to reflect dynamic grid conditions, evolving technologies, and new DER installations. Finally, it identifies challenges, such as ensuring data quality, managing computational demands, and aligning short-term and long-term goals. By addressing these aspects, this paper provides a structured approach to perform and apply HCA, offering insights for engineers, planners, and policymakers to manage DER integration effectively.
Transporting a heavy payload using multiple aerial robots (MARs) is an efficient manner to extend the load capacity of a single aerial robot. However, existing schemes for the multiple aerial robots transportation system (MARTS) still lack the capability to generate a collision-free and dynamically feasible trajectory in real-time and further track an agile trajectory especially when there are no sensors available to measure the states of payload and cable. Therefore, they are limited to low-agility transportation in simple environments. To bridge the gap, we propose complete planning and control schemes for the MARTS, achieving safe and agile aerial transportation (SAAT) of a cable-suspended payload in complex environments. Flatness maps for the aerial robot considering the complete kinematical constraint and the dynamical coupling between each aerial robot and payload are derived. To improve the responsiveness for the generation of the safe, dynamically feasible, and agile trajectory in complex environments, a real-time spatio-temporal trajectory planning scheme is proposed for the MARTS. Besides, we break away from the reliance on the state measurement for both the payload and cable, as well as the closed-loop control for the payload, and propose a fully distributed control scheme to track the agile trajectory that is robust against imprecise payload mass and non-point mass payload. The proposed schemes are extensively validated through benchmark comparisons, ablation studies, and simulations. Finally, extensive real-world experiments are conducted on a MARTS integrated by three aerial robots with onboard computers and sensors. The result validates the efficiency and robustness of our proposed schemes for SAAT in complex environments.
Generalized planning is concerned with how to find a single plan to solve multiple similar planning instances. Abstractions are widely used for solving generalized planning, and QNP (qualitative numeric planning) is a popular abstract model. Recently, Cui et al. showed that a plan solves a sound and complete abstraction of a generalized planning problem if and only if the refined plan solves the original problem. However, existing work on automatic abstraction for generalized planning can hardly guarantee soundness let alone completeness. In this paper, we propose an automatic sound and complete abstraction method for generalized planning with baggable types. We use a variant of QNP, called bounded QNP (BQNP), where integer variables are increased or decreased by only one. Since BQNP is undecidable, we propose and implement a sound but incomplete solver for BQNP. We present an automatic method to abstract a BQNP problem from a classical planning instance with baggable types. The basic idea for abstraction is to introduce a counter for each bag of indistinguishable tuples of objects. We define a class of domains called proper baggable domains, and show that for such domains, the BQNP problem got by our automatic method is a sound and complete abstraction for a generalized planning problem whose instances share the same bags with the given instance but the sizes of the bags might be different. Thus, the refined plan of a solution to the BQNP problem is a solution to the generalized planning problem. Finally, we implement our abstraction method and experiments on a number of domains demonstrate the promise of our approach.
Deep learning's success in perception, natural language processing, etc. inspires hopes for advancements in autonomous robotics. However, real-world robotics face challenges like variability, high-dimensional state spaces, non-linear dependencies, and partial observability. A key issue is non-stationarity of robots, environments, and tasks, leading to performance drops with out-of-distribution data. Unlike current machine learning models, humans adapt quickly to changes and new tasks due to a cognitive architecture that enables systematic generalization and meta-cognition. Human brain's System 1 handles routine tasks unconsciously, while System 2 manages complex tasks consciously, facilitating flexible problem-solving and self-monitoring. For robots to achieve human-like learning and reasoning, they need to integrate causal models, working memory, planning, and metacognitive processing. By incorporating human cognition insights, the next generation of service robots will handle novel situations and monitor themselves to avoid risks and mitigate errors.
We demonstrate that generative deep learning can translate galaxy observations across ultraviolet, visible, and infrared photometric bands. Leveraging mock observations from the Illustris simulations, we develop and validate a supervised image-to-image model capable of performing both band interpolation and extrapolation. The resulting trained models exhibit high fidelity in generating outputs, as verified by both general image comparison metrics (MAE, SSIM, PSNR) and specialized astronomical metrics (GINI coefficient, M20). Moreover, we show that our model can be used to predict real-world observations, using data from the DECaLS survey as a case study. These findings highlight the potential of generative learning to augment astronomical datasets, enabling efficient exploration of multi-band information in regions where observations are incomplete. This work opens new pathways for optimizing mission planning, guiding high-resolution follow-ups, and enhancing our understanding of galaxy morphology and evolution.
Embodied manipulation is a fundamental ability in the realm of embodied artificial intelligence. Although current embodied manipulation models show certain generalizations in specific settings, they struggle in new environments and tasks due to the complexity and diversity of real-world scenarios. The traditional end-to-end data collection and training manner leads to significant data demands. Decomposing end-to-end tasks into atomic skills helps reduce data requirements and improves the task success rate. However, existing methods are limited by predefined skill sets that cannot be dynamically updated. To address the issue, we introduce a three-wheeled data-driven method to build an atomic skill library. We divide tasks into subtasks using the Vision-Language-Planning (VLP). Then, atomic skill definitions are formed by abstracting the subtasks. Finally, an atomic skill library is constructed via data collection and Vision-Language-Action (VLA) fine-tuning. As the atomic skill library expands dynamically with the three-wheel update strategy, the range of tasks it can cover grows naturally. In this way, our method shifts focus from end-to-end tasks to atomic skills, significantly reducing data costs while maintaining high performance and enabling efficient adaptation to new tasks. Extensive experiments in real-world settings demonstrate the effectiveness and efficiency of our approach.
The proposed construction of new particle accelerator-based facilities in the coming decades -- and upgrades to existing facilities -- provides the unique opportunity to embed innovative environmental impact reduction techniques into their design. This living document provides high-level guidelines to improve environmental sustainability in the planning, construction, operational and decommissioning stages of large accelerator facilities. A collection of various resources is provided, with examples of some existing and suggested practices.
We evaluate the cross sections for the $p p \to p p \eta$ reaction at energies relevant for the HADES, PANDA and SIS100 experiments at GSI-FAIR within an effective Lagrangian approach. We consider the $\eta$-bremsstrahlung mechanism with the intermediate proton exchange via the $\pi^{0}$, $\eta$, $\rho^{0}$ and $\omega$ exchanges and the mechanism involving the nucleon resonances $N(1535)$, $N(1650)$, $N(1710)$ and $N(1880)$ excited via the pseudoscalar- or/and vector-meson exchanges, depending on the model. We also discuss the role of the $\omega \omega$- and $\rho^{0} \rho^{0}$-fusion processes with the reggeized vector-meson exchanges. To determine the parameters of the model, the $\gamma p \to \eta p$ and $\pi^{-} p \to \eta n$ reactions are discussed and the results are compared with Crystal Ball and CLAS data. For the $p p \to p p \eta$ reaction, the model results are compared with the energy dependence of the cross section measured far from the threshold and with the differential distributions $d\sigma/d\cos\theta_{\eta}$ and $d\sigma/dp_{\eta}$ measured by the DISTO Collaboration. The comparison shows that the $N(1535)$ resonance is the dominant contribution and that other contributions are also important due to interference effects. Assuming that the $\rho$ exchange is the dominant resonant excitation process, the model is able to describe the available data, e.g. it reproduces the shape of the angular distributions measured by the DISTO Collaboration. Predictions are given for the HADES experiment at center-of-mass energy of $\sqrt{s} = 3.46$~GeV, which can be verified in the near future, and for planned PANDA and SIS100 experiments at higher energies.
Power grid operators face increasing difficulties in the control room as the increase in energy demand and the shift to renewable energy introduce new complexities in managing congestion and maintaining a stable supply. Effective grid topology control requires advanced tools capable of handling multi-objective trade-offs. While Reinforcement Learning (RL) offers a promising framework for tackling such challenges, existing Multi-Objective Reinforcement Learning (MORL) approaches fail to scale to the large state and action spaces inherent in real-world grid operations. Here we present a two-phase, efficient and scalable Multi-Objective Optimisation (MOO) method designed for grid topology control, combining an efficient RL learning phase with a rapid planning phase to generate day-ahead plans for unseen scenarios. We validate our approach using historical data from TenneT, a European Transmission System Operator (TSO), demonstrating minimal deployment time, generating day-ahead plans within 4-7 minutes with strong performance. These results underline the potential of our scalable method to support real-world power grid management, offering a practical, computationally efficient, and time-effective tool for operational planning. Based on current congestion costs and inefficiencies in grid operations, adopting our approach by TSOs could potentially save millions of euros annually, providing a compelling economic incentive for its integration in the control room.
We present a compact scintillating fibre timing detector developed for the Mu3e experiment. Mu3e is one of the flagship experiments of the Swiss particle physics scene, aiming to search for the charged lepton flavour violating (neutrinoless) muon decay $\mu^+ \rightarrow e^+e^-e^+$. Mu3e is planned to start taking data in 2025 at the Paul Scherrer Institute in Switzerland, using the most intense continuous surface muon beam in the world (10$^8$ muons per second). At the University of Geneva, together with partners from ETH Zurich, we are developing a scintillating fibre detector formed by staggering three layers of 250 $\mu m$ diameter round scintillating fibres. The fibre ribbons are coupled at both ends to multi-channel silicon photo-multiplier arrays, which are read out with the MuTRiG ASIC, specifically developed for this experiment. This presentation is focused on the performances of the scintillating fibre detector, notably on the time resolution around 250 ps, the efficiency greater than 97\% and the spatial resolution of $\sim$ 100 $\mu m$. In this presentation, we also include the challenges overcome to build this very thin scintillating fibre detector, having a thickness smaller than 0.2\% of the radiation length. Furthermore, we discuss the operation and performance of the MuTRiG ASIC, used for reading out the 3072 channels of the fibre detector.
Mu3e is an experiment currently under construction at the Paul Scherrer Institute in Switzerland, designed to search for the Lepton Flavor Violating (LFV) decay $\mu^+ \rightarrow e^+e^-e^+$. In extensions of the Standard Model (SM) that account for neutrino masses, this decay is theoretically allowed but occurs only through extremely rare loop processes, with a predicted branching ratio of approximately $\mathcal{O}(10^{-54})$. Such a small probability implies that any observation of this decay would provide clear evidence for physics beyond the SM. The Mu3e experiment aims to probe the $\mu^+ \rightarrow e^+e^-e^+$ decay with a sensitivity of approximately $\mathcal{O}(10^{-15})$ in its Phase-1 and plans to achieve a sensitivity of $\mathcal{O}(10^{-16})$ after future upgrades. To reach its Phase-1 ambitious goals, Mu3e is going to use the most intense continuous muon beam in the world, generating 10$^{8}$ muon stops per second in the target placed at the center of the Mu3e. Mu3e will use three main technologies for particle detection. The tracking will done through ultra-thin (50 - 70 $\mu m$) pixel detectors based on MuPix11 sensors. These are high-voltage monolithic active pixel sensors (HV-MAPS) with a $\sim$ 23~$\mu$m spatial resolution. The timing will be done through scintillating fibres ($\sim$ 250 ps) and tiles ($\sim$ 40 ps), coupled to silicon photomultipliers and read out by MuTRiG3 ASICs. A triggerless DAQ system based on FPGAs will collect data from the detectors, which will then undergo reconstruction in a GPU filter farm. The assembly of the detectors has started, with a detector commissioning beam time planned for 2025. This document reports on the status of the construction, installation, and data-taking plans for the near future.
We present a novel approach for recommending actionable strategies by integrating strategic frameworks with decision heuristics through semantic analysis. While strategy frameworks provide systematic models for assessment and planning, and decision heuristics encode experiential knowledge,these traditions have historically remained separate. Our methodology bridges this gap using advanced natural language processing (NLP), demonstrated through integrating frameworks like the 6C model with the Thirty-Six Stratagems. The approach employs vector space representations and semantic similarity calculations to map framework parameters to heuristic patterns, supported by a computational architecture that combines deep semantic processing with constrained use of Large Language Models. By processing both primary content and secondary elements (diagrams, matrices) as complementary linguistic representations, we demonstrate effectiveness through corporate strategy case studies. The methodology generalizes to various analytical frameworks and heuristic sets, culminating in a plug-and-play architecture for generating recommender systems that enable cohesive integration of strategic frameworks and decision heuristics into actionable guidance.
The need to explore and/or optimize expensive simulators with many qualitative factors arises in broad scientific and engineering problems. Our motivating application lies in path planning - the exploration of feasible paths for navigation, which plays an important role in robotics, surgical planning and assembly planning. Here, the feasibility of a path is evaluated via expensive virtual experiments, and its parameter space is typically discrete and high-dimensional. A carefully selected experimental design is thus essential for timely decision-making. We propose here a novel framework, called QuIP, for experimental design of Qualitative factors via Integer Programming under a Gaussian process surrogate model with an exchangeable covariance function. For initial design, we show that its asymptotic D-optimal design can be formulated as a variant of the well-known assignment problem in operations research, which can be efficiently solved to global optimality using state-of-the-art integer programming solvers. For sequential design (specifically, for active learning or black-box optimization), we show that its design criterion can similarly be formulated as an assignment problem, thus enabling efficient and reliable optimization with existing solvers. We then demonstrate the effectiveness of QuIP over existing methods in a suite of path planning experiments and an application to rover trajectory optimization.
This article describes a procedure for measuring and evaluating radio impulsive noise (IN) from a specific source. A good knowledge of the noise caused by different sources is essential to plan radio services and to ensure good quality of service. Moreover, it is necessary to harmonize noise measurement methods to achieve results that can be mutually compared. This article not only provides steps that should be followed to make proper measurements, but also specifies appropriate parameters to characterize the IN when it is generated by a principal source. A detailed description of parameter calculation is presented, based on the recommendations of the International Telecommunication Union (ITU). This answers the request made in an ITU-R 214-4/3 question, which suggests determining the appropriate parameters to describe the noise when it has an impulsive characteristic.
This paper proposes a novel approach to formulate time-optimal point-to-point motion planning and control under uncertainty. The approach defines a robustified two-stage Optimal Control Problem (OCP), in which stage 1, with a fixed time grid, is seamlessly stitched with stage 2, which features a variable time grid. Stage 1 optimizes not only the nominal trajectory, but also feedback gains and corresponding state covariances, which robustify constraints in both stages. The outcome is a minimized uncertainty in stage 1 and a minimized total motion time for stage 2, both contributing to the time optimality and safety of the total motion. A timely replanning strategy is employed to handle changes in constraints and maintain feasibility, while a tailored iterative algorithm is proposed for efficient, real-time OCP execution.
The Unmanned Aerial Vehicle (UAV) path planning problem is a complex optimization problem in the field of robotics. In this paper, we investigate the possible utilization of this problem in benchmarking global optimization methods. We devise a problem instance generator and pick 56 representative instances, which we compare to established benchmarking suits through Exploratory Landscape Analysis to show their uniqueness. For the computational comparison, we select twelve well-performing global optimization techniques from both subfields of stochastic algorithms (evolutionary computation methods) and deterministic algorithms (Dividing RECTangles, or DIRECT-type methods). The experiments were conducted in settings with varying dimensionality and computational budgets. The results were analyzed through several criteria (number of best-found solutions, mean relative error, Friedman ranks) and utilized established statistical tests. The best-ranking methods for the UAV problems were almost universally the top-performing evolutionary techniques from recent competitions on numerical optimization at the Institute of Electrical and Electronics Engineers Congress on Evolutionary Computation. Lastly, we discussed the variable dimension characteristics of the studied UAV problems that remain still largely under-investigated.
Unmanned Aerial Vehicles (UAVs) are pivotal in applications such as search and rescue and environmental monitoring, excelling in intelligent perception tasks. However, their limited battery capacity hinders long-duration and long-distance missions. Charging UAVs (CUAVs) offers a potential solution by recharging mission UAVs (MUAVs), but existing methods rely on impractical pre-planned routes, failing to enable organic cooperation and limiting mission efficiency. We introduce a novel multi-agent deep reinforcement learning model named \textbf{H}eterogeneous \textbf{G}raph \textbf{A}ttention \textbf{M}ulti-agent Deep Deterministic Policy Gradient (HGAM), designed to dynamically coordinate MUAVs and CUAVs. This approach maximizes data collection, geographical fairness, and energy efficiency by allowing UAVs to adapt their routes in real-time to current task demands and environmental conditions without pre-planning. Our model uses heterogeneous graph attention networks (GATs) to present heterogeneous agents and facilitate efficient information exchange. It operates within an actor-critic framework. Simulation results show that our model significantly improves cooperation among heterogeneous UAVs, outperforming existing methods in several metrics, including data collection rate and charging efficiency.
Autonomous Driving Systems (ADSs) are safety-critical, as real-world safety violations can result in significant losses. Rigorous testing is essential before deployment, with simulation testing playing a key role. However, ADSs are typically complex, consisting of multiple modules such as perception and planning, or well-trained end-to-end autonomous driving systems. Offline methods, such as the Genetic Algorithm (GA), can only generate predefined trajectories for dynamics, which struggle to cause safety violations for ADSs rapidly and efficiently in different scenarios due to their evolutionary nature. Online methods, such as single-agent reinforcement learning (RL), can quickly adjust the dynamics' trajectory online to adapt to different scenarios, but they struggle to capture complex corner cases of ADS arising from the intricate interplay among multiple vehicles. Multi-agent reinforcement learning (MARL) has a strong ability in cooperative tasks. On the other hand, it faces its own challenges, particularly with convergence. This paper introduces MARL-OT, a scalable framework that leverages MARL to detect safety violations of ADS resulting from surrounding vehicles' cooperation. MARL-OT employs MARL for high-level guidance, triggering various dangerous scenarios for the rule-based online fuzzer to explore potential safety violations of ADS, thereby generating dynamic, realistic safety violation scenarios. Our approach improves the detected safety violation rate by up to 136.2% compared to the state-of-the-art (SOTA) testing technique.
Autonomous drone racing has risen as a challenging robotic benchmark for testing the limits of learning, perception, planning, and control. Expert human pilots are able to agilely fly a drone through a race track by mapping the real-time feed from a single onboard camera directly to control commands. Recent works in autonomous drone racing attempting direct pixel-to-commands control policies (without explicit state estimation) have relied on either intermediate representations that simplify the observation space or performed extensive bootstrapping using Imitation Learning (IL). This paper introduces an approach that learns policies from scratch, allowing a quadrotor to autonomously navigate a race track by directly mapping raw onboard camera pixels to control commands, just as human pilots do. By leveraging model-based reinforcement learning~(RL) - specifically DreamerV3 - we train visuomotor policies capable of agile flight through a race track using only raw pixel observations. While model-free RL methods such as PPO struggle to learn under these conditions, DreamerV3 efficiently acquires complex visuomotor behaviors. Moreover, because our policies learn directly from pixel inputs, the perception-aware reward term employed in previous RL approaches to guide the training process is no longer needed. Our experiments demonstrate in both simulation and real-world flight how the proposed approach can be deployed on agile quadrotors. This approach advances the frontier of vision-based autonomous flight and shows that model-based RL is a promising direction for real-world robotics.
This paper investigates the optimal infrastructure planning and order assignment problem of an on-demand food-delivery platform with a mixed fleet of drones and human couriers. The platform has two delivery modes: (a) ground delivery and (b) drone-assisted delivery (i.e., air delivery). In ground delivery, couriers directly collect and transport orders from restaurants to destinations. For air delivery, the delivery process involves three legs: initially, a human courier picks up the order from the restaurant and transports it to a nearby launchpad, where personnel load the orders onto drones and replace batteries as needed. The loaded drone then transports the order from the launchpad to a kiosk, where another courier retrieves the order from the kiosk for final delivery. The platform must determine the optimal locations for launchpads and kiosks within a transportation network, and devise an order assignment strategy that allocates food-delivery orders between ground and air delivery considering the bundling probabilities of ground deliveries and the waiting times at launchpads and kiosks. We formulate the platform's problem as a mixed-integer nonlinear program and develop a novel neural network-assisted optimization method to obtain high-quality solutions. A case study in Hong Kong validates our model and algorithm, revealing that drone delivery reduces operational costs, minimizes courier fleet size, and increases order bundling opportunities. We also find that the expansion of air delivery services may entail larger delivery times due to the trade-off between the travel time savings induced by the faster air delivery and the associated detours incurred by intermodal transfer and extra waiting times at launchpads and kiosks, which crucially depends on the distance of the orders and the sequence of activating long-distance air delivery routes versus short-distance ones.
Effective data management and sharing are critical success factors in industry-academia collaboration. This paper explores the motivations and lessons learned from publishing open data sets in such collaborations. Through a survey of participants in a European research project that published 13 data sets, and an analysis of metadata from almost 281 thousand datasets in Zenodo, we collected qualitative and quantitative results on motivations, achievements, research questions, licences and file types. Through inductive reasoning and statistical analysis we found that planning the data collection is essential, and that only few datasets (2.4%) had accompanying scripts for improved reuse. We also found that authors are not well aware of the importance of licences or which licence to choose. Finally, we found that data with a synthetic origin, collected with simulations and potentially mixed with real measurements, can be very meaningful, as predicted by Gartner and illustrated by many datasets collected in our research project.
In transportation systems and autonomous vehicles, intelligent agents must understand the future motion of traffic participants to effectively plan motion trajectories. At the same time, the motion of traffic participants is inherently uncertain. In this paper, we propose TrajFlow, a generative framework for estimating the occupancy density of traffic participants. Our framework utilizes a causal encoder to extract semantically meaningful embeddings of the observed trajectory, as well as a normalizing flow to decode these embeddings and determine the most likely future location of traffic participants at some time point in the future. Our formulation differs from existing approaches because we model the marginal distribution of spatial locations instead of the joint distribution of unobserved trajectories. The advantages of a marginal formulation are numerous. First, we demonstrate that the marginal formulation produces higher accuracy on challenging trajectory forecasting benchmarks. Second, the marginal formulation allows for a fully continuous sampling of future locations. Finally, marginal densities are better suited for downstream tasks as they allow for the computation of per-agent motion trajectories and occupancy grids, the two most commonly used representations for motion forecasting. We present a novel architecture based entirely on neural differential equations as an implementation of this framework and provide ablations to demonstrate the advantages of a continuous implementation over a more traditional discrete neural network based approach. The code is available at https://github.com/kosieram21/TrajFlow .
This paper introduces an innovative framework for understanding on-demand platforms by quantifying positive network effects, trust, revenue dynamics, and the influence of demand on platform operations at per-minute or even per-second granularity. Drawing inspiration from physics, the framework provides both a theoretical and pragmatic perspective, offering a pictorial and quantitative representation of how on-demand platforms create value. It seeks to demystify their nuanced operations by providing practical, tangible, and highly applicable metrics, platform design templates, and real-time optimization tools for strategic what-if scenario planning. Its model demonstrates strong predictive power and is deeply rooted in raw data. The framework offers a deterministic insight into the workings of diverse platforms like Uber, Airbnb, and food delivery services. Furthermore, it generalizes to model all on-demand service platforms with cyclical operations. It works synergistically with machine learning, game theory, and agent-based models by providing a solid quantitative core rooted in raw data, based on physical truths, and is capable of delivering tangible predictions for real-time operational adjustments. The framework's mathematical model was rigorously validated using highly detailed historical data retrieved with near 100% certainty. Applying data-driven induction, distinct qualities were identified in big data sets via an iterative process. Through analogical thinking, a clear and highly intuitive mapping between the elements, operational principles, and dynamic behaviors of a well-known physical system was established to create a physics-inspired lens for Uber. This novel quantitative framework was named PASER (Profit Amplification by Stimulated Emission of Revenue), drawing an analogy to its physical counterpart, the LASER (Light Amplification by Stimulated Emission of Radiation).
In this paper, we present ENTER, an interpretable Video Question Answering (VideoQA) system based on event graphs. Event graphs convert videos into graphical representations, where video events form the nodes and event-event relationships (temporal/causal/hierarchical) form the edges. This structured representation offers many benefits: 1) Interpretable VideoQA via generated code that parses event-graph; 2) Incorporation of contextual visual information in the reasoning process (code generation) via event graphs; 3) Robust VideoQA via Hierarchical Iterative Update of the event graphs. Existing interpretable VideoQA systems are often top-down, disregarding low-level visual information in the reasoning plan generation, and are brittle. While bottom-up approaches produce responses from visual data, they lack interpretability. Experimental results on NExT-QA, IntentQA, and EgoSchema demonstrate that not only does our method outperform existing top-down approaches while obtaining competitive performance against bottom-up approaches, but more importantly, offers superior interpretability and explainability in the reasoning process.
Biological flyers and swimmers navigate in unsteady wake flows using limited sensory abilities and actuation energies. Understanding how vortical structures can be leveraged for energy-efficient navigation in unsteady flows is beneficial in developing autonomous navigation for small-scale aerial and marine vehicles. Such vehicles are typically operated with constrained onboard actuation and sensing capabilities, making energy-efficient trajectory planning critically important. This study finds that trajectory planners can leverage three-dimensionality appearing in a complex unsteady wake for efficient navigation using limited flowfield information. This is revealed with comprehensive investigations by finite-horizon model-predictive control for trajectory planning of a swimmer behind a cylinder wake at Re=300. The navigation performance of three-dimensional (3D) cases is compared to scenarios in a two-dimensional (2D) wake. The underactuated swimmer is able to reach the target by leveraging the background flow when the prediction horizon exceeds one-tenth of the wake-shedding period, demonstrating that navigation is feasible with limited information about the flowfield. Further, we identify that the swimmer can leverage the secondary transverse vortical structures to reach the target faster than is achievable navigating in a 2D wake.
We develop a new methodology to select scenarios of DER adoption most critical for distribution grids. Anticipating risks of future voltage and line flow violations due to additional PV adopters is central for utility investment planning but continues to rely on deterministic or ad hoc scenario selection. We propose a highly efficient search framework based on multi-objective Bayesian Optimization. We treat underlying grid stress metrics as computationally expensive black-box functions, approximated via Gaussian Process surrogates and design an acquisition function based on probability of scenarios being Pareto-critical across a collection of line- and bus-based violation objectives. Our approach provides a statistical guarantee and offers an order of magnitude speed-up relative to a conservative exhaustive search. Case studies on realistic feeders with 200-400 buses demonstrate the effectiveness and accuracy of our approach.
Legal professionals often struggle with lengthy judgments and require efficient summarization for quick comprehension. To address this challenge, we investigate the need for structured planning in legal case summarization, particularly through event-centric representations that reflect the narrative nature of legal case documents. We propose our framework, CoPERLex, which operates in three stages: first, it performs content selection to identify crucial information from the judgment; second, the selected content is utilized to generate intermediate plans through event-centric representations modeled as Subject-Verb-Object tuples; and finally, it generates coherent summaries based on both the content and the structured plan. Our experiments on four legal summarization datasets demonstrate the effectiveness of integrating content selection and planning components, highlighting the advantages of event-centric plans over traditional entity-centric approaches in the context of legal judgements.
Problem definition: To mitigate excessive crowding in public transit networks, network expansion is often not feasible due to financial and time constraints. Instead, operators are required to make use of existing infrastructure more efficiently. In this regard, this paper considers the problem of determining lines and frequencies in a public transit system, factoring in the impact of crowding. Methodology: We introduce a novel formulation to address the line planning problem under crowding and propose a mixed-integer second-order cone programming (MI-SOCP) reformulation. Three variants of the cut-and-column generation algorithm with tailored acceleration techniques find near-system-optimal solutions by dynamically generating passenger routes and adding linear cutting planes to deal with the non-linearity introduced by the crowding terms. We find integral solutions using a diving heuristic. In practice, passengers may deviate from system-optimal routes. We, thus, evaluate line plans by computing a user-equilibrium routing based on Wardrop's first principle. Results and implications: We experimentally evaluate the performance of the proposed approaches on both an artificial network and the Beijing metro network. The results demonstrate that our algorithm effectively scales to large-scale instances involving hundreds of stations and candidate lines, and nearly 57,000 origin-destination pairs. We find that considering crowding while developing line plans can significantly reduce crowding, at only a minor expense to the travel time passengers experience. This holds both for system-optimal passenger routing and user-optimal passenger routing, which only differ slightly.
Safety verification for autonomous vehicles (AVs) and ground robots is crucial for ensuring reliable operation given their uncertain environments. Formal language tools provide a robust and sound method to verify safety rules for such complex cyber-physical systems. In this paper, we propose a hybrid approach that combines the strengths of formal verification languages like Linear Temporal Logic (LTL) and Signal Temporal Logic (STL) to generate safe trajectories and optimal control inputs for autonomous vehicle navigation. We implement a symbolic path planning approach using LTL to generate a formally safe reference trajectory. A mixed integer linear programming (MILP) solver is then used on this reference trajectory to solve for the control inputs while satisfying the state, control and safety constraints described by STL. We test our proposed solution on two environments and compare the results with popular path planning algorithms. In contrast to conventional path planning algorithms, our formally safe solution excels in handling complex specification scenarios while ensuring both safety and comparable computation times.
Subgraph matching query is a classic problem in graph data management and has a variety of real-world applications, such as discovering structures in biological or chemical networks, finding communities in social network analysis, explaining neural networks, and so on. To further solve the subgraph matching problem, several recent advanced works attempt to utilize deep-learning-based techniques to handle the subgraph matching query. However, most of these works only obtain approximate results for subgraph matching without theoretical guarantees of accuracy. In this paper, we propose a novel and effective graph neural network (GNN)-based anchor embedding framework (GNN-AE), which allows exact subgraph matching. Unlike GNN-based approximate subgraph matching approaches that only produce inexact results, in this paper, we pioneer a series of concepts related to anchor (including anchor, anchor graph/path, etc.) in subgraph matching and carefully devise the anchor (graph) embedding technique based on GNN models. We transform the subgraph matching problem into a search problem in the embedding space via the anchor (graph & path) embedding techniques. With the proposed anchor matching mechanism, GNN-AE can guarantee subgraph matching has no false dismissals. We design an efficient matching growth algorithm, which can retrieve the locations of all exact matches in parallel. We also propose a cost-model-based DFS query plan to enhance the parallel matching growth algorithm. Through extensive experiments on 6 real-world and 3 synthetic datasets, we confirm the effectiveness and efficiency of our GNN-AE approach for exact subgraph matching.
Background: Multiparametric breast MRI data might improve tumor diagnostics, characterization, and treatment planning. Accurate alignment and delineation of images acquired at different field strengths such as 3T and 7T, remain challenging research tasks. Purpose: To address alignment challenges and enable consistent tumor segmentation across different MRI field strengths. Study type: Retrospective. Subjects: Nine female subjects with breast tumors were involved: six histologically proven invasive ductal carcinomas (IDC) and three fibroadenomas. Field strength/sequence: Imaging was performed at 3T and 7T scanners using post-contrast T1-weighted three-dimensional time-resolved angiography with stochastic trajectories (TWIST) sequence. Assessments: The method's performance for joint image registration and tumor segmentation was evaluated using several quantitative metrics, including signal-to-noise ratio (PSNR), structural similarity index (SSIM), normalized cross-correlation (NCC), Dice coefficient, F1 score, and relative sum of squared differences (rel SSD). Statistical tests: The Pearson correlation coefficient was used to test the relationship between the registration and segmentation metrics. Results: When calculated for each subject individually, the PSNR was in a range from 27.5 to 34.5 dB, and the SSIM was from 82.6 to 92.8%. The model achieved an NCC from 96.4 to 99.3% and a Dice coefficient of 62.9 to 95.3%. The F1 score was between 55.4 and 93.2% and the rel SSD was in the range of 2.0 and 7.5%. The segmentation metrics Dice and F1 Score are highly correlated (0.995), while a moderate correlation between NCC and SSIM (0.681) was found for registration. Data conclusion: Initial results demonstrate that the proposed method may be feasible in providing joint tumor segmentation and registration of MRI data acquired at different field strengths.
The point clouds collected by the Airborne Laser Scanning (ALS) system provide accurate 3D information of urban land covers. By utilizing multi-temporal ALS point clouds, semantic changes in urban area can be captured, demonstrating significant potential in urban planning, emergency management, and infrastructure maintenance. Existing 3D change detection methods struggle to efficiently extract multi-class semantic information and change features, still facing the following challenges: (1) the difficulty of accurately modeling cross-temporal point clouds spatial relationships for effective change feature extraction; (2) class imbalance of change samples which hinders distinguishability of semantic features; (3) the lack of real-world datasets for 3D semantic change detection. To resolve these challenges, we propose the Multi-task Enhanced Cross-temporal Point Transformer (ME-CPT) network. ME-CPT establishes spatiotemporal correspondences between point cloud across different epochs and employs attention mechanisms to jointly extract semantic change features, facilitating information exchange and change comparison. Additionally, we incorporate a semantic segmentation task and through the multi-task training strategy, further enhance the distinguishability of semantic features, reducing the impact of class imbalance in change types. Moreover, we release a 22.5 $km^2$ 3D semantic change detection dataset, offering diverse scenes for comprehensive evaluation. Experiments on multiple datasets show that the proposed MT-CPT achieves superior performance compared to existing state-of-the-art methods. The source code and dataset will be released upon acceptance at https://github.com/zhangluqi0209/ME-CPT.
As a publicly funded body in the UK, Oak National Academy is in a unique position to innovate within this field as we have a comprehensive curriculum of approximately 13,000 open education resources (OER) for all National Curriculum subjects, designed and quality-assured by expert, human teachers. This has provided the corpus of content needed for building a high-quality AI-powered lesson planning tool, Aila, that is free to use and, therefore, accessible to all teachers across the country. Furthermore, using our evidence-informed curriculum principles, we have codified and exemplified each component of lesson design. To assess the quality of lessons produced by Aila at scale, we have developed an AI-powered auto-evaluation agent,facilitating informed improvements to enhance output quality. Through comparisons between human and auto-evaluations, we have begun to refine this agent further to increase its accuracy, measured by its alignment with an expert human evaluator. In this paper we present this iterative evaluation process through an illustrative case study focused on one quality benchmark - the level of challenge within multiple-choice quizzes. We also explore the contribution that this may make to similar projects and the wider sector.
The optimal transportation problem, first suggested by Gaspard Monge in the 18th century and later revived in the 1940s by Leonid Kantorovich, deals with the question of transporting a certain measure to another, using transport maps or transport plans that minimize the total cost of transportation. This problem is very popular since it has a variety of applications in economics, physics, computer science and more. One of the main tools in this theory is the duality theorem, which states that the optimal total cost equals the value of a different optimization problem called the dual problem. In this work, I show how the problem and duality theorem can be generalized to an abstract formulation, in which I omit the use of measures. I show how this generalization implies a wide range of different optimal transport problems, and even other problems from game theory, linear programming and functional analysis. In particular, I show how the optimal transport problem can be generalized to deal with vector measures as a result of the abstract theorem and discuss the properties of this problem: I present its corresponding duality theorem and formulate conditions for the existence of transport plans, transport maps and solutions to the dual problem.
In this paper, we address the problem of manipulating multi-particle aggregates using a bimanual robotic system. Our approach enables the autonomous transport of dispersed particles through a series of shaping and pushing actions using robotically-controlled tools. Achieving this advanced manipulation capability presents two key challenges: high-level task planning and trajectory execution. For task planning, we leverage Vision Language Models (VLMs) to enable primitive actions such as tool affordance grasping and non-prehensile particle pushing. For trajectory execution, we represent the evolving particle aggregate's contour using truncated Fourier series, providing efficient parametrization of its closed shape. We adaptively compute trajectory waypoints based on group cohesion and the geometric centroid of the aggregate, accounting for its spatial distribution and collective motion. Through real-world experiments, we demonstrate the effectiveness of our methodology in actively shaping and manipulating multi-particle aggregates while maintaining high system cohesion.
Signal Temporal Logic (STL) is a powerful specification language for describing complex temporal behaviors of continuous signals, making it well-suited for high-level robotic task descriptions. However, generating executable plans for STL tasks is challenging, as it requires consideration of the coupling between the task specification and the system dynamics. Existing approaches either follow a model-based setting that explicitly requires knowledge of the system dynamics or adopt a task-oriented data-driven approach to learn plans for specific tasks. In this work, we investigate the problem of generating executable STL plans for systems whose dynamics are unknown a priori. We propose a new planning framework that uses only task-agnostic data during the offline training stage, enabling zero-shot generalization to new STL tasks. Our framework is hierarchical, involving: (i) decomposing the STL task into a set of progress and time constraints, (ii) searching for time-aware waypoints guided by task-agnostic data, and (iii) generating trajectories using a pre-trained safe diffusion model. Simulation results demonstrate the effectiveness of our method indeed in achieving zero-shot generalization to various STL tasks.
Trajectory data play a crucial role in many applications, ranging from network optimization to urban planning. Existing studies on trajectory data are task-specific, and their applicability is limited to the specific tasks on which they have been trained, such as generation, recovery, or prediction. However, the potential of a unified model has not yet been fully explored in trajectory modeling. Although various trajectory tasks differ in inputs, outputs, objectives, and conditions, they share common mobility patterns. Based on these common patterns, we can construct a general framework that enables a single model to address different tasks. However, building a trajectory task-general framework faces two critical challenges: 1) the diversity in the formats of different tasks and 2) the complexity of the conditions imposed on different tasks. In this work, we propose a general trajectory modeling framework via masked conditional diffusion (named GenMove). Specifically, we utilize mask conditions to unify diverse formats. To adapt to complex conditions associated with different tasks, we utilize historical trajectory data to obtain contextual trajectory embeddings, which include rich contexts such as spatiotemporal characteristics and user preferences. Integrating the contextual trajectory embedding into diffusion models through a classifier-free guidance approach allows the model to flexibly adjust its outputs based on different conditions. Extensive experiments on mainstream tasks demonstrate that our model significantly outperforms state-of-the-art baselines, with the highest performance improvement exceeding 13% in generation tasks.
This paper proposes a robot action planning scheme that provides an efficient and probabilistically safe plan for a robot interacting with an unconcerned human -- someone who is either unaware of the robot's presence or unwilling to engage in ensuring safety. The proposed scheme is predictive, meaning that the robot is required to predict human actions over a finite future horizon; such predictions are often inaccurate in real-world scenarios. One possible approach to reduce the uncertainties is to provide the robot with the capability of reasoning about the human's awareness of potential dangers. This paper discusses that by using a binary variable, so-called danger awareness coefficient, it is possible to differentiate between concerned and unconcerned humans, and provides a learning algorithm to determine this coefficient by observing human actions. Moreover, this paper argues how humans rely on predictions of other agents' future actions (including those of robots in human-robot interaction) in their decision-making. It also shows that ignoring this aspect in predicting human's future actions can significantly degrade the efficiency of the interaction, causing agents to deviate from their optimal paths. The proposed robot action planning scheme is verified and validated via extensive simulation and experimental studies on a LoCoBot WidowX-250.
Multi-agent reinforcement learning (MARL) demonstrates significant progress in solving cooperative and competitive multi-agent problems in various environments. One of the principal challenges in MARL is the need for explicit prediction of the agents' behavior to achieve cooperation. To resolve this issue, we propose the Shared Recurrent Memory Transformer (SRMT) which extends memory transformers to multi-agent settings by pooling and globally broadcasting individual working memories, enabling agents to exchange information implicitly and coordinate their actions. We evaluate SRMT on the Partially Observable Multi-Agent Pathfinding problem in a toy Bottleneck navigation task that requires agents to pass through a narrow corridor and on a POGEMA benchmark set of tasks. In the Bottleneck task, SRMT consistently outperforms a variety of reinforcement learning baselines, especially under sparse rewards, and generalizes effectively to longer corridors than those seen during training. On POGEMA maps, including Mazes, Random, and MovingAI, SRMT is competitive with recent MARL, hybrid, and planning-based algorithms. These results suggest that incorporating shared recurrent memory into the transformer-based architectures can enhance coordination in decentralized multi-agent systems. The source code for training and evaluation is available on GitHub: https://github.com/Aloriosa/srmt.
Dynamic urban environments, characterized by moving cameras and objects, pose significant challenges for camera trajectory estimation by complicating the distinction between camera-induced and object motion. We introduce MONA, a novel framework designed for robust moving object detection and segmentation from videos shot by dynamic cameras. MONA comprises two key modules: Dynamic Points Extraction, which leverages optical flow and tracking any point to identify dynamic points, and Moving Object Segmentation, which employs adaptive bounding box filtering, and the Segment Anything for precise moving object segmentation. We validate MONA by integrating with the camera trajectory estimation method LEAP-VO, and it achieves state-of-the-art results on the MPI Sintel dataset comparing to existing methods. These results demonstrate MONA's effectiveness for moving object detection and its potential in many other applications in the urban planning field.
In many real-world scenarios, such as gas leak detection or environmental pollutant tracking, solving the Inverse Source Localization and Characterization problem involves navigating complex, dynamic fields with sparse and noisy observations. Traditional methods face significant challenges, including partial observability, temporal and spatial dynamics, out-of-distribution generalization, and reward sparsity. To address these issues, we propose a hierarchical framework that integrates Bayesian inference and reinforcement learning. The framework leverages an attention-enhanced particle filtering mechanism for efficient and accurate belief updates, and incorporates two complementary execution strategies: Attention Particle Filtering Planning and Attention Particle Filtering Reinforcement Learning. These approaches optimize exploration and adaptation under uncertainty. Theoretical analysis proves the convergence of the attention-enhanced particle filter, while extensive experiments across diverse scenarios validate the framework's superior accuracy, adaptability, and computational efficiency. Our results highlight the framework's potential for broad applications in dynamic field estimation tasks.
Active Inference, grounded in the Free Energy Principle, provides a powerful lens for understanding how agents balance exploration and goal-directed behavior in uncertain environments. Here, we propose a new planning framework, that integrates Monte Carlo Tree Search (MCTS) with active inference objectives to systematically reduce epistemic uncertainty while pursuing extrinsic rewards. Our key insight is that MCTS already renowned for its search efficiency can be naturally extended to incorporate free energy minimization by blending expected rewards with information gain. Concretely, the Cross-Entropy Method (CEM) is used to optimize action proposals at the root node, while tree expansions leverage reward modeling alongside intrinsic exploration bonuses. This synergy allows our planner to maintain coherent estimates of value and uncertainty throughout planning, without sacrificing computational tractability. Empirically, we benchmark our planner on a diverse set of continuous control tasks, where it demonstrates performance gains over both standalone CEM and MCTS with random rollouts.
Identifying anatomical landmarks in 3D dental models is vital for orthodontic treatment, yet manual placement is complex and time-consuming. Although some machine learning approaches have been proposed for automatic tooth landmark detection in 3D Intraoral Scans (IOS), none provide a fully end-to-end solution that bypasses teeth segmentation, limiting practical applicability. We introduce CHaRNet (Conditioned Heatmap Regression Network), the first fully end-to-end deep learning framework for tooth landmark detection in 3D IOS. Unlike traditional two-stage workflows that segment teeth before detecting landmarks, CHaRNet directly operates on the input point cloud, thus reducing complexity and computational overhead. Our method integrates four modules: (1) a point cloud encoder, (2) a point cloud decoder with a heatmap regression head, (3) a teeth presence classification head, and (4) the novel Conditioned Heatmap Regression (CHaR) module. By leveraging teeth presence classification, the CHaR module dynamically adapts to missing teeth and enhances detection accuracy in complex dental models. We evaluate CHaRNet using five point cloud learning algorithms on a clinical dataset of 1,214 annotated 3D models. Both the dataset and code will be publicly released to address the lack of open datasets in orthodontics and inspire further research. CHaRNet achieves a Mean Euclidean Distance Error (MEDE) of 0.51 mm on typical dental models and 1.28 mm across all dentition types, with corresponding Mean Success Rates (MSR) of 87.06% and 82.40%, respectively. Notably, it exhibits robust performance on irregular geometries, including models with missing teeth. This end-to-end approach streamlines orthodontic workflows, enhances 3D IOS analysis precision, and supports efficient computer-assisted treatment planning.
World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning policy. To speed up the learning process, the pretrain-finetune paradigm is often used, where online RL is initialized by a pretrained model and a policy learned offline. However, naively performing such initialization in RL may result in dramatic performance degradation during the online interactions in the new task. To tackle this challenge, we first analyze the performance degradation and identify two primary root causes therein: the mismatch of the planning policy and the mismatch of the dynamics model, due to distribution shift. We further analyze the effects of these factors on performance degradation during finetuning, and our findings reveal that the choice of finetuning strategies plays a pivotal role in mitigating these effects. We then introduce AdaWM, an Adaptive World Model based planning method, featuring two key steps: (a) mismatch identification, which quantifies the mismatches and informs the finetuning strategy, and (b) alignment-driven finetuning, which selectively updates either the policy or the model as needed using efficient low-rank updates. Extensive experiments on the challenging CARLA driving tasks demonstrate that AdaWM significantly improves the finetuning process, resulting in more robust and efficient performance in autonomous driving systems.
Boron Neutron Capture Therapy (BNCT) is a form of radiotherapy based on the irradiation of the tumour with a low energy neutron beam, after the administration of a selective drug enriched in boron-10. The therapy exploits the high cross section of thermal neutron capture in boron, generating two low-range charged particles. The availability of accelerators able to generate high-intensity neutron beams via proton nuclear interaction is boosting the construction of new clinical centres. One of these is under development in Italy, using a 5 MeV, 30 mA proton radiofrequency accelerator coupled to a beryllium target, funded by the Complementary Plan to the Recovery and Resilience National Plan, under the project ANTHEM. The present study focuses on radiation protection aspects of patients undergoing BNCT, specifically on the activation of their organs and tissues. A criterion to establish the relevance of such activation after BNCT has been proposed. Based on the current Italian regulatory framework, the level of patient activation following BNCT treatment does not pose a significant radiological concern, even shortly after irradiation. Another aspect is the activation of patient's excretions, which can impact on the design of the building and requires a process for the discharge. The described study contributes to the radiation protection study for the ANTHEM BNCT centre in Italy.
Europe is warming at the fastest rate of all continents, experiencing a temperature increase of about 1{\deg}C higher than the corresponding global increase. Aiming to be the first climate-neutral continent by 2050 under the European Green Deal, Europe requires an in-depth understanding of the potential energy transition pathways. In this paper, we develop four qualitative long-term scenarios covering the European energy landscape, considering key uncertainty pillars -- categorized under social, technological, economic, political, and geopolitical aspects. First, we place the scenarios in a three-dimensional space defined by Social dynamics, Innovation, and Geopolitical instabilities. These scenarios are brought to life by defining their narratives and focus areas according to their location in this three-dimensional space. The scenarios envision diverse futures and include distinct features. The EU Trinity scenario pictures how internal divisions among EU member states, in the context of global geopolitical instability, affect the EU climate targets. The REPowerEU++ scenario outlines the steps needed for a self-sufficient, independent European energy system by 2050. The Go RES scenario examines the feasibility of achieving carbon neutrality earlier than 2050 given favourable uncertain factors. The NECP Essentials scenario extends current national energy and climate plans until 2060 to assess their role in realizing climate neutrality. The scenarios are extended by incorporating policies and economic factors and detailed in a Qualitative to Quantitative (Q2Q) matrix, linking narratives to quantification. Finally, two scenarios are quantified to illustrate the quantification process. All the scenarios are in the process of being quantified and will be openly available and reusable.
The generation of synthetic CT (sCT) images from cone-beam CT (CBCT) data using deep learning methodologies represents a significant advancement in radiation oncology. This systematic review, following PRISMA guidelines and using the PICO model, comprehensively evaluates the literature from 2014 to 2024 on the generation of sCT images for radiation therapy planning in oncology. A total of 35 relevant studies were identified and analyzed, revealing the prevalence of deep learning approaches in the generation of sCT. This review comprehensively covers synthetic CT generation based on CBCT and proton-based studies. Some of the commonly employed architectures explored are convolutional neural networks (CNNs), generative adversarial networks (GANs), transformers, and diffusion models. Evaluation metrics including mean absolute error (MAE), root mean square error (RMSE), peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) consistently demonstrate the comparability of sCT images with gold-standard planning CTs (pCT), indicating their potential to improve treatment precision and patient outcomes. Challenges such as field-of-view (FOV) disparities and integration into clinical workflows are discussed, along with recommendations for future research and standardization efforts. In general, the findings underscore the promising role of sCT-based approaches in personalized treatment planning and adaptive radiation therapy, with potential implications for improved oncology treatment delivery and patient care.
Season and their transitions play a critical role in sharpening ecosystems and human activities, yet traditional classifications, meteorological and astronomical, fail to capture the complexities of biosphere-atmosphere interactions. Conventional definitions often overlook the interplay between climate variables, biosphere processes, and seasonal anticipation, particularly as global climate change disrupts traditional patterns. This study addresses the limitations of current seasonal classification by proposing a framework based on phenological markers such as NDVI, EVI, LAI, fPAR, and the Bowen ratio, using plants as a nature-based sensor of seasonal transitions. Indicators derived from satellite data and ground observations provide robust foundations for defining seasonal boundaries. The normalized daily temperature range (DTRT), validated in crop and orchard regions, is hypothesized as a reliable seasonality index to capture transitions. We demonstrated the alignment of this index with phenological markers across boreal, temperate, and deciduous forests. Analyzing trends, extreme values and inflection points in the seasonality index time series, we established a methodology to identify seasonal onset, duration, and transitions. This universal, scalable classification aligns with current knowledge and perception of seasonal shifts and captures site-specific timing. Findings reveal shifts in the Euro-Mediterranean region, with winters shortening, summers extending, and transitions becoming more pronounced. Effects include the Gulf Stream s influence on milder transitions, urban heat islands accelerating seasonal shifts, and large inland lakes moderating durations. This underscores the importance of understanding seasonal transitions to enable climate change adaptive strategies in agriculture, forestry, urban planning, medicine, trade, marketing, and tourism.
Deep generative models, such as generative adversarial networks and diffusion models, have recently emerged as powerful tools for planning tasks and behavior synthesis in autonomous systems. Various guidance strategies have been introduced to steer the generative process toward outputs that are more likely to satisfy the planning objectives. These strategies avoid the need for model retraining but do not provide any guarantee that the generated outputs will satisfy the desired planning objectives. To address this limitation, we introduce certified guidance, an approach that modifies a generative model, without retraining it, into a new model guaranteed to satisfy a given specification with probability one. We focus on Signal Temporal Logic specifications, which are rich enough to describe nontrivial planning tasks. Our approach leverages neural network verification techniques to systematically explore the latent spaces of the generative models, identifying latent regions that are certifiably correct with respect to the STL property of interest. We evaluate the effectiveness of our method on four planning benchmarks using GANs and diffusion models. Our results confirm that certified guidance produces generative models that are always correct, unlike existing guidance methods that are not certified.
Motion planning is a critical module in autonomous driving, with the primary challenge of uncertainty caused by interactions with other participants. As most previous methods treat prediction and planning as separate tasks, it is difficult to model these interactions. Furthermore, since the route path navigates ego vehicles to a predefined destination, it provides relatively stable intentions for ego vehicles and helps constrain uncertainty. On this basis, we construct Int2Planner, an \textbf{Int}ention-based \textbf{Int}egrated motion \textbf{Planner} achieves multi-modal planning and prediction. Instead of static intention points, Int2Planner utilizes route intention points for ego vehicles and generates corresponding planning trajectories for each intention point to facilitate multi-modal planning. The experiments on the private dataset and the public nuPlan benchmark show the effectiveness of route intention points, and Int2Planner achieves state-of-the-art performance. We also deploy it in real-world vehicles and have conducted autonomous driving for hundreds of kilometers in urban areas. It further verifies that Int2Planner can continuously interact with the traffic environment. Code will be avaliable at https://github.com/cxlz/Int2Planner.
The KOTO II experiment is proposed to measure the branching ratio of the decay $K_L\to\pi^0\nu\bar{\nu}$ at J-PARC. With a beamline to extract long-lived neutral kaons at 5 degrees from a production target, the single event sensitivity of the decay is $8.5\times 10^{-13}$, which is much smaller than the Standard Model prediction $3\times 10^{-11}$. This allows searches for new physics beyond the Standard Model and the first discovery of the decay with a significance exceeding $5\sigma$. As the only experiment proposed in the world dedicated to rare kaon decays, KOTO II will be indispensable in the quest for a complete understanding of flavor dynamics in the quark sector. Moreover, by combining efforts from the kaon community worldwide, we plan to develop the KOTO II detector further and expand the physics reach of the experiment to include measurements of the branching ratio of the $K_L\to\pi^0\ell^+\ell^-$ decays, studies of other $K_L$ decays, and searches for dark photons, axions, and axion-like particles. KOTO II will therefore obtain a comprehensive understanding of $K_L$ decays, providing further constraints on new physics scenarios with existing $K^+$ results.
Light-travel-time delays provide one of the most powerful ways of learning about the structure and kinematics of active galactic nuclei (AGNs). Estimating delays from observations of AGN variability presents statistical challenges because the time series are almost invariably irregularly sampled. Correct assessment of errors in lag estimates is important for evaluating results. The most widely used method of determining phase lags has been the interpolated cross-correlation function method introduced by Gaskell and Sparke (1986, GS). It is shown here that the widely used modified smooth bootstrap method of Peterson et al. (1998) significantly overestimates the error in lags derived using the GS, especially for poorly sampled light curves. The remarkably high accuracy claimed for lags obtained by the JAVELIN method of Zu et al. (2011) (more than an order of magnitude improvement for 25% of cases) is spurious and the accuracy no better than the GS method. A related method proposed by Li et al. (2013) suffers from similar but less serious problems. A slightly modified version of the analytic formula of Gaskell and Peterson (1987) gives an easy and accurate way of estimating lag errors for well-sampled, high-quality data. The width of the continuum autocorrelation function is shown to be proportional to the square root of the luminosity. This is useful in planning observing campaigns. The discrete correlation function method is less powerful than the GS method and for many typical situations gives errors in the lag twice as large as those of the GS method.
Agriculture plays a crucial role in the global economy and social stability, and accurate crop yield prediction is essential for rational planting planning and decision-making. This study focuses on crop yield Time-Series Data prediction. Considering the crucial significance of agriculture in the global economy and social stability and the importance of accurate crop yield prediction for rational planting planning and decision-making, this research uses a dataset containing multiple crops, multiple regions, and data over many years to deeply explore the relationships between climatic factors (average rainfall, average temperature) and agricultural inputs (pesticide usage) and crop yield. Multiple hybrid machine learning models such as Linear Regression, Random Forest, Gradient Boost, XGBoost, KNN, Decision Tree, and Bagging Regressor are adopted for yield prediction. After evaluation, it is found that the Random Forest and Bagging Regressor models perform excellently in predicting crop yield with high accuracy and low error.As agricultural data becomes increasingly rich and time-series prediction techniques continue to evolve, the results of this study contribute to advancing the practical application of crop yield prediction in agricultural production management. The integration of time-series analysis allows for more dynamic, data-driven decision-making, enhancing the accuracy and reliability of crop yield forecasts over time.
Existing approaches to enforcing design constraints in Reinforcement Learning (RL) applications often rely on training-time penalties in the reward function or training/inference-time invalid action masking, but these methods either cannot be modified after training, or are limited in the types of constraints that can be implemented. To address this limitation, we propose Reinforcement Learning Constrained Beam Search (RLCBS) for inference-time refinement in combinatorial optimization problems. This method respects flexible, inference-time constraints that support exclusion of invalid actions and forced inclusion of desired actions, and employs beam search to maximize sequence probability for more sensible constraint incorporation. RLCBS is extensible to RL-based planning and optimization problems that do not require real-time solution, and we apply the method to optimize process parameters for a novel modular testbed for paper drying. An RL agent is trained to minimize energy consumption across varying machine speed levels by generating optimal dryer module and air supply temperature configurations. Our results demonstrate that RLCBS outperforms NSGA-II under complex design constraints on drying module configurations at inference-time, while providing a 2.58-fold or higher speed improvement.
Blood vessels (BVs) play a critical role in the Tumor Micro-Environment (TME), potentially influencing cancer progression and treatment response. However, manually quantifying BVs in Hematoxylin and Eosin (H&E) stained images is challenging and labor-intensive due to their heterogeneous appearances. We propose a novel approach of constructing guiding maps to improve the performance of state-of-the-art segmentation models for BV segmentation, the guiding maps encourage the models to learn representative features of BVs. This is particularly beneficial for computational pathology, where labeled training data is often limited and large models are prone to overfitting. We have quantitative and qualitative results to demonstrate the efficacy of our approach in improving segmentation accuracy. In future, we plan to validate this method to segment BVs across various tissue types and investigate the role of cellular structures in relation to BVs in the TME.
For many tasks, multi-robot teams often provide greater efficiency, robustness, and resiliency. However, multi-robot collaboration in real-world scenarios poses a number of major challenges, especially when dynamic robots must balance competing objectives like formation control and obstacle avoidance in the presence of stochastic dynamics and sensor uncertainty. In this paper, we propose a distributed, multi-agent receding-horizon feedback motion planning approach using Probably Approximately Correct Nonlinear Model Predictive Control (PAC-NMPC) that is able to reason about both model and measurement uncertainty to achieve robust multi-agent formation control while navigating cluttered obstacle fields and avoiding inter-robot collisions. Our approach relies not only on the underlying PAC-NMPC algorithm but also on a terminal cost-function derived from gyroscopic obstacle avoidance. Through numerical simulation, we show that our distributed approach performs on par with a centralized formulation, that it offers improved performance in the case of significant measurement noise, and that it can scale to more complex dynamical systems.
The improved competence of generative models can help building multi-modal virtual assistants that leverage modalities beyond language. By observing humans performing multi-step tasks, one can build assistants that have situational awareness of actions and tasks being performed, enabling them to cater assistance based on this understanding. In this paper, we develop a Context-aware Instructional Task Assistant with Multi-modal Large Language Models (InsTALL) that leverages an online visual stream (e.g. a user's screen share or video recording) and responds in real-time to user queries related to the task at hand. To enable useful assistance, InsTALL 1) trains a multi-modal model on task videos and paired textual data, and 2) automatically extracts task graph from video data and leverages it at training and inference time. We show InsTALL achieves state-of-the-art performance across proposed sub-tasks considered for multimodal activity understanding -- task recognition (TR), action recognition (AR), next action prediction (AP), and plan prediction (PP) -- and outperforms existing baselines on two novel sub-tasks related to automatic error identification.
Health data is one of the most sensitive data for people, which attracts the attention of malicious activities. We propose an open-source health data management framework, that follows a patient-centric approach. The proposed framework implements the Self-Sovereign Identity paradigm with innovative technologies such as Decentralized Identifiers and Verifiable Credentials. The framework uses Blockchain technology to provide immutability, verifiable data registry, and auditability, as well as an agent-based model to provide protection and privacy for the patient data. We also define different use cases regarding the daily patient-practitioner-laboratory interactions and specific functions to cover patient data loss, data access revocation, and emergency cases where patients are unable to give consent and access to their data. To address this design, a proof of concept is created with an interaction between patient and doctor. The most feasible technologies are selected and the created design is validated. We discuss the differences and novelties of this framework, which includes the patient-centric approach also for data storage, the designed recovery and emergency plan, the defined backup procedure, and the selected blockchain platform.
Agile healthcare frameworks, derived from methodologies in IT and manufacturing, offer transformative potential for low-income regions. This study explores Agile integration in resource-constrained environments, focusing on Ghana. Key benefits include adaptability, iterative planning, and stakeholder collaboration to address infrastructure gaps, workforce shortages, and the "know-do gap." Digital tools like mobile health (mHealth) applications and the District Health Information Management System (DHIMS) demonstrate Agile scalability and efficacy in improving outcomes and resource allocation. Policy alignment, such as through Ghana's National Health Insurance Scheme (NHIS), is crucial for sustaining these practices. Findings reveal Agile ability to enable real-time decision-making, foster community engagement, and drive interdisciplinary collaboration. This paper provides actionable strategies and systemic innovations, positioning Agile as a scalable model for equitable, high-quality care delivery in other low-income regions.
We introduce a modeling framework for manipulation planning based on the formulation of the dynamics as a projected dynamical system. This method uses implicit signed distance functions and their gradients to formulate an equivalent gradient complementarity system. The optimal control problem is then solved via a direct method, discretized using finite-elements with switch detection. An extension to this approach is provided in the form of a friction formulation commonly used in quasi-static models. We show that this approach is able to generate trajectories for problems including multiple pushers, friction, and non-convex objects modeled as unions of convex ellipsoids with reasonable computational effort.
Radiotherapy (RT) planning is complex, subjective, and time-intensive. Advances in artificial intelligence (AI) promise to improve its precision, efficiency, and consistency, but progress is often limited by the scarcity of large, standardized datasets. To address this, we introduce the Automated Iterative RT Planning (AIRTP) system, a scalable solution for generating high-quality treatment plans. This scalable solution is designed to generate substantial volumes of consistently high-quality treatment plans, overcoming a key obstacle in the advancement of AI-driven RT planning. Our AIRTP pipeline adheres to clinical guidelines and automates essential steps, including organ-at-risk (OAR) contouring, helper structure creation, beam setup, optimization, and plan quality improvement, using AI integrated with RT planning software like Eclipse of Varian. Furthermore, a novel approach for determining optimization parameters to reproduce 3D dose distributions, i.e. a method to convert dose predictions to deliverable treatment plans constrained by machine limitations. A comparative analysis of plan quality reveals that our automated pipeline produces treatment plans of quality comparable to those generated manually, which traditionally require several hours of labor per plan. Committed to public research, the first data release of our AIRTP pipeline includes nine cohorts covering head-and-neck and lung cancer sites to support an AAPM 2025 challenge. This data set features more than 10 times the number of plans compared to the largest existing well-curated public data set to our best knowledge. Repo:{https://github.com/RiqiangGao/GDP-HMM_AAPMChallenge}
Most current AI models have little ability to store and later retrieve a record or representation of what they do. In human cognition, episodic memories play an important role in both recall of the past as well as planning for the future. The ability to form and use episodic memories would similarly enable a broad range of improved capabilities in an AI agent that interacts with and takes actions in the world. Researchers have begun directing more attention to developing memory abilities in AI models. It is therefore likely that models with such capability will be become widespread in the near future. This could in some ways contribute to making such AI agents safer by enabling users to better monitor, understand, and control their actions. However, as a new capability with wide applications, we argue that it will also introduce significant new risks that researchers should begin to study and address. We outline these risks and benefits and propose four principles to guide the development of episodic memory capabilities so that these will enhance, rather than undermine, the effort to keep AI safe and trustworthy.
Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to perceive and act in mobile environments. However, current approaches face significant limitations: they fall short in addressing real-world human needs, struggle with reasoning-intensive and long-horizon tasks, and lack mechanisms to learn and improve from prior experiences. To overcome these challenges, we introduce Mobile-Agent-E, a hierarchical multi-agent framework capable of self-evolution through past experience. By hierarchical, we mean an explicit separation of high-level planning and low-level action execution. The framework comprises a Manager, responsible for devising overall plans by breaking down complex tasks into subgoals, and four subordinate agents--Perceptor, Operator, Action Reflector, and Notetaker--which handle fine-grained visual perception, immediate action execution, error verification, and information aggregation, respectively. Mobile-Agent-E also features a novel self-evolution module which maintains a persistent long-term memory comprising Tips and Shortcuts. Tips are general guidance and lessons learned from prior tasks on how to effectively interact with the environment. Shortcuts are reusable, executable sequences of atomic operations tailored for specific subroutines. The inclusion of Tips and Shortcuts facilitates continuous refinement in performance and efficiency. Alongside this framework, we introduce Mobile-Eval-E, a new benchmark featuring complex mobile tasks requiring long-horizon, multi-app interactions. Empirical results show that Mobile-Agent-E achieves a 22% absolute improvement over previous state-of-the-art approaches across three foundation model backbones. Project page: https://x-plug.github.io/MobileAgent.
Fully autonomous vehicles (AVs) continue to spark immense global interest, yet predictions on when they will operate safely and broadly remain heavily debated. This paper synthesizes two distinct research traditions: computational complexity and algorithmic constraints versus reliability growth modeling and real-world testing to form an integrated, quantitative timeline for future AV deployment. We propose a mathematical framework that unifies NP-hard multi-agent path planning analyses, high-performance computing (HPC) projections, and extensive Crow-AMSAA reliability growth calculations, factoring in operational design domain (ODD) variations, severity, and partial vs. full domain restrictions. Through category-specific case studies (e.g., consumer automotive, robo-taxis, highway trucking, industrial and defense applications), we show how combining HPC limitations, safety demonstration requirements, production/regulatory hurdles, and parallel/serial test strategies can push out the horizon for universal Level 5 deployment by up to several decades. Conversely, more constrained ODDs; like fenced industrial sites or specialized defense operations; may see autonomy reach commercial viability in the near-to-medium term. Our findings illustrate that while targeted domains can achieve automated service sooner, widespread driverless vehicles handling every environment remain far from realized. This paper thus offers a unique and rigorous perspective on why AV timelines extend well beyond short-term optimism, underscoring how each dimension of complexity and reliability imposes its own multi-year delays. By quantifying these constraints and exploring potential accelerators (e.g., advanced AI hardware, infrastructure up-grades), we provide a structured baseline for researchers, policymakers, and industry stakeholders to more accurately map their expectations and investments in AV technology.
Lane-changing maneuvers, particularly those executed abruptly or in risky situations, are a significant cause of road traffic accidents. However, current research mainly focuses on predicting safe lane changes. Furthermore, existing accident datasets are often based on images only and lack comprehensive sensory data. In this work, we focus on predicting risky lane changes using the CRASH dataset (our own collected dataset specifically for risky lane changes), and safe lane changes (using the HighD dataset). Then, we leverage KG and Bayesian inference to predict these maneuvers using linguistic contextual information, enhancing the model's interpretability and transparency. The model achieved a 91.5% f1-score with anticipation time extending to four seconds for risky lane changes, and a 90.0% f1-score for predicting safe lane changes with the same anticipation time. We validate our model by integrating it into a vehicle within the CARLA simulator in scenarios that involve risky lane changes. The model managed to anticipate sudden lane changes, thus providing automated vehicles with further time to plan and execute appropriate safe reactions. Finally, to enhance the explainability of our model, we utilize RAG to provide clear and natural language explanations for the given prediction.
Software security is of utmost importance for most software systems. Developers must systematically select, plan, design, implement, and especially, maintain and evolve security features -- functionalities to mitigate attacks or protect personal data such as cryptography or access control -- to ensure the security of their software. Although security features are usually available in libraries, integrating security features requires writing and maintaining additional security-critical code. While there have been studies on the use of such libraries, surprisingly little is known about how developers engineer security features, how they select what security features to implement and which ones may require custom implementation, and the implications for maintenance. As a result, we currently rely on assumptions that are largely based on common sense or individual examples. However, to provide them with effective solutions, researchers need hard empirical data to understand what practitioners need and how they view security -- data that we currently lack. To fill this gap, we contribute an exploratory study with 26 knowledgeable industrial participants. We study how security features of software systems are selected and engineered in practice, what their code-level characteristics are, and what challenges practitioners face. Based on the empirical data gathered, we provide insights into engineering practices and validate four common assumptions.
This study presents a comprehensive analysis of four significant California wildfires: Palisades, Eaton, Kenneth, and Hurst, examining their impacts through multiple dimensions, including land cover change, jurisdictional management, structural damage, and demographic vulnerability. Using the Chebyshev-Kolmogorov-Arnold network model applied to Sentinel-2 imagery, the extent of burned areas was mapped, ranging from 315.36 to 10,960.98 hectares. Our analysis revealed that shrubland ecosystems were consistently the most affected, comprising 57.4-75.8% of burned areas across all events. The jurisdictional assessment demonstrated varying management complexities, from singular authority (98.7% in the Palisades Fire) to distributed management across multiple agencies. A structural impact analysis revealed significant disparities between urban interface fires (Eaton: 9,869 structures; Palisades: 8,436 structures) and rural events (Kenneth: 24 structures; Hurst: 17 structures). The demographic analysis showed consistent gender distributions, with 50.9% of the population identified as female and 49.1% as male. Working-age populations made up the majority of the affected populations, ranging from 53.7% to 54.1%, with notable temporal shifts in post-fire periods. The study identified strong correlations between urban interface proximity, structural damage, and population exposure. The Palisades and Eaton fires affected over 20,000 people each, compared to fewer than 500 in rural events. These findings offer valuable insights for the development of targeted wildfire management strategies, particularly in wildland urban interface zones, and emphasize the need for age- and gender-conscious approaches in emergency response planning.
We present a simple and easy-to-implement algorithm to detect plan infeasibility in kinematic motion planning. Our method involves approximating the robot's configuration space to a discrete space, where each degree of freedom has a finite set of values. The obstacle region separates the free configuration space into different connected regions. For a path to exist between the start and goal configurations, they must lie in the same connected region of the free space. Thus, to ascertain plan infeasibility, we merely need to sample adequate points from the obstacle region that isolate start and goal. Accordingly, we progressively construct the configuration space by sampling from the discretized space and updating the bitmap cells representing obstacle regions. Subsequently, we partition this partially built configuration space to identify different connected components within it and assess the connectivity of the start and goal cells. We illustrate this methodology on five different scenarios with configuration spaces having up to 5 degree-of-freedom (DOF).
A Grad-Shafranov equation (GSE) valid for compact quasisymmetric stellarators is derived by an asymptotic expansion around a vacuum field carried to first order. We obtain an equation for the existence of flux surfaces leading up to the GSE. The flux surface label must simultaneously satisfy the existence equation and the GSE, which generally leads to an overdetermined problem. We show how the overdetermined problem can be resolved within our model for a class of hybrid devices similar to that studied by Henneberg and Plunk (S. Henneberg and G. Plunk, PRR 2024). We are also able to solve the existence equation for flux surfaces analytically in the most general case by introducing a special coordinate system. In future work, we plan to carry out an optimization seeking to minimize the error in our GSE while obeying the flux surface existence equation. This should be faster than a conventional stellarator optimization and will allow us to find solutions outside the class of hybrid devices.
Payment Channel Networks (PCNs) are a method for improving the scaling and latency of cryptocurrency transactions. For a payment to be made between two peers in a PCN, a feasible low-fee path in the network must be planned. Many PCN path planning algorithms use a search algorithm that is a variant of Dijkstra's algorithm. In this article, we prove the correctness and computational complexity of this algorithm. Specifically, we show that, if the PCN satisfies a consistency property relating to the fees charged by payment channels, the algorithm is correct and has polynomial computational complexity. However, in the general case, the algorithm is not correct and the path planning problem is NP-hard. These newly developed results can be used to inform the development of new or existing PCNs amenable to path planning. For example, we show that the Lightning Network, which is the most widely used PCN and is built on the Bitcoin cryptocurrency, currently satisfies the above consistency property. As a second contribution, we demonstrate that a small modification to the above path planning algorithm which, although having the same asymptotic computational complexity, empirically shows better performance. This modification involves the use of a bidirectional search and is empirically evaluated by simulating transactions on the Lightning Network.
Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. In particular, world models have emerged as a linchpin technology, offering high-fidelity representations of the driving environment that integrate multi-sensor data, semantic cues, and temporal dynamics. This paper systematically reviews recent advances in world models for autonomous driving, proposing a three-tiered taxonomy: 1) Generation of Future Physical World, covering image-, BEV-, OG-, and PC-based generation methods that enhance scene evolution modeling through diffusion models and 4D occupancy forecasting; 2) Behavior Planning for Intelligent Agents, combining rule-driven and learning-based paradigms with cost map optimization and reinforcement learning for trajectory generation in complex traffic conditions; 3) Interaction Between Prediction and Planning, achieving multi-agent collaborative decision-making through latent space diffusion and memory-augmented architectures. The study further analyzes training paradigms including self-supervised learning, multimodal pretraining, and generative data augmentation, while evaluating world models' performance in scene understanding and motion prediction tasks. Future research must address key challenges in self-supervised representation learning, long-tail scenario generation, and multimodal fusion to advance the practical deployment of world models in complex urban environments. Overall, our comprehensive analysis provides a theoretical framework and technical roadmap for harnessing the transformative potential of world models in advancing safe and reliable autonomous driving solutions.
Urban prediction tasks, such as forecasting traffic flow, temperature, and crime rates, are crucial for efficient urban planning and management. However, existing Spatiotemporal Graph Neural Networks (ST-GNNs) often rely solely on accuracy, overlooking spatial and demographic disparities in their predictions. This oversight can lead to imbalanced resource allocation and exacerbate existing inequities in urban areas. This study introduces a Residual-Aware Attention (RAA) Block and an equality-enhancing loss function to address these disparities. By adapting the adjacency matrix during training and incorporating spatial disparity metrics, our approach aims to reduce local segregation of residuals and errors. We applied our methodology to urban prediction tasks in Chicago, utilizing a travel demand dataset as an example. Our model achieved a 48% significant improvement in fairness metrics with only a 9% increase in error metrics. Spatial analysis of residual distributions revealed that models with RAA Blocks produced more equitable prediction results, particularly by reducing errors clustered in central regions. Attention maps demonstrated the model's ability to dynamically adjust focus, leading to more balanced predictions. Case studies of various community areas in Chicago further illustrated the effectiveness of our approach in addressing spatial and demographic disparities, supporting more balanced and equitable urban planning and policy-making.
Robots operating in complex and unknown environments frequently require geometric-semantic representations of the environment to safely perform their tasks. While inferring the environment, they must account for many possible scenarios when planning future actions. Since objects' class types are discrete and the robot's self-pose and the objects' poses are continuous, the environment can be represented by a hybrid discrete-continuous belief which is updated according to models and incoming data. Prior probabilities and observation models representing the environment can be learned from data using deep learning algorithms. Such models often couple environmental semantic and geometric properties. As a result, semantic variables are interconnected, causing semantic state space dimensionality to increase exponentially. In this paper, we consider planning under uncertainty using partially observable Markov decision processes (POMDPs) with hybrid semantic-geometric beliefs. The models and priors consider the coupling between semantic and geometric variables. Within POMDP, we introduce the concept of semantically aware safety. Obtaining representative samples of the theoretical hybrid belief, required for estimating the value function, is very challenging. As a key contribution, we develop a novel form of the hybrid belief and leverage it to sample representative samples. We show that under certain conditions, the value function and probability of safety can be calculated efficiently with an explicit expectation over all possible semantic mappings. Our simulations show that our estimates of the objective function and probability of safety achieve similar levels of accuracy compared to estimators that run exhaustively on the entire semantic state-space using samples from the theoretical hybrid belief. Nevertheless, the complexity of our estimators is polynomial rather than exponential.
Rapid advancements in autonomous vehicles (AVs) are poised to revolutionize transportation and communities, including disaster evacuations, particularly through the deployment of Shared Autonomous Vehicles (SAVs). Despite the potential, the use of SAVs in rural disaster evacuations remains an underexplored area. To address this gap, this study proposes a simulation-based framework that integrates both mathematical programming and SUMO traffic simulation to deploy SAVs in pre- and post-disaster evacuations in rural areas. The framework prioritizes the needs of vulnerable groups, including individuals with disabilities, limited English proficiency, and elderly residents. Sumter County, Florida, serves as the case study due to its unique characteristics: a high concentration of vulnerable individuals and limited access to public transportation, making it one of the most transportation-insecure counties in the state. These conditions present significant challenges for evacuation planning in the region. To explore potential solutions, we conducted mass evacuation simulations by incorporating SAVs across seven scenarios. These scenarios represented varying SAV penetration levels, ranging from 20% to 100% of the vulnerable population, and were compared to a baseline scenario using only passenger cars. Additionally, we examined both pre-disaster and post-disaster conditions, accounting for infrastructure failures and road closures. According to the simulation results, higher SAV integration significantly improves traffic distribution and reduces congestion. Scenarios featuring more SAVs exhibited lower congestion peaks and more stable traffic flow. Conversely, mixed traffic environments demonstrate reduced average speeds attributable to interactions between SAVs and passenger cars, while exclusive use of SAVs results in higher speeds and more stable travel patterns.
Efficient and socially equitable restoration of transportation networks post disasters is crucial for community resilience and access to essential services. The ability to rapidly recover critical infrastructure can significantly mitigate the impacts of disasters, particularly in underserved communities where prolonged isolation exacerbates vulnerabilities. Traditional restoration methods prioritize functionality over computational efficiency and equity, leaving low-income communities at a disadvantage during recovery. To address this gap, this research introduces a novel framework that combines quantum computing technology with an equity-focused approach to network restoration. Optimization of road link recovery within budget constraints is achieved by leveraging D Wave's hybrid quantum solver, which targets the connectivity needs of low, average, and high income communities. This framework combines computational speed with equity, ensuring priority support for underserved populations. Findings demonstrate that this hybrid quantum solver achieves near instantaneous computation times of approximately 8.7 seconds across various budget scenarios, significantly outperforming the widely used genetic algorithm. It offers targeted restoration by first aiding low-income communities and expanding aid as budgets increase, aligning with equity goals. This work showcases quantum computing's potential in disaster recovery planning, providing a rapid and equitable solution that elevates urban resilience and social sustainability by aiding vulnerable populations in disasters.
Accurate and efficient segmentation of brain tumors is critical for diagnosis, treatment planning, and monitoring in clinical practice. In this study, we present an enhanced ResUNet architecture for automatic brain tumor segmentation, integrating an EfficientNetB0 encoder, a channel attention mechanism, and an Atrous Spatial Pyramid Pooling (ASPP) module. The EfficientNetB0 encoder leverages pre-trained features to improve feature extraction efficiency, while the channel attention mechanism enhances the model's focus on tumor-relevant features. ASPP enables multiscale contextual learning, crucial for handling tumors of varying sizes and shapes. The proposed model was evaluated on two benchmark datasets: TCGA LGG and BraTS 2020. Experimental results demonstrate that our method consistently outperforms the baseline ResUNet and its EfficientNet variant, achieving Dice coefficients of 0.903 and 0.851 and HD95 scores of 9.43 and 3.54 for whole tumor and tumor core regions on the BraTS 2020 dataset, respectively. compared with state-of-the-art methods, our approach shows competitive performance, particularly in whole tumor and tumor core segmentation. These results indicate that combining a powerful encoder with attention mechanisms and ASPP can significantly enhance brain tumor segmentation performance. The proposed approach holds promise for further optimization and application in other medical image segmentation tasks.
Bed-to-wheelchair transferring is a ubiquitous activity of daily living (ADL), but especially challenging for caregiving robots with limited payloads. We develop a novel algorithm that leverages the presence of other assistive devices: a Hoyer sling and a wheelchair for coarse manipulation of heavy loads, alongside a robot arm for fine-grained manipulation of deformable objects (Hoyer sling straps). We instrument the Hoyer sling and wheelchair with actuators and sensors so that they can become intelligent agents in the algorithm. We then focus on one subtask of the transferring ADL -- tying Hoyer sling straps to the sling bar -- that exemplifies the challenges of transfer: multi-agent planning, deformable object manipulation, and generalization to varying hook shapes, sling materials, and care recipient bodies. To address these challenges, we propose CART-MPC, a novel algorithm based on turn-taking multi-agent model predictive control that uses a learned neural dynamics model for a keypoint-based representation of the deformable Hoyer sling strap, and a novel cost function that leverages linking numbers from knot theory and neural amortization to accelerate inference. We validate it in both RCareWorld simulation and real-world environments. In simulation, CART-MPC successfully generalizes across diverse hook designs, sling materials, and care recipient body shapes. In the real world, we show zero-shot sim-to-real generalization capabilities to tie deformable Hoyer sling straps on a sling bar towards transferring a manikin from a hospital bed to a wheelchair. See our website for supplementary materials: https://emprise.cs.cornell.edu/cart-mpc/.
Wind energy is the most mature renewable energy technology, however, its exploitation in cities is often met with skepticism. Thanks to their ability to operate effectively at low wind from any direction, vertical axis wind turbines (VAWTs) offer an attractive opportunity for wind energy harvesting in cities, but limited evidence exists on their potential in complex urban environments, and the role of different geographical settings, local meteorological conditions, and urban characteristics remains unclear. Here we use realistic Weather Research and Forecast model high-resolution wind speed simulations alongside representative VAWT power curves to quantify the range of micro-generation potentials at the annual, seasonal, and diurnal scale across two Swiss cities (Lausanne and Geneva) residing in complex terrain. Our results show that Lausanne generally experiences higher (+24%) wind speed than Geneva. Both cities present the greatest micro-generation potential during the summer months, although Lausanne shows non-negligible potential also during the wintertime. Wind speed is higher during the nighttime in Lausanne and during the daytime in Geneva, due to the different interaction between the local lake-breeze circulation and the synoptic flow. Simulated performance of case-study VAWTs is dominated by cut-in wind speed and power curve inflection point. On average, in 2022, an individual VAWT would have produced 2665 kWh of total annual electricity, equivalent to 16.5 square meters of photovoltaic panels. These results highlight the need for research on urban wind energy featuring detailed city-scale assessments that account for urban heterogeneities and regional circulation patters, to inform future planning investment and engineering development.
We present the Unit Region Encoding of floorplans, which is a unified and compact geometry-aware encoding representation for various applications, ranging from interior space planning, floorplan metric learning to floorplan generation tasks. The floorplans are represented as the latent encodings on a set of boundary-adaptive unit region partition based on the clustering of the proposed geometry-aware density map. The latent encodings are extracted by a trained network (URE-Net) from the input dense density map and other available semantic maps. Compared to the over-segmented rasterized images and the room-level graph structures, our representation can be flexibly adapted to different applications with the sliced unit regions while achieving higher accuracy performance and better visual quality. We conduct a variety of experiments and compare to the state-of-the-art methods on the aforementioned applications to validate the superiority of our representation, as well as extensive ablation studies to demonstrate the effect of our slicing choices.
Hair styling is a crucial aspect of personal grooming, significantly influenced by the appearance of front hair. While brushing is commonly used both to detangle hair and for styling purposes, existing research primarily focuses on robotic systems for detangling hair, with limited exploration into robotic hair styling. This research presents a novel robotic system designed to automatically adjust front hairstyles, with an emphasis on path planning for root-centric strand adjustment. The system utilizes images to compare the current hair state with the desired target state through an orientation map of hair strands. By concentrating on the differences in hair orientation and specifically targeting adjustments at the root of each strand, the system performs detailed styling tasks. The path planning approach ensures effective alignment of the hairstyle with the target, and a closed-loop mechanism refines these adjustments to accurately evolve the hairstyle towards the desired outcome. Experimental results demonstrate that the proposed system achieves a high degree of similarity and consistency in front hair styling, showing promising results for automated, precise hairstyle adjustments.
Cephalometric analysis is essential for the diagnosis and treatment planning of orthodontics. In lateral cephalograms, however, the manual detection of anatomical landmarks is a time-consuming procedure. Deep learning solutions hold the potential to address the time constraints associated with certain tasks; however, concerns regarding their performance have been observed. To address this critical issue, we proposed an end-to-end cascaded deep learning framework (Self-CepahloNet) for the task, which demonstrated benchmark performance over the ISBI 2015 dataset in predicting 19 dental landmarks. Due to their adaptive nodal capabilities, Self-ONN (self-operational neural networks) demonstrate superior learning performance for complex feature spaces over conventional convolutional neural networks. To leverage this attribute, we introduced a novel self-bottleneck in the HRNetV2 (High Resolution Network) backbone, which has exhibited benchmark performance on the ISBI 2015 dataset for the dental landmark detection task. Our first-stage results surpassed previous studies, showcasing the efficacy of our singular end-to-end deep learning model, which achieved a remarkable 70.95% success rate in detecting cephalometric landmarks within a 2mm range for the Test1 and Test2 datasets. Moreover, the second stage significantly improved overall performance, yielding an impressive 82.25% average success rate for the datasets above within the same 2mm distance. Furthermore, external validation was conducted using the PKU cephalogram dataset. Our model demonstrated a commendable success rate of 75.95% within the 2mm range.
We investigate a scenario where a chaser spacecraft or satellite equipped with a monocular camera navigates in close proximity to a target spacecraft. The satellite's primary objective is to construct a representation of the operational environment and localize itself within it, utilizing the available image data. We frame the joint task of state trajectory and map estimation as an instance of smoothing-based simultaneous localization and mapping (SLAM), where the underlying structure of the problem is represented as a factor graph. Rather than considering estimation and planning as separate tasks, we propose to control the camera observations to actively reduce the uncertainty of the estimation variables, the spacecraft state, and the map landmarks. This is accomplished by adopting an information-theoretic metric to reason about the impact of candidate actions on the evolution of the belief state. Numerical simulations indicate that the proposed method successfully captures the interplay between planning and estimation, hence yielding reduced uncertainty and higher accuracy when compared to commonly adopted passive sensing strategies.
Traffic simulation models have long been popular in modern traffic planning and operation applications. Efficient calibration of simulation models is usually a crucial step in a simulation study. However, traditional calibration procedures are often resource-intensive and time-consuming, limiting the broader adoption of simulation models. In this study, a vehicle trajectory-based automatic calibration framework for mesoscopic traffic simulation is proposed. The framework incorporates behavior models from both the demand and the supply sides of a traffic network. An optimization-based network flow estimation model is designed for demand and route choice calibration. Dimensionality reduction techniques are incorporated to define the zoning system and the path choice set. A stochastic approximation model is established for capacity and driving behavior parameter calibration. The applicability and performance of the calibration framework are demonstrated through a case study for the City of Birmingham network in Michigan.
High-resolution land cover mapping plays a crucial role in addressing a wide range of global challenges, including urban planning, environmental monitoring, disaster response, and sustainable development. However, creating accurate, large-scale land cover datasets remains a significant challenge due to the inherent complexities of geospatial data, such as diverse terrain, varying sensor modalities, and atmospheric conditions. Synthetic Aperture Radar (SAR) imagery, with its ability to penetrate clouds and capture data in all-weather, day-and-night conditions, offers unique advantages for land cover mapping. Despite these strengths, the lack of benchmark datasets tailored for SAR imagery has limited the development of robust models specifically designed for this data modality. To bridge this gap and facilitate advancements in SAR-based geospatial analysis, we introduce OpenEarthMap-SAR, a benchmark SAR dataset, for global high-resolution land cover mapping. OpenEarthMap-SAR consists of 1.5 million segments of 5033 aerial and satellite images with the size of 1024$\times$1024 pixels, covering 35 regions from Japan, France, and the USA, with partially manually annotated and fully pseudo 8-class land cover labels at a ground sampling distance of 0.15--0.5 m. We evaluated the performance of state-of-the-art methods for semantic segmentation and present challenging problem settings suitable for further technical development. The dataset also serves the official dataset for IEEE GRSS Data Fusion Contest Track I. The dataset has been made publicly available at https://zenodo.org/records/14622048.
This book covers static and dynamic traffic assignment models used in transportation planning and network analysis. Traffic assignment is the final step in the traditional planning process, and recent decades have seen many advances in formulating and solving such models. The book discusses classical solution methods alongside recent ones used in contemporary planning software. The primary audience for the book is graduate students new to transportation network analysis, and to this end there are appendices providing general mathematical background, and more specific background in formulating optimization problems. We have also included appendices discussing more general optimization applications outside of traffic assignment. We believe the book is also of interest to practitioners seeking to understand recent advances in network analysis, and to researchers wanting a unified reference for traffic assignment content. A second volume is currently under preparation, and will cover transit, freight, and logistics models in transportation networks. A free PDF version of the text will always be available online at https://sboyles.github.io/blubook.html. We will periodically post updated versions of the text at this link, along with slides and other instructor resources.
Distributing computations among agents in large networks reduces computational effort in multi-agent path finding (MAPF). One distribution strategy is prioritized planning (PP). In PP, we couple and prioritize interacting agents to achieve a desired behavior across all agents in the network. We characterize the interaction with a directed acyclic graph (DAG). The computation time for solving MAPF problem using PP is mainly determined through the longest path in this DAG. The longest path depends on the fixed undirected coupling graph and the variable prioritization. The approaches from literature to prioritize agents are numerous and pursue various goals. This article presents an approach for prioritization in PP to reduce the longest path length in the coupling DAG and thus the computation time for MAPF using PP. We prove that this problem can be mapped to a graph-coloring problem, in which the number of colors required corresponds to the longest path length in the coupling DAG. We propose a decentralized graph-coloring algorithm to determine priorities for the agents. We evaluate the approach by applying it to multi-agent motion planning (MAMP) for connected and automated vehicles (CAVs) on roads using, a variant of MAPF.
Multi-agent path finding (MAPF) in large networks is computationally challenging. An approach for MAPF is prioritized planning (PP), in which agents plan sequentially according to their priority. Albeit a computationally efficient approach for MAPF, the solution quality strongly depends on the prioritization. Most prioritizations rely either on heuristics, which do not generalize well, or iterate to find adequate priorities, which costs computational effort. In this work, we show how agents can compute with multiple prioritizations simultaneously. Our approach is general as it does not rely on domain-specific knowledge. The context of this work is multi-agent motion planning (MAMP) with a receding horizon subject to computation time constraints. MAMP considers the system dynamics in more detail compared to MAPF. In numerical experiments on MAMP, we demonstrate that our approach to prioritization comes close to optimal prioritization and outperforms state-of-the-art methods with only a minor increase in computation time. We show real-time capability in an experiment on a road network with ten vehicles in our Cyber-Physical Mobility Lab.
Antibiotic resistance, which is a serious healthcare issue, emerges due to uncontrolled and repeated antibiotic use that causes bacteria to mutate and develop resistance to antibiotics. The Antibiotics Time Machine Problem aims to come up with treatment plans that maximize the probability of reversing these mutations. Motivated by the severity of the problem, we develop a risk-averse approach and formulate a scenario-based mixed-integer linear program with a conditional value-at-risk objective function. We propose a risk-averse scenario batch decomposition algorithm that partitions the scenarios into manageable risk-averse subproblems, enabling the construction of lower and upper bounds. We develop several algorithmic enhancements in the form of stronger no-good cuts and symmetry breaking constraints in addition to scenario regrouping and warm starting. We conduct extensive computational experiments for static and dynamic versions of the problem on a real dataset and demonstrate the effectiveness of our approach. Our results suggest that risk-averse solutions can achieve significantly better worst-case performance compared to risk-neutral solutions with a slight decrease in terms of the average performance, especially for the dynamic version. Although our methodology is presented in the context of the Antibiotics Time Machine Problem, it can be adapted to other risk-averse problem settings in which the decision variables come from special ordered sets of type one.
Longitudinal MRI analysis is crucial for predicting disease outcomes, particularly in chronic conditions like hepatocellular carcinoma (HCC), where early detection can significantly influence treatment strategies and patient prognosis. Yet, due to challenges like limited data availability, subtle parenchymal changes, and the irregular timing of medical screenings, current approaches have so far focused on cross-sectional imaging data. To address this, we propose HCCNet, a novel model architecture that integrates a 3D adaptation of the ConvNeXt CNN architecture with a Transformer encoder, capturing both the intricate spatial features of 3D MRIs and the complex temporal dependencies across different time points. HCCNet utilizes a two-stage pre-training process tailored for longitudinal MRI data. The CNN backbone is pre-trained using a self-supervised learning framework adapted for 3D MRIs, while the Transformer encoder is pre-trained with a sequence-order-prediction task to enhance its understanding of disease progression over time. We demonstrate the effectiveness of HCCNet by applying it to a cohort of liver cirrhosis patients undergoing regular MRI screenings for HCC surveillance. Our results show that HCCNet significantly improves predictive accuracy and reliability over baseline models, providing a robust tool for personalized HCC surveillance. The methodological approach presented in this paper is versatile and can be adapted to various longitudinal MRI screening applications. Its ability to handle varying patient record lengths and irregular screening intervals establishes it as an invaluable framework for monitoring chronic diseases, where timely and accurate disease prognosis is critical for effective treatment planning.
Completely capturing the three-dimensional (3D) data of an object is essential in industrial and robotic applications. The task of next-best-view (NBV) planning is to calculate the next optimal viewpoint based on the current data, gradually achieving a complete 3D reconstruction of the object. However, many existing NBV planning algorithms incur heavy computational costs due to the extensive use of ray-casting. Specifically, this framework refits different types of voxel clusters into ellipsoids based on the voxel structure. Then, the next optimal viewpoint is selected from the candidate views using a projection-based viewpoint quality evaluation function in conjunction with a global partitioning strategy. This process replaces extensive ray-casting, significantly improving the computational efficiency. Comparison experiments in the simulation environment show that our framework achieves the highest point cloud coverage with low computational time compared to other frameworks. The real-world experiments also confirm the efficiency and feasibility of the framework. Our method will be made open source to benefit the community.
Autonomous agricultural vehicles (AAVs), including field robots and autonomous tractors, are becoming essential in modern farming by improving efficiency and reducing labor costs. A critical task in AAV operations is headland turning between crop rows. This task is challenging in orchards with limited headland space, irregular boundaries, operational constraints, and static obstacles. While traditional trajectory planning methods work well in arable farming, they often fail in cluttered orchard environments. This letter presents a novel trajectory planner that enhances the safety and efficiency of AAV headland maneuvers, leveraging advancements in autonomous driving. Our approach includes an efficient front-end algorithm and a high-performance back-end optimization. Applied to vehicles with various implements, it outperforms state-of-the-art methods in both standard and challenging orchard fields. This work bridges agricultural and autonomous driving technologies, facilitating a broader adoption of AAVs in complex orchards.
Driven by the need to address labor shortages and meet the demands of a rapidly growing population, robotic automation has become a critical component in precision agriculture. Leaf-level hyperspectral spectroscopy is shown to be a powerful tool for phenotyping, monitoring crop health, identifying essential nutrients within plants as well as detecting diseases and water stress. This work introduces RoMu4o, a robotic manipulation unit for orchard operations offering an automated solution for proximal hyperspectral leaf sensing. This ground robot is equipped with a 6DOF robotic arm and vision system for real-time deep learning-based image processing and motion planning. We developed robust perception and manipulation pipelines that enable the robot to successfully grasp target leaves and perform spectroscopy. These frameworks operate synergistically to identify and extract the 3D structure of leaves from an observed batch of foliage, propose 6D poses, and generate collision-free constraint-aware paths for precise leaf manipulation. The end-effector of the arm features a compact design that integrates an independent lighting source with a hyperspectral sensor, enabling high-fidelity data acquisition while streamlining the calibration process for accurate measurements. Our ground robot is engineered to operate in unstructured orchard environments. However, the performance of the system is evaluated in both indoor and outdoor plant models. The system demonstrated reliable performance for 1-LPB hyperspectral sampling, achieving 95% success rate in lab trials and 79% in field trials. Field experiments revealed an overall success rate of 70% for autonomous leaf grasping and hyperspectral measurement in a pistachio orchard. The open-source repository is available at: https://github.com/mehradmrt/UCM-AgBot-ROS2
Low-order frequency response models for power systems have a decades-long history in optimization and control problems such as unit commitment, economic dispatch, and wide-area control. With a few exceptions, these models are built upon the Newtonian mechanics of synchronous generators, assuming that the frequency dynamics across a system are approximately homogeneous, and assume the dynamics of nodal voltages for most operating conditions are negligible, and thus are not directly computed at all buses. As a result, the use of system frequency models results in the systematic underestimation of frequency minimum nadir and maximum RoCoF, and provides no insight into the reactive power-voltage dynamics. This paper proposes a low-order model of both frequency and voltage response in grid-forming inverter-dominated power systems. The proposed model accounts for spatial-temporal variations in frequency and voltage behavior across a system and as a result, demonstrates the heterogeneity of frequency response in future renewable power systems. Electromagnetic transient (EMT) simulations are used to validate the utility, accuracy, and computational efficiency of these models, setting the basis for them to serve as fast, scalable alternatives to EMT simulation, especially when dealing with very large-scale systems, for both planning and operational studies.
We investigate the unconstrained minimum energy required for vehicles to move through turbulence. We restrict our study to vehicles that interact with their environment through thrust, weight and drag forces, such as rotorcraft or submersibles. For such vehicles, theory predicts an optimum ratio between vehicle velocity and a characteristic velocity of the turbulence. The energy required for transit can be substantially smaller than what is required to move through quiescent fluid. We describe a simple picture for how a flight trajectory could preferentially put vehicles in tailwinds rather than headwinds, predicated on the organization of turbulence around vortices. This leads to an analytical parameter-free lower bound on the energy required to traverse a turbulent flow. We test this bound by computationally optimizing trajectories in Kraichnan's model of turbulence, and find that the energy required by point-models of vehicles is slightly larger than but close to our bound. Finally, we predict the existence of an optimum level of turbulence for which power is minimized, so that turbulence can be both too strong or too weak to be useful. This work strengthens previous findings that environmental turbulence can always reduce energy use. Thus, favorable trajectories are available to maneuverable vehicles if they have sufficient knowledge of the flow and computational resources for path planning.
Ensuring the proper use of sensitive data in analytics under complex privacy policies is an increasingly critical challenge. Many existing approaches lack portability, verifiability, and scalability across diverse data processing frameworks. We introduce Picachv, a novel security monitor that automatically enforces data use policies. It works on relational algebra as an abstraction for program semantics, enabling policy enforcement on query plans generated by programs during execution. This approach simplifies analysis across diverse analytical operations and supports various front-end query languages. By formalizing both data use policies and relational algebra semantics in Coq, we prove that Picachv correctly enforces policies. Picachv also leverages Trusted Execution Environments (TEEs) to enhance trust in runtime, providing provable policy compliance to stakeholders that the analytical tasks comply with their data use policies. We integrated Picachv into Polars, a state-of-the-art data analytics framework, and evaluate its performance using the TPC-H benchmark. We also apply our approach to real-world use cases. Our work demonstrates the practical application of formal methods in securing data analytics, addressing key challenges.
Short-term shifts in booking behaviors can disrupt forecasting in the travel and hospitality industry, especially during global crises. Traditional metrics like average or median lead times often overlook important distribution changes. This study introduces a normalized L1 (Manhattan) distance to assess Airbnb booking lead time divergences from 2018 to 2022, focusing on the COVID-19 pandemic across four major U.S. cities. We identify a two-phase disruption: an abrupt change at the pandemic's onset followed by partial recovery with persistent deviations from pre-2018 patterns. Our method reveals changes in travelers' planning horizons that standard statistics miss, highlighting the need to analyze the entire lead-time distribution for more accurate demand forecasting and pricing strategies. The normalized L1 metric provides valuable insights for tourism stakeholders navigating ongoing market volatility.
We address the problem of path-planning for an autonomous mobile vehicle, called the ego vehicle, in an unknown andtime-varying environment. The objective is for the ego vehicle to minimize exposure to a spatiotemporally-varying unknown scalar field called the threat field. Noisy measurements of the threat field are provided by a network of mobile sensors. Weaddress the problem of optimally configuring (placing) these sensors in the environment. To this end, we propose sensor reconfiguration by maximizing a reward function composed of three different elements. First, the reward includes an informa tion measure that we call context-relevant mutual information (CRMI). Unlike typical sensor placement techniques that maxi mize mutual information of the measurements and environment state, CRMI directly quantifies uncertainty reduction in the ego path cost while it moves in the environment. Therefore, the CRMI introduces active coupling between the ego vehicle and the sensor network. Second, the reward includes a penalty on the distances traveled by the sensors. Third, the reward includes a measure of proximity of the sensors to the ego vehicle. Although we do not consider communication issues in this paper, such proximity is of relevance for future work that addresses communications between the sensors and the ego vehicle. We illustrate and analyze the proposed technique via numerical simulations.
The rapid advancement of digital technologies and recent global pandemic scenarios have led to a growing focus on how these technologies can enhance healthcare service delivery and workflow to address crises. Action plans that consolidate existing digital transformation programs are being reviewed to establish core infrastructure and foundations for sustainable healthcare solutions. Reforming health and social care to personalize home care, for example, can help avoid treatment in overcrowded acute hospital settings and improve the experiences and outcomes for both healthcare professionals and service users. In this information-intensive domain, addressing the interoperability challenge through standards-based roadmaps is crucial for enabling effective connections between health and social care services. This approach facilitates safe and trustworthy data workflows between different healthcare system providers. In this paper, we present a methodology for extracting, transforming, and loading data through a semi-automated process using a Common Semantic Standardized Data Model (CSSDM) to create personalized healthcare knowledge graph (KG). The CSSDM is grounded in the formal ontology of ISO 13940 ContSys and incorporates FHIR-based specifications to support structural attributes for generating KGs. We propose that the CSSDM facilitates data harmonization and linking, offering an alternative approach to interoperability. This approach promotes a novel form of collaboration between companies developing health information systems and cloud-enabled health services. Consequently, it provides multiple stakeholders with access to high-quality data and information sharing.
Unmanned Aerial Vehicles (UAVs) are increasingly essential in various fields such as surveillance, reconnaissance, and telecommunications. This study aims to develop a learning algorithm for the path planning of UAV wireless communication relays, which can reduce storage requirements and accelerate Deep Reinforcement Learning (DRL) convergence. Assuming the system possesses terrain maps of the area and can estimate user locations using localization algorithms or direct GPS reporting, it can input these parameters into the learning algorithms to achieve optimized path planning performance. However, higher resolution terrain maps are necessary to extract topological information such as terrain height, object distances, and signal blockages. This requirement increases memory and storage demands on UAVs while also lengthening convergence times in DRL algorithms. Similarly, defining the telecommunication coverage map in UAV wireless communication relays using these terrain maps and user position estimations demands higher memory and storage utilization for the learning path planning algorithms. Our approach reduces path planning training time by applying a dimensionality reduction technique based on Principal Component Analysis (PCA), sample combination, Prioritized Experience Replay (PER), and the combination of Mean Squared Error (MSE) and Mean Absolute Error (MAE) loss calculations in the coverage map estimates, thereby enhancing a Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. The proposed solution reduces the convergence episodes needed for basic training by approximately four times compared to the traditional TD3.
Increasingly many AI systems can plan and execute interactions in open-ended environments, such as making phone calls or buying online goods. As developers grow the space of tasks that such AI agents can accomplish, we will need tools both to unlock their benefits and manage their risks. Current tools are largely insufficient because they are not designed to shape how agents interact with existing institutions (e.g., legal and economic systems) or actors (e.g., digital service providers, humans, other AI agents). For example, alignment techniques by nature do not assure counterparties that some human will be held accountable when a user instructs an agent to perform an illegal action. To fill this gap, we propose the concept of agent infrastructure: technical systems and shared protocols external to agents that are designed to mediate and influence their interactions with and impacts on their environments. Agent infrastructure comprises both new tools and reconfigurations or extensions of existing tools. For example, to facilitate accountability, protocols that tie users to agents could build upon existing systems for user authentication, such as OpenID. Just as the Internet relies on infrastructure like HTTPS, we argue that agent infrastructure will be similarly indispensable to ecosystems of agents. We identify three functions for agent infrastructure: 1) attributing actions, properties, and other information to specific agents, their users, or other actors; 2) shaping agents' interactions; and 3) detecting and remedying harmful actions from agents. We propose infrastructure that could help achieve each function, explaining use cases, adoption, limitations, and open questions. Making progress on agent infrastructure can prepare society for the adoption of more advanced agents.
Solar irradiance clustering can enhance solar power capacity planning and help improve forecasting models by identifying similar irradiance patterns influenced by seasonal and weather changes. In this study, we adopt an efficient two-level clustering approach to automatically identify seasons using the clear sky irradiance in first level and subsequently to identify daily cloud level as clear, cloudy and partly cloudy within each season in second level. In the second level of clustering, three methods are compared, namely, Daily Irradiance Index (DII or $\beta$), Euclidean Distance (ED), and Dynamic Time Warping (DTW) distance. The DII is computed as the ratio of time integral of measured irradiance to time integral of the clear sky irradiance. The identified clusters were compared quantitatively using established clustering metrics and qualitatively by comparing the mean irradiance profiles. The results clearly establish the superiority of the $\beta$-based clustering approach as the leader, setting a new benchmark for solar irradiance clustering studies. Moreover, $\beta$-based clustering remains effective even for annual data unlike the time-series methods which suffer significant performance degradation. Interestingly, contrary to expectations, ED-based clustering outperforms the more compute-intensive DTW distance-based clustering. The method has been rigorously validated using data from two distinct US locations, demonstrating robust scalability for larger datasets and potential applicability for other locations.
The proton-proton collisions at the Large Hadron Collider (LHC) produce an intense, high-energy beam of neutrinos of all flavors, collimated in the forward direction. Recently two dedicated neutrino experiments, FASER and SND@LHC, have started operating to take advantage of the TeV energy LHC neutrino beam, with first results released in 2023 and further results released in 2024. The first detection of neutrinos produced at a particle collider opens up a new avenue of research, allowing to study the highest energy neutrinos produced in a controlled laboratory environment, with an associated broad and rich physics program. Neutrino measurements at the LHC will provide important contributions to QCD, neutrino and BSM physics, with impactful implications for astro-particle physics. This review article summarizes the physics motivation, status and plans of, present and future neutrino experiments at the LHC.
Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks, largely due to their dependence on language-based outputs. While some approaches have introduced a point-based action space to mitigate this issue, they fall short in managing more intricate tasks within complex environments. This deficiency arises from their failure to fully exploit the inherent thinking and reasoning capabilities that are fundamental strengths of Vision-Language Models (VLMs). To address these limitations, we propose a novel approach named SpatialCoT, specifically designed to bolster the spatial reasoning capabilities of VLMs. Our approach comprises two stages: spatial coordinate bi-directional alignment, which aligns vision-language inputs with spatial coordinates, and chain-of-thought spatial grounding, which harnesses the reasoning capabilities of language models for advanced spatial reasoning. We evaluate SpatialCoT on challenging navigation and manipulation tasks, both in simulation and real-world settings. Experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches in both tasks.
We consider the problem of transporting multiple packages from an initial location to a destination location in a windy urban environment using a team of SUAVs. Each SUAV carries one package. We assume that the wind field is unknown, but wind speed can be measured by SUAVs during flight. The SUAVs fly sequentially one after the other, measure wind speeds along their trajectories, and report the measurements to a central computer. The overall objective is to minimize the total travel time of all SUAVs, which is in turn related to the number of SUAV traversals through the environment. For a discretized environment modeled by a graph, we describe a method to estimate wind speeds and the time of traversal for each SUAV path. Each SUAV traverses a minimum-time path planned based on the current wind field estimate. We study cases of static and time-varying wind fields with and without measurement noise. For each case, we demonstrate via numerical simulation that the proposed method finds the optimal path after a minimal number of traversals.
This article presents a new hybrid algorithm, crossover binary particle swarm optimization (crBPSO), for allocating resources in local energy systems via multi-agent (MA) technology. Initially, a hierarchical MA-based architecture in a grid-connected local energy setup is presented. In this architecture, task specific agents operate in a master-slave manner. Where, the master runs a well-formulated optimization routine aiming at minimizing costs of energy procurement, battery degradation, and load scheduling delay. The slaves update the master on their current status and receive optimal action plans accordingly. Simulation results demonstrate that the proposed algorithm outperforms selected existing ones by 21\% in terms average energy system costs while satisfying customers' energy demand and maintaining the required quality of service.
Estimating the shortest travel time and providing route recommendation between different locations in a city or region can quantitatively measure the conditions of the transportation network during or after extreme events. One common approach is to use Dijkstra's Algorithm, which produces the shortest path as well as the shortest distance. However, this option is computationally expensive when applied to large-scale networks. This paper proposes a novel fast framework based on graph neural networks (GNNs) which approximate the single-source shortest distance between pairs of locations, and predict the single-source shortest path subsequently. We conduct multiple experiments on synthetic graphs of different size to demonstrate the feasibility and computational efficiency of the proposed model. In real-world case studies, we also applied the proposed method of flood risk analysis of coastal urban areas to calculate delays in evacuation to public shelters during hurricanes. The results indicate the accuracy and computational efficiency of the GNN model, and its potential for effective implementation in emergency planning and management.
We present GeoManip, a framework to enable generalist robots to leverage essential conditions derived from object and part relationships, as geometric constraints, for robot manipulation. For example, cutting the carrot requires adhering to a geometric constraint: the blade of the knife should be perpendicular to the carrot's direction. By interpreting these constraints through symbolic language representations and translating them into low-level actions, GeoManip bridges the gap between natural language and robotic execution, enabling greater generalizability across diverse even unseen tasks, objects, and scenarios. Unlike vision-language-action models that require extensive training, operates training-free by utilizing large foundational models: a constraint generation module that predicts stage-specific geometric constraints and a geometry parser that identifies object parts involved in these constraints. A solver then optimizes trajectories to satisfy inferred constraints from task descriptions and the scene. Furthermore, GeoManip learns in-context and provides five appealing human-robot interaction features: on-the-fly policy adaptation, learning from human demonstrations, learning from failure cases, long-horizon action planning, and efficient data collection for imitation learning. Extensive evaluations on both simulations and real-world scenarios demonstrate GeoManip's state-of-the-art performance, with superior out-of-distribution generalization while avoiding costly model training.
This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are renowned for their generative modeling capabilities, practical applications in fields such as biology often require sample generation that maximizes specific metrics (e.g., stability, affinity in proteins, closeness to target structures). In these scenarios, diffusion models can be adapted not only to generate realistic samples but also to explicitly maximize desired measures at inference time without fine-tuning. This tutorial explores the foundational aspects of such inference-time algorithms. We review these methods from a unified perspective, demonstrating that current techniques -- such as Sequential Monte Carlo (SMC)-based guidance, value-based sampling, and classifier guidance -- aim to approximate soft optimal denoising processes (a.k.a. policies in RL) that combine pre-trained denoising processes with value functions serving as look-ahead functions that predict from intermediate states to terminal rewards. Within this framework, we present several novel algorithms not yet covered in the literature. Furthermore, we discuss (1) fine-tuning methods combined with inference-time techniques, (2) inference-time algorithms based on search algorithms such as Monte Carlo tree search, which have received limited attention in current research, and (3) connections between inference-time algorithms in language models and diffusion models. The code of this tutorial on protein design is available at https://github.com/masa-ue/AlignInversePro
Online motion planning is a challenging problem for intelligent robots moving in dense environments with dynamic obstacles, e.g., crowds. In this work, we propose a novel approach for optimal and safe online motion planning with minimal information about dynamic obstacles. Specifically, our approach requires only the current position of the obstacles and their maximum speed, but it does not need any information about their exact trajectories or dynamic model. The proposed methodology combines Monte Carlo Tree Search (MCTS), for online optimal planning via model simulations, with Velocity Obstacles (VO), for obstacle avoidance. We perform experiments in a cluttered simulated environment with walls, and up to 40 dynamic obstacles moving with random velocities and directions. With an ablation study, we show the key contribution of VO in scaling up the efficiency of MCTS, selecting the safest and most rewarding actions in the tree of simulations. Moreover, we show the superiority of our methodology with respect to state-of-the-art planners, including Non-linear Model Predictive Control (NMPC), in terms of improved collision rate, computational and task performance.
Planning for autonomous systems typically requires reasoning with models at different levels of abstraction, and the harmonization of two competing sets of objectives: high-level mission goals that refer to an interaction of the system with the external environment, and low-level platform constraints that aim to preserve the integrity and the correct interaction of the subsystems. The complicated interplay between these two models makes it very hard to reason on the system as a whole, especially when the objective is to find plans with robustness guarantees, considering the non-deterministic behavior of the lower layers of the system. In this paper, we introduce the problem of Platform-Aware Mission Planning (PAMP), addressing it in the setting of temporal durative actions. The PAMP problem differs from standard temporal planning for its exists-forall nature: the high-level plan dealing with mission goals is required to satisfy safety and executability constraints, for all the possible non-deterministic executions of the low-level model of the platform and the environment. We propose two approaches for solving PAMP. The first baseline approach amalgamates the mission and platform levels, while the second is based on an abstraction-refinement loop that leverages the combination of a planner and a verification engine. We prove the soundness and completeness of the proposed approaches and validate them experimentally, demonstrating the importance of heterogeneous modeling and the superiority of the technique based on abstraction-refinement.
Online medical consultation (OMC) restricts doctors to gathering patient information solely through inquiries, making the already complex sequential decision-making process of diagnosis even more challenging. Recently, the rapid advancement of large language models has demonstrated a significant potential to transform OMC. However, most studies have primarily focused on improving diagnostic accuracy under conditions of relatively sufficient information, while paying limited attention to the "inquiry" phase of the consultation process. This lack of focus has left the relationship between "inquiry" and "diagnosis" insufficiently explored. In this paper, we first extract real patient interaction strategies from authentic doctor-patient conversations and use these strategies to guide the training of a patient simulator that closely mirrors real-world behavior. By inputting medical records into our patient simulator to simulate patient responses, we conduct extensive experiments to explore the relationship between "inquiry" and "diagnosis" in the consultation process. Experimental results demonstrate that inquiry and diagnosis adhere to the Liebig's law: poor inquiry quality limits the effectiveness of diagnosis, regardless of diagnostic capability, and vice versa. Furthermore, the experiments reveal significant differences in the inquiry performance of various models. To investigate this phenomenon, we categorize the inquiry process into four types: (1) chief complaint inquiry; (2) specification of known symptoms; (3) inquiry about accompanying symptoms; and (4) gathering family or medical history. We analyze the distribution of inquiries across the four types for different models to explore the reasons behind their significant performance differences. We plan to open-source the weights and related code of our patient simulator at https://github.com/LIO-H-ZEN/PatientSimulator.
The impact of Artificial Intelligence (AI) is transforming various aspects of urban life, including, governance, policy and planning, healthcare, sustainability, economics, entrepreneurship, etc. Although AI immense potential for positively impacting urban living, its success depends on overcoming significant challenges, particularly in telecommunications infrastructure. Smart city applications, such as, federated learning, Internet of Things (IoT), and online financial services, require reliable Quality of Service (QoS) from telecommunications networks to ensure effective information transfer. However, with over three billion people underserved or lacking access to internet, many of these AI-driven applications are at risk of either remaining underutilized or failing altogether. Furthermore, many IoT and video-based applications in densely populated urban areas require high-quality connectivity. This paper explores these issues, focusing on the challenges that need to be mitigated to make AI succeed in emerging countries, where more than 80% of the world population resides and urban migration grows. In this context, an overview of a case study conducted in Kathmandu, Nepal, highlights citizens' aspirations for affordable, high-quality internet-based services. The findings underscore the pressing need for advanced telecommunication networks to meet diverse user requirements while addressing investment and infrastructure gaps. This discussion provides insights into bridging the digital divide and enabling AI's transformative potential in urban areas.
In this study, we firstly introduce a method that converts CityGML data into voxels which works efficiently and fast in high resolution for large scale datasets such as cities but by sacrificing some building details to overcome the limitations of previous voxelization methodologies that have been computationally intensive and inefficient at transforming large-scale urban areas into voxel representations for high resolution. Those voxelized 3D city data from multiple cities and corresponding air temperature data are used to develop a machine learning model. Before the model training, Gaussian blurring is implemented on input data to consider spatial relationships, as a result the correlation rate between air temperature and volumetric building morphology is also increased after the Gaussian blurring. After the model training, the prediction results are not just evaluated with Mean Square Error (MSE) but some image similarity metrics such as Structural Similarity Index Measure (SSIM) and Learned Perceptual Image Patch Similarity (LPIPS) that are able to detect and consider spatial relations during the evaluation process. This trained model is capable of predicting the spatial distribution of air temperature by using building volume information of corresponding pixel as input. By doing so, this research aims to assist urban planners in incorporating environmental parameters into their planning strategies, thereby facilitating more sustainable and inhabitable urban environments.
How are robots becoming smarter at interacting with their surroundings? Recent advances have reshaped how robots use tactile sensing to perceive and engage with the world. Tactile sensing is a game-changer, allowing robots to embed sensorimotor control strategies to interact with complex environments and skillfully handle heterogeneous objects. Such control frameworks plan contact-driven motions while staying responsive to sudden changes. We review the latest methods for building perception and control systems in tactile robotics while offering practical guidelines for their design and implementation. We also address key challenges to shape the future of intelligent robots.
Industrial robotics demands significant energy to operate, making energy-reduction methodologies increasingly important. Strategies for planning minimum-energy trajectories typically involve solving nonlinear optimal control problems (OCPs), which rarely cope with real-time requirements. In this paper, we propose a paradigm for generating near minimum-energy trajectories for manipulators by learning from optimal solutions. Our paradigm leverages a residual learning approach, which embeds boundary conditions while focusing on learning only the adjustments needed to steer a standard solution to an optimal one. Compared to a computationally expensive OCP-based planner, our paradigm achieves 87.3% of the performance near the training dataset and 50.8% far from the dataset, while being two to three orders of magnitude faster.
Buildings are significant contributors to global greenhouse gas emissions, accounting for 26% of global energy sector emissions in 2022. Meeting net zero goals requires a rapid reduction in building emissions, both directly from the buildings and indirectly from the production of electricity and heat used in buildings. National energy planning for net zero demands both detailed and comprehensive building energy consumption data. However, geo-located building-level energy data is rarely available in Europe, with analysis typically relying on anonymised, simulated or low-resolution data. To address this problem, we introduce a dataset of Neighbourhood Energy, Buildings, and Urban Landscapes (NEBULA) for modelling domestic energy consumption for small neighbourhoods (5-150 households). NEBULA integrates data on building characteristics, climate, urbanisation, environment, and socio-demographics and contains 609,964 samples across England and Wales.
This work addresses the path planning problem for a group of unmanned aerial vehicles (UAVs) to maintain a desired formation during operation. Our approach formulates the problem as an optimization task by defining a set of fitness functions that not only ensure the formation but also include constraints for optimal and safe UAV operation. To optimize the fitness function and obtain a suboptimal path, we employ the teaching-learning-based optimization algorithm and then further enhance it with mechanisms such as mutation, elite strategy, and multi-subject combination. A number of simulations and experiments have been conducted to evaluate the proposed method. The results demonstrate that the algorithm successfully generates valid paths for the UAVs to fly in a triangular formation for an inspection task.
The unmanned aerial vehicles (UAVs) are efficient tools for diverse tasks such as electronic reconnaissance, agricultural operations and disaster relief. In the complex three-dimensional (3D) environments, the path planning with obstacle avoidance for UAVs is a significant issue for security assurance. In this paper, we construct a comprehensive 3D scenario with obstacles and no-fly zones for dynamic UAV trajectory. Moreover, a novel artificial potential field algorithm coupled with simulated annealing (APF-SA) is proposed to tackle the robust path planning problem. APF-SA modifies the attractive and repulsive potential functions and leverages simulated annealing to escape local minimum and converge to globally optimal solutions. Simulation results demonstrate that the effectiveness of APF-SA, enabling efficient autonomous path planning for UAVs with obstacle avoidance.
Building autonomous mobile robots (AMRs) with optimized efficiency and adaptive capabilities-able to respond to changing task demands and dynamic environments-is a strongly desired goal for advancing construction robotics. Such robots can play a critical role in enabling automation, reducing operational carbon footprints, and supporting modular construction processes. Inspired by the adaptive autonomy of living organisms, we introduce interoception, which centers on the robot's internal state representation, as a foundation for developing self-reflection and conscious learning to enable continual learning and adaptability in robotic agents. In this paper, we factorize internal state variables and mathematical properties as "cognitive dissonance" in shared control paradigms, where human interventions occasionally occur. We offer a new perspective on how interoception can help build adaptive motion planning in AMRs by integrating the legacy of heuristic costs from grid/graph-based algorithms with recent advances in neuroscience and reinforcement learning. Declarative and procedural knowledge extracted from human semantic inputs is encoded into a hypergraph model that overlaps with the spatial configuration of onsite layout for path planning. In addition, we design a velocity-replay module using an encoder-decoder architecture with few-shot learning to enable robots to replicate velocity profiles in contextualized scenarios for multi-robot synchronization and handover collaboration. These "cached" knowledge representations are demonstrated in simulated environments for multi-robot motion planning and stacking tasks. The insights from this study pave the way toward artificial general intelligence in AMRs, fostering their progression from complexity to competence in construction automation.
Unmanned Aerial Vehicles (UAVs) have great potential in urban traffic monitoring due to their rapid speed, cost-effectiveness, and extensive field-of-view, while being unconstrained by traffic congestion. However, their limited flight duration presents critical challenges in sustainable recharging strategies and efficient route planning in long-term monitoring tasks. Additionally, existing approaches for long-term monitoring often neglect the evolving nature of urban traffic networks. In this study, we introduce a novel dynamic UAV routing framework for long-term, network-wide urban traffic monitoring, leveraging existing ground vehicles as mobile charging stations without disrupting their operations. To address the complexity of long-term monitoring scenarios involving multiple flights, we decompose the problem into manageable single-flight tasks, in which each flight is modeled as a Team Arc Orienteering Problem with Decreasing Profits with the objective to collectively maximize the spatiotemporal network coverage. Between flights, we adaptively update the edge weights to incorporate real-time traffic changes and revisit intervals. We validate our framework through extensive microscopic simulations in a modified Sioux Falls network under various scenarios. Comparative results demonstrate that our model outperforms three baseline approaches, especially when historical information is incomplete or absent. Moreover, we show that our monitoring framework can capture network-wide traffic trends and construct accurate Macroscopic Fundamental Diagrams (MFDs). These findings demonstrate the effectiveness of the proposed dynamic UAV routing framework, underscoring its suitability for efficient and reliable long-term traffic monitoring. Our approach's adaptability and high accuracy in capturing the MFD highlight its potential in network-wide traffic control and management applications.
Commonsense temporal reasoning at scale is a core problem for cognitive systems. The correct inference of the duration for which fluents hold is required by many tasks, including natural language understanding and planning. Many AI systems have limited deductive closure because they cannot extrapolate information correctly regarding existing fluents and events. In this study, we discuss the knowledge representation and reasoning schemes required for robust temporal projection in the Cyc Knowledge Base. We discuss how events can start and end risk periods for fluents. We then use discrete survival functions, which represent knowledge of the persistence of facts, to extrapolate a given fluent. The extrapolated intervals can be truncated by temporal constraints and other types of commonsense knowledge. Finally, we present the results of experiments to demonstrate that these methods obtain significant improvements in terms of Q/A performance.
This paper presents a modular framework for motion planning using movement primitives. Central to the approach is Contraction Theory, a modular stability tool for nonlinear dynamical systems. The approach extends prior methods by achieving parallel and sequential combinations of both discrete and rhythmic movements, while enabling independent modulation of each movement. This modular framework enables a divide-and-conquer strategy to simplify the programming of complex robot motion planning. Simulation examples illustrate the flexibility and versatility of the framework, highlighting its potential to address diverse challenges in robot motion planning.
In this paper, we present an optimization-based framework for generating estimation-aware trajectories in scenarios where measurement (output) uncertainties are state-dependent and set-valued. The framework leverages the concept of regularity for set-valued output maps. Specifically, we demonstrate that, for output-regular maps, one can utilize a set-valued observability measure that is concave with respect to finite-horizon state trajectories. By maximizing this measure, optimized estimation-aware trajectories can be designed for a broad class of systems, including those with locally linearized dynamics. To illustrate the effectiveness of the proposed approach, we provide a representative example in the context of trajectory planning for vision-based estimation. We present an estimation-aware trajectory for an uncooperative target-tracking problem that uses a machine learning (ML)-based estimation module on an ego-satellite.
We present a new code and approach, JERALD -- JAX Enhanced Resolution Approximate Lagrangian Dynamics -- , that improves on and extends the Lagrangian Deep Learning method of Dai & Seljak (2021), producing high-resolution dark matter, stellar mass and neutral hydrogen maps from lower-resolution approximate $N$-body simulations. The model is trained using the Sherwood-Relics simulation suite (for a fixed cosmology), specifically designed for the intergalactic medium and the neutral hydrogen distribution in the cosmic web. The output is tested in the redshift range from $z=5$ to $z=0$ and the generalization properties of the learned mapping is demonstrated. JERALD produces maps with dark matter, stellar and neutral hydrogen power spectra in excellent agreement with full-hydrodynamic simulations with $8\times$ higher resolution, at large and intermediate scales; in particular, JERALD's neutral hydrogen power spectra agree with their higher-resolution full-hydrodynamic counterparts within 90% up to $k\simeq1\,h$Mpc$^{-1}$ and within 70% up to $k\simeq10\,h$Mpc$^{-1}$. JERALD provides a fast, accurate and physically motivated approach that we plan to embed in a statistical inference pipeline, such as Simulation-Based Inference, to constrain dark matter properties from large- to intermediate-scale structure observables.
In reinforcement learning, the value function is typically trained to solve the Bellman equation, which connects the current value to future values. This temporal dependency hints that the value function may contain implicit information about the environment's transition dynamics. By rearranging the Bellman equation, we show that a converged value function encodes a model of the underlying dynamics of the environment. We build on this insight to propose a simple method for inferring dynamics models directly from the value function, potentially mitigating the need for explicit model learning. Furthermore, we explore the challenges of next-state identifiability, discussing conditions under which the inferred dynamics model is well-defined. Our work provides a theoretical foundation for leveraging value functions in dynamics modeling and opens a new avenue for bridging model-free and model-based reinforcement learning.
The average-reward formulation of reinforcement learning (RL) has drawn increased interest in recent years due to its ability to solve temporally-extended problems without discounting. Independently, RL algorithms have benefited from entropy-regularization: an approach used to make the optimal policy stochastic, thereby more robust to noise. Despite the distinct benefits of the two approaches, the combination of entropy regularization with an average-reward objective is not well-studied in the literature and there has been limited development of algorithms for this setting. To address this gap in the field, we develop algorithms for solving entropy-regularized average-reward RL problems with function approximation. We experimentally validate our method, comparing it with existing algorithms on standard benchmarks for RL.
In reinforcement learning, two objective functions have been developed extensively in the literature: discounted and averaged rewards. The generalization to an entropy-regularized setting has led to improved robustness and exploration for both of these objectives. Recently, the entropy-regularized average-reward problem was addressed using tools from large deviation theory in the tabular setting. This method has the advantage of linearity, providing access to both the optimal policy and average reward-rate through properties of a single matrix. In this paper, we extend that framework to more general settings by developing approaches based on function approximation by neural networks. This formulation reveals new theoretical insights into the relationship between different objectives used in RL. Additionally, we combine our algorithm with a posterior policy iteration scheme, showing how our approach can also solve the average-reward RL problem without entropy-regularization. Using classic control benchmarks, we experimentally find that our method compares favorably with other algorithms in terms of stability and rate of convergence.
Measurement quality assurance (QA) practices play a key role in the safe use of Intensity Modulated Radiation Therapies (IMRT) for cancer treatment. These practices have reduced measurement-based IMRT QA failure below 1%. However, these practices are time and labor intensive which can lead to delays in patient care. In this study, we examine how conformal prediction methodologies can be used to robustly triage plans. We propose a new training-aware conformal risk control method by combining the benefit of conformal risk control and conformal training. We incorporate the decision making thresholds based on the gamma passing rate, along with the risk functions used in clinical evaluation, into the design of the risk control framework. Our method achieves high sensitivity and specificity and significantly reduces the number of plans needing measurement without generating a huge confidence interval. Our results demonstrate the validity and applicability of conformal prediction methods for improving efficiency and reducing the workload of the IMRT QA process.
We consider optimal planning in a large-scale system formalised as a hierarchical finite state machine (HFSM). A planning algorithm is proposed computing an optimal plan between any two states in the HFSM, consisting of two steps: A pre-processing step that computes optimal exit costs of the machines in the HFSM, with time complexity scaling with the number of machines; and a query step that efficiently computes an optimal plan by removing irrelevant subtrees of the HFSM using the optimal exit costs. The algorithm is reconfigurable in the sense that changes in the HFSM are handled with ease, where the pre-processing step recomputes only the optimal exit costs affected by the change. The algorithm can also exploit compact representations that groups together identical machines in the HFSM, where the algorithm only needs to compute the optimal exit costs for one of the identical machines within each group, thereby avoid unnecessary recomputations. We validate the algorithm on large systems with millions of states and a robotic application. It is shown that our approach outperforms Dijkstra's algorithm, Bidirectional Dijkstra and Contraction Hierarchies.
Autonomous driving is a challenging task that requires perceiving and understanding the surrounding environment for safe trajectory planning. While existing vision-based end-to-end models have achieved promising results, these methods are still facing the challenges of vision understanding, decision reasoning and scene generalization. To solve these issues, a generative planning with 3D-vision language pre-training model named GPVL is proposed for end-to-end autonomous driving. The proposed paradigm has two significant aspects. On one hand, a 3D-vision language pre-training module is designed to bridge the gap between visual perception and linguistic understanding in the bird's eye view. On the other hand, a cross-modal language model is introduced to generate holistic driving decisions and fine-grained trajectories with perception and navigation information in an auto-regressive manner. Experiments on the challenging nuScenes dataset demonstrate that the proposed scheme achieves excellent performances compared with state-of-the-art methods. Besides, the proposed GPVL presents strong generalization ability and real-time potential when handling high-level commands in various scenarios. It is believed that the effective, robust and efficient performance of GPVL is crucial for the practical application of future autonomous driving systems. Code is available at https://github.com/ltp1995/GPVL
Network simulation is pivotal in network modeling, assisting with tasks ranging from capacity planning to performance estimation. Traditional approaches such as Discrete Event Simulation (DES) face limitations in terms of computational cost and accuracy. This paper introduces RouteNet-Gauss, a novel integration of a testbed network with a Machine Learning (ML) model to address these challenges. By using the testbed as a hardware accelerator, RouteNet-Gauss generates training datasets rapidly and simulates network scenarios with high fidelity to real-world conditions. Experimental results show that RouteNet-Gauss significantly reduces prediction errors by up to 95% and achieves a 488x speedup in inference time compared to state-of-the-art DES-based methods. RouteNet-Gauss's modular architecture is dynamically constructed based on the specific characteristics of the network scenario, such as topology and routing. This enables it to understand and generalize to different network configurations beyond those seen during training, including networks up to 10x larger. Additionally, it supports Temporal Aggregated Performance Estimation (TAPE), providing configurable temporal granularity and maintaining high accuracy in flow performance metrics. This approach shows promise in improving both simulation efficiency and accuracy, offering a valuable tool for network operators.
The real-world data of power networks is often inaccessible due to privacy and security concerns, highlighting the need for tools to generate realistic synthetic network data. Existing methods leverage geographic tools like OpenStreetMap with heuristic rules to model system topology and typically focus on single-phase, balanced systems, limiting their applicability to real-world distribution systems, which are usually unbalanced. This work proposes a Bayesian Hierarchical Model (BHM) to generate unbalanced three-phase distribution systems learning from existing networks. The scheme takes as input the base topology and aggregated demand per node and outputs a three-phase unbalanced system. The proposed scheme achieves a Mean Absolute Percentage Error (MAPE) of less than $8\%$ across all phases, with computation times of 20.4 seconds for model training and 3.1 seconds per sample generation. The tool is applied to learn from publicly available SMART-DS dataset and applied to generate European 906 and IEEE-123 systems. We demonstrate the transfer learning capability of the proposed tool by leveraging a model trained on an observed system to generate a synthetic network for an unobserved system. Specifically, the tool is trained using the publicly available SMART-DS dataset and subsequently applied to generate synthetic networks for the European 906-bus system and the IEEE 123-bus system. This tool allows researchers to simulate realistic unbalanced three-phase power data with high accuracy and speed, enhancing planning and operational analysis for modern power grids.
Background Advanced adaptive randomised clinical trials are increasingly used. Compared to their conventional counterparts, their flexibility may make them more efficient, increase the probability of obtaining conclusive results without larger samples than necessary, and increase the probability that individual participants are allocated to more promising interventions. However, limited guidance is available on designing and evaluating the performance of advanced adaptive trials. Methods We summarise the methodological considerations and provide practical guidance on the entire workflow of planning and evaluating advanced adaptive trials using adaptive stopping, adaptive arm dropping, and response-adaptive randomisation within a Bayesian statistical framework. Results This comprehensive practical guide covers the key methodological decisions for advanced adaptive trials and their specification and evaluation using statistical simulation. These considerations include interventions and common control use; outcome type and generation; analysis timing and outcome-data lag; allocation rules; analysis model; adaptation rules for stopping and arm dropping; clinical scenarios assessed; performance metrics; calibration; sensitivity analyses; and reporting. The considerations are covered in the context of realistic examples, along with simulation code using the adaptr R package. Conclusions This practical guide will help clinical trialists, methodologists, and biostatisticians design and evaluate advanced adaptive trials.
Efficient and consistent feature computation is crucial for a wide range of online ML applications. Typically, feature computation is divided into two distinct phases, i.e., offline stage for model training and online stage for model serving. These phases often rely on execution engines with different interface languages and function implementations, causing significant inconsistencies. Moreover, many online ML features involve complex time-series computations (e.g., functions over varied-length table windows) that differ from standard streaming and analytical queries. Existing data processing systems (e.g., Spark, Flink, DuckDB) often incur multi-second latencies for these computations, making them unsuitable for real-time online ML applications that demand timely feature updates. This paper presents OpenMLDB, a feature computation system deployed in 4Paradigm's SageOne platform and over 100 real scenarios. Technically, OpenMLDB first employs a unified query plan generator for consistent computation results across the offline and online stages, significantly reducing feature deployment overhead. Second, OpenMLDB provides an online execution engine that resolves performance bottlenecks caused by long window computations (via pre-aggregation) and multi-table window unions (via data self-adjusting). It also provides a high-performance offline execution engine with window parallel optimization and time-aware data skew resolving. Third, OpenMLDB features a compact data format and stream-focused indexing to maximize memory usage and accelerate data access. Evaluations in testing and real workloads reveal significant performance improvements and resource savings compared to the baseline systems. The open community of OpenMLDB now has over 150 contributors and gained 1.6k stars on GitHub.
In capitalist societies, only a single right can be fully exerted without constraints of any kind: the limitless accumulation of wealth. Such imperative or prime axiom is the ultimate cause of the raising waves of inequalities observed today. In this work we extended the agent-based model proposed by Castro de Oliveira arXiv:1711.06164 to study the effects of non-uniform income redistribution policies and tax evasion on the final steady-state wealth distribution of economic agents. Our simulational results strongly support that well designed policies of income redistribution and rigid control of tax planning possibilities are unavoidable instruments to promote the raise of more economically egalitarian and sustainable societies.
As part of the LAMOST medium-resolution spectroscopic survey, the LAMOST-MRS-O is a non-time domain survey that aims to perform medium-resolution spectral observations for member stars in the open cluster area. This survey plans to obtain the spectroscopic parameters such as radial velocity and metal abundances of member stars and provide data support for further study on the chemical and dynamical characteristics and evolution of open clusters in combination with Gaia data. We have completed the observations on ten open cluster fields and obtained 235184 medium-resolution spectra of 133792 stars. Based on the data analyzed of LAMOST DR11V1.1, for some clusters of particular concern, it is found that the sampling ratio of members stars with Gmag < 15 mag can reach 70%, which indicates that the LAMOST-MRS-O has reached our initial design goal.
DESTINY+ is a planned JAXA medium-class Epsilon mission from Earth to deep space using a low-thrust, many-revolution orbit. Such a trajectory design is a challenging problem not only for trajectory design but also for flight operations, and in particular, it is essential to evaluate the impact of operational uncertainties to ensure mission success. In this study, we design the low-thrust trajectory from Earth orbit to a lunar transfer orbit by differential dynamic programming using the Sundman transformation. The results of Monte Carlo simulations with operational uncertainties confirm that the spacecraft can be successfully guided to the lunar transfer orbit by using the feedback control law of differential dynamic programming in the angular domain.
In human-robot teams, human situational awareness is the operator's conscious knowledge of the team's states, actions, plans and their environment. Appropriate human situational awareness is critical to successful human-robot collaboration. In human-robot teaming, it is often assumed that the best and required level of situational awareness is knowing everything at all times. This view is problematic, because what a human needs to know for optimal team performance varies given the dynamic environmental conditions, task context and roles and capabilities of team members. We explore this topic by interviewing 16 participants with active and repeated experience in diverse human-robot teaming applications. Based on analysis of these interviews, we derive a framework explaining the dynamic nature of required situational awareness in human-robot teaming. In addition, we identify a range of factors affecting the dynamic nature of required and actual levels of situational awareness (i.e., dynamic situational awareness), types of situational awareness inefficiencies resulting from gaps between actual and required situational awareness, and their main consequences. We also reveal various strategies, initiated by humans and robots, that assist in maintaining the required situational awareness. Our findings inform the implementation of accurate estimates of dynamic situational awareness and the design of user-adaptive human-robot interfaces. Therefore, this work contributes to the future design of more collaborative and effective human-robot teams.
Purpose : Planning a transition towards sustainable carbon neutrality at the organization level raises several accounting challenges. This paper aims to shed light on key challenges, highlight answers from current accounting standards and guidance, point out potential inconsistencies or limits, and outline potential solutions from the industrial ecology community through systemic environmental assessment tools, such as life cycle assessment (LCA) and environmentally-extended input-output (EEIO) analysis. Results and discussion: We propose a Measure-Reduce-Neutralize-Control sequence allowing organizations to plan their sustainable net-zero strategy, and discuss 24 accounting challenges occurring within this sequence. We then outline ways forward for organizations planning their carbon neutrality trajectory, pointing to existing resources, and for guidelines providers and the industrial ecology communities to address current limitations in the development of future accounting methods and guidelines. Overarching solutions to many accounting issues are to develop comprehensive, open-source, and high-quality life cycle inventory databases, to enable improved dynamic assessments and prospective LCA through integrated assessment models, to refine methods for assessing mineral scarcity and environmental impacts, the supply in some metals being expected to be a bottleneck to the energy transition, and to identify the appropriate climate metrics for planning sustainable carbon neutrality pathways at the organizational level.
Glioblastoma, a highly aggressive brain tumor, poses major challenges due to its poor prognosis and high morbidity rates. Partial differential equation-based models offer promising potential to enhance therapeutic outcomes by simulating patient-specific tumor behavior for improved radiotherapy planning. However, model calibration remains a bottleneck due to the high computational demands of optimization methods like Monte Carlo sampling and evolutionary algorithms. To address this, we recently introduced an approach leveraging a neural forward solver with gradient-based optimization to significantly reduce calibration time. This approach requires a highly accurate and fully differentiable forward model. We investigate multiple architectures, including (i) an enhanced TumorSurrogate, (ii) a modified nnU-Net, and (iii) a 3D Vision Transformer (ViT). The optimized TumorSurrogate achieved the best overall results, excelling in both tumor outline matching and voxel-level prediction of tumor cell concentration. It halved the MSE relative to the baseline model and achieved the highest Dice score across all tumor cell concentration thresholds. Our study demonstrates significant enhancement in forward solver performance and outlines important future research directions.
We consider the spatial classification problem for monitoring using data collected by a coordinated team of mobile robots. Such classification problems arise in several applications including search-and-rescue and precision agriculture. Specifically, we want to classify the regions of a search environment into interesting and uninteresting as quickly as possible using a team of mobile sensors and mobile charging stations. We develop a data-driven strategy that accommodates the noise in sensed data and the limited energy capacity of the sensors, and generates collision-free motion plans for the team. We propose a bi-level approach, where a high-level planner leverages a multi-armed bandit framework to determine the potential regions of interest for the drones to visit next based on the data collected online. Then, a low-level path planner based on integer programming coordinates the paths for the team to visit the target regions subject to the physical constraints. We characterize several theoretical properties of the proposed approach, including anytime guarantees and task completion time. We show the efficacy of our approach in simulation, and further validate these observations in physical experiments using mobile robots.
Satellite communication is a key technology in our modern connected world. With increasingly complex hardware, one challenge is to efficiently configure links (connections) on a satellite transponder. Planning an optimal link configuration is extremely complex and depends on many parameters and metrics. The optimal use of the limited resources, bandwidth and power of the transponder is crucial. Such an optimization problem can be approximated using metaheuristic methods such as simulated annealing, but recent research results also show that reinforcement learning can achieve comparable or even better performance in optimization methods. However, there have not yet been any studies on link configuration on satellite transponders. In order to close this research gap, a transponder environment was developed as part of this work. For this environment, the performance of the reinforcement learning algorithm PPO was compared with the metaheuristic simulated annealing in two experiments. The results show that Simulated Annealing delivers better results for this static problem than the PPO algorithm, however, the research in turn also underlines the potential of reinforcement learning for optimization problems.
We search for reflection-dominated Compton-thick active galactic nuclei (CT AGN) candidates in the Lockman Hole region using the data of SRG/eROSITA Lockman Hole survey. We selected sources with anomalously hard photon indices in the $0.3 - 8.0$ keV band, untypical for type I AGN. In particular, we required that the upper end of the $90\%$ error interval did not exceed a fiducial boundary of $\Gamma=1.3$. We found 291 sources which constitute a rare subpopulation among extragalactic X-ray sources detected by eROSITA in the Lockman Hole field, $\approx 5\%$. These sources constitute the eROSITA sample of CT AGN candidates in the Lockman Hole field. We further divide the sources into three categories depending on the availability of reliable redshift and statistically significant detection of intrinsic absorption. We present two catalogues: the bright sample (37 sources) and the faint one (254). We estimate the fraction and sky density of reflection-dominated CT AGN candidates. We show examples of individual spectra and use stacking analysis to search for possible redshift evolution of their properties with redshift. We analyse combined eROSITA spectra of bright sources of different categories with a physically motivated spectral model UXCLUMPY and find them fully consistent with the fits to the about $\sim 1$ Msec XMM-Newton data for one of our reflection-dominated CT candidates, Type 2 galaxy $\text{SRGe J105348.6+573032}$. The catalogues of CT AGN candidates could be a good starting point for planning future studies and follow-ups at all wavelengths.
The effective design of patrol strategies is a difficult and complex problem, especially in medium and large areas. The objective is to plan, in a coordinated manner, the optimal routes for a set of patrols in a given area, in order to achieve maximum coverage of the area, while also trying to minimize the number of patrols. In this paper, we propose a multi-agent reinforcement learning (MARL) model, based on a decentralized partially observable Markov decision process, to plan unpredictable patrol routes within an urban environment represented as an undirected graph. The model attempts to maximize a target function that characterizes the environment within a given time frame. Our model has been tested to optimize police patrol routes in three medium-sized districts of the city of Malaga. The aim was to maximize surveillance coverage of the most crime-prone areas, based on actual crime data in the city. To address this problem, several MARL algorithms have been studied, and among these the Value Decomposition Proximal Policy Optimization (VDPPO) algorithm exhibited the best performance. We also introduce a novel metric, the coverage index, for the evaluation of the coverage performance of the routes generated by our model. This metric is inspired by the predictive accuracy index (PAI), which is commonly used in criminology to detect hotspots. Using this metric, we have evaluated the model under various scenarios in which the number of agents (or patrols), their starting positions, and the level of information they can observe in the environment have been modified. Results show that the coordinated routes generated by our model achieve a coverage of more than $90\%$ of the $3\%$ of graph nodes with the highest crime incidence, and $65\%$ for $20\%$ of these nodes; $3\%$ and $20\%$ represent the coverage standards for police resource allocation.
Semantic segmentation of remote sensing images is essential for various applications, including vegetation monitoring, disaster management, and urban planning. Previous studies have demonstrated that the self-attention mechanism (SA) is an effective approach for designing segmentation networks that can capture long-range pixel dependencies. SA enables the network to model the global dependencies between the input features, resulting in improved segmentation outcomes. However, the high density of attentional feature maps used in this mechanism causes exponential increases in computational complexity. Additionally, it introduces redundant information that negatively impacts the feature representation. Inspired by traditional threshold segmentation algorithms, we propose a novel threshold attention mechanism (TAM). This mechanism significantly reduces computational effort while also better modeling the correlation between different regions of the feature map. Based on TAM, we present a threshold attention network (TANet) for semantic segmentation. TANet consists of an attentional feature enhancement module (AFEM) for global feature enhancement of shallow features and a threshold attention pyramid pooling module (TAPP) for acquiring feature information at different scales for deep features. We have conducted extensive experiments on the ISPRS Vaihingen and Potsdam datasets. The results demonstrate the validity and superiority of our proposed TANet compared to the most state-of-the-art models.
The field of AI is undergoing a fundamental transition from generative models that can produce synthetic content to artificial agents that can plan and execute complex tasks with only limited human involvement. Companies that pioneered the development of language models have now built AI agents that can independently navigate the internet, perform a wide range of online tasks, and increasingly serve as AI personal assistants and virtual coworkers. The opportunities presented by this new technology are tremendous, as are the associated risks. Fortunately, there exist robust analytic frameworks for confronting many of these challenges, namely, the economic theory of principal-agent problems and the common law doctrine of agency relationships. Drawing on these frameworks, this Article makes three contributions. First, it uses agency law and theory to identify and characterize problems arising from AI agents, including issues of information asymmetry, discretionary authority, and loyalty. Second, it illustrates the limitations of conventional solutions to agency problems: incentive design, monitoring, and enforcement might not be effective for governing AI agents that make uninterpretable decisions and operate at unprecedented speed and scale. Third, the Article explores the implications of agency law and theory for designing and regulating AI agents, arguing that new technical and legal infrastructure is needed to support governance principles of inclusivity, visibility, and liability.
One of the themes that have been approached more and more within the specialised literature is being represented by economic cycles. The analysis of these is very useful in the long term predictions, in finding solutions for the economic raise and for detecting the economic crisis. At the same time, it is underlined in a lot of scientific and research papers, the importance of the sustainable development in the present and future society. In this paper we intend to bring contributions to the study of the cycles of a sustainable economy and we will analyse it having in mind the purpose of creating the sustainable economy. We will demonstrate the fact that curves that represent graphically all these, are not simple logistics anymore, bi-logistics or multilogistics curves, but curves in plan that are obtained by composing logistics functions with the function of the sustainable development or with the function that shapes the economic component of it mathematically. We will present an interpretation of mathematic models within the frame of the sustainable development.
Identifying optimal medical treatments to improve survival has long been a critical goal of pharmacoepidemiology. Traditionally, we use an average treatment effect measure to compare outcomes between treatment plans. However, new methods leveraging advantages of machine learning combined with the foundational tenets of causal inference are offering an alternative to the average treatment effect. Here, we use three unique, precision medicine algorithms (random forests, residual weighted learning, efficient augmentation relaxed learning) to identify optimal treatment rules where patients receive the optimal treatment as indicated by their clinical history. First, we present a simple hypothetical example and a real-world application among heart failure patients using Medicare claims data. We next demonstrate how the optimal treatment rule improves the absolute risk in a hypothetical, three-modifier setting. Finally, we identify an optimal treatment rule that optimizes the time to outcome in a real-world heart failure setting. In both examples, we compare the average time to death under the optimized, tailored treatment rule with the average time to death under a universal treatment rule to show the benefit of precision medicine methods. The improvement under the optimal treatment rule in the real-world setting is greatest (additional ~9 days under the tailored rule) for survival time free of heart failure readmission.
Healthcare systems worldwide face persistent challenges in efficiency, accessibility, and personalization. Powered by modern AI technologies such as multimodal large language models and world models, Embodied AI (EmAI) represents a transformative frontier, offering enhanced autonomy and the ability to interact with the physical world to address these challenges. As an interdisciplinary and rapidly evolving research domain, "EmAI in healthcare" spans diverse fields such as algorithms, robotics, and biomedicine. This complexity underscores the importance of timely reviews and analyses to track advancements, address challenges, and foster cross-disciplinary collaboration. In this paper, we provide a comprehensive overview of the "brain" of EmAI for healthcare, wherein we introduce foundational AI algorithms for perception, actuation, planning, and memory, and focus on presenting the healthcare applications spanning clinical interventions, daily care & companionship, infrastructure support, and biomedical research. Despite its promise, the development of EmAI for healthcare is hindered by critical challenges such as safety concerns, gaps between simulation platforms and real-world applications, the absence of standardized benchmarks, and uneven progress across interdisciplinary domains. We discuss the technical barriers and explore ethical considerations, offering a forward-looking perspective on the future of EmAI in healthcare. A hierarchical framework of intelligent levels for EmAI systems is also introduced to guide further development. By providing systematic insights, this work aims to inspire innovation and practical applications, paving the way for a new era of intelligent, patient-centered healthcare.
We describe the development of a one-credit course to promote AI literacy at The University of Texas at Austin. In response to a call for the rapid deployment of class to serve a broad audience in Fall of 2023, we designed a 14-week seminar-style course that incorporated an interdisciplinary group of speakers who lectured on topics ranging from the fundamentals of AI to societal concerns including disinformation and employment. University students, faculty, and staff, and even community members outside of the University, were invited to enroll in this online offering: The Essentials of AI for Life and Society. We collected feedback from course participants through weekly reflections and a final survey. Satisfyingly, we found that attendees reported gains in their AI literacy. We sought critical feedback through quantitative and qualitative analysis, which uncovered challenges in designing a course for this general audience. We utilized the course feedback to design a three-credit version of the course that is being offered in Fall of 2024. The lessons we learned and our plans for this new iteration may serve as a guide to instructors designing AI courses for a broad audience.
The utilization of Unmanned Ground Vehicles (UGVs) for patrolling industrial sites has expanded significantly. These UGVs typically are equipped with perception systems, e.g., computer vision, with limited range due to sensor limitations or site topology. High-level control of the UGVs requires Coverage Path Planning (CPP) algorithms that navigate all relevant waypoints and promptly start the next cycle. In this paper, we propose the novel Fast-Revisit Coverage Path Planning (FaRe-CPP) algorithm using a greedy heuristic approach to propose waypoints for maximum coverage area and a random search-based path optimization technique to obtain a path along the proposed waypoints with minimum revisit time. We evaluated the algorithm in a simulated environment using Gazebo and a camera-equipped TurtleBot3 against a number of existing algorithms. Compared to their average revisit times and path lengths, our FaRe-CPP algorithm approximately showed a 45% and 40% reduction, respectively, in these highly relevant performance indicators.
An accelerated deployment of renewable energy sources is crucial for a successful transformation of the current energy system, with wind energy playing a key role in this transition. This study addresses the integrated wind farm layout and cable routing problem, a challenging nonlinear optimization problem. We model this problem as an extended version of the Quota Steiner Tree Problem (QSTP), optimizing turbine placement and network connectivity simultaneously to meet specified expansion targets. Our proposed approach accounts for the wake effect - a region of reduced wind speed induced by each installed turbine - and enforces minimum spacing between turbines. We introduce an exact solution framework in terms of the novel Quota Steiner Tree Problem with interference (QSTPI). By leveraging an interference-based splitting strategy, we develop an advanced solver capable of tackling large-scale problem instances. The presented approach outperforms generic state-of-the-art mixed integer programming solvers on our dataset by up to two orders of magnitude. Moreover, we demonstrate that our integrated method significantly reduces the costs in contrast to a sequential approach. Thus, we provide a planning tool that enhances existing planning methodologies for supporting a faster and cost-efficient expansion of wind energy.
In this paper, we present a human-based computation approach for the analysis of peripheral blood smear (PBS) images images in patients with Sickle Cell Disease (SCD). We used the Mechanical Turk microtask market to crowdsource the labeling of PBS images. We then use the expert-tagged erythrocytesIDB dataset to assess the accuracy and reliability of our proposal. Our results showed that when a robust consensus is achieved among the Mechanical Turk workers, probability of error is very low, based on comparison with expert analysis. This suggests that our proposed approach can be used to annotate datasets of PBS images, which can then be used to train automated methods for the diagnosis of SCD. In future work, we plan to explore the potential integration of our findings with outcomes obtained through automated methodologies. This could lead to the development of more accurate and reliable methods for the diagnosis of SCD
The early detection and prediction of health status decline among the elderly at the neighborhood level are of great significance for urban planning and public health policymaking. While existing studies affirm the connection between living environments and health outcomes, most rely on single data modalities or simplistic feature concatenation of multi-modal information, limiting their ability to comprehensively profile the health-oriented urban environments. To fill this gap, we propose CureGraph, a contrastive multi-modal representation learning framework for urban health prediction that employs graph-based techniques to infer the prevalence of common chronic diseases among the elderly within the urban living circles of each neighborhood. CureGraph leverages rich multi-modal information, including photos and textual reviews of residential areas and their surrounding points of interest, to generate urban neighborhood embeddings. By integrating pre-trained visual and textual encoders with graph modeling techniques, CureGraph captures cross-modal spatial dependencies, offering a comprehensive understanding of urban environments tailored to elderly health considerations. Extensive experiments on real-world datasets demonstrate that CureGraph improves the best baseline by $28\%$ on average in terms of $R^2$ across elderly disease risk prediction tasks. Moreover, the model enables the identification of stage-wise chronic disease progression and supports comparative public health analysis across neighborhoods, offering actionable insights for sustainable urban development and enhanced quality of life. The code is publicly available at https://github.com/jinlin2021/CureGraph.
Prognostic task is of great importance as it closely related to the survival analysis of patients, the optimization of treatment plans and the allocation of resources. The existing prognostic models have shown promising results on specific datasets, but there are limitations in two aspects. On the one hand, they merely explore certain types of modal data, such as patient histopathology WSI and gene expression analysis. On the other hand, they adopt the per-cancer-per-model paradigm, which means the trained models can only predict the prognostic effect of a single type of cancer, resulting in weak generalization ability. In this paper, a deep-learning based model, named UMPSNet, is proposed. Specifically, to comprehensively understand the condition of patients, in addition to constructing encoders for histopathology images and genomic expression profiles respectively, UMPSNet further integrates four types of important meta data (demographic information, cancer type information, treatment protocols, and diagnosis results) into text templates, and then introduces a text encoder to extract textual features. In addition, the optimal transport OT-based attention mechanism is utilized to align and fuse features of different modalities. Furthermore, a guided soft mixture of experts (GMoE) mechanism is introduced to effectively address the issue of distribution differences among multiple cancer datasets. By incorporating the multi-modality of patient data and joint training, UMPSNet outperforms all SOTA approaches, and moreover, it demonstrates the effectiveness and generalization ability of the proposed learning paradigm of a single model for multiple cancer types. The code of UMPSNet is available at https://github.com/binging512/UMPSNet.
The automatic identification of Magnetic Resonance Imaging (MRI) sequences can streamline clinical workflows by reducing the time radiologists spend manually sorting and identifying sequences, thereby enabling faster diagnosis and treatment planning for patients. However, the lack of standardization in the parameters of MRI scans poses challenges for automated systems and complicates the generation and utilization of datasets for machine learning research. To address this issue, we propose a system for MRI sequence identification using an unsupervised contrastive deep learning framework. By training a convolutional neural network based on the ResNet-18 architecture, our system classifies nine common MRI sequence types as a 9-class classification problem. The network was trained using an in-house internal dataset and validated on several public datasets, including BraTS, ADNI, Fused Radiology-Pathology Prostate Dataset, the Breast Cancer Dataset (ACRIN), among others, encompassing diverse acquisition protocols and requiring only 2D slices for training. Our system achieves a classification accuracy of over 0.95 across the nine most common MRI sequence types.
The challenge of traversability estimation is a crucial aspect of autonomous navigation in unstructured outdoor environments such as forests. It involves determining whether certain areas are passable or risky for robots, taking into account factors like terrain irregularities, slopes, and potential obstacles. The majority of current methods for traversability estimation operate on the assumption of an offline computation, overlooking the significant influence of the robot's heading direction on accurate traversability estimates. In this work, we introduce a deep neural network that uses detailed geometric environmental data together with the robot's recent movement characteristics. This fusion enables the generation of robot direction awareness and continuous traversability estimates, essential for enhancing robot autonomy in challenging terrains like dense forests. The efficacy and significance of our approach are underscored by experiments conducted on both simulated and real robotic platforms in various environments, yielding quantitatively superior performance results compared to existing methods. Moreover, we demonstrate that our method, trained exclusively in a high-fidelity simulated setting, can accurately predict traversability in real-world applications without any real data collection. Our experiments showcase the advantages of our method for optimizing path-planning and exploration tasks within difficult outdoor environments, underscoring its practicality for effective, real-world robotic navigation. In the spirit of collaborative advancement, we have made the code implementation available to the public.
We introduce ActiveGAMER, an active mapping system that utilizes 3D Gaussian Splatting (3DGS) to achieve high-quality, real-time scene mapping and exploration. Unlike traditional NeRF-based methods, which are computationally demanding and restrict active mapping performance, our approach leverages the efficient rendering capabilities of 3DGS, allowing effective and efficient exploration in complex environments. The core of our system is a rendering-based information gain module that dynamically identifies the most informative viewpoints for next-best-view planning, enhancing both geometric and photometric reconstruction accuracy. ActiveGAMER also integrates a carefully balanced framework, combining coarse-to-fine exploration, post-refinement, and a global-local keyframe selection strategy to maximize reconstruction completeness and fidelity. Our system autonomously explores and reconstructs environments with state-of-the-art geometric and photometric accuracy and completeness, significantly surpassing existing approaches in both aspects. Extensive evaluations on benchmark datasets such as Replica and MP3D highlight ActiveGAMER's effectiveness in active mapping tasks.
Automated vehicle (AV) acceptance relies on their understanding via feedback. While visualizations aim to enhance user understanding of AV's detection, prediction, and planning functionalities, establishing an optimal design is challenging. Traditional "one-size-fits-all" designs might be unsuitable, stemming from resource-intensive empirical evaluations. This paper introduces OptiCarVis, a set of Human-in-the-Loop (HITL) approaches using Multi-Objective Bayesian Optimization (MOBO) to optimize AV feedback visualizations. We compare conditions using eight expert and user-customized designs for a Warm-Start HITL MOBO. An online study (N=117) demonstrates OptiCarVis's efficacy in significantly improving trust, acceptance, perceived safety, and predictability without increasing cognitive load. OptiCarVis facilitates a comprehensive design space exploration, enhancing in-vehicle interfaces for optimal passenger experiences and broader applicability.
This project introduces a hierarchical planner integrating Linear Temporal Logic (LTL) constraints with natural language prompting for robot motion planning. The framework decomposes maps into regions, generates directed graphs, and converts them into transition systems for high-level planning. Text instructions are translated into LTL formulas and converted to Deterministic Finite Automata (DFA) for sequential goal-reaching tasks while adhering to safety constraints. High-level plans, derived via Breadth-First Search (BFS), guide low-level planners like Exploring Random Trees (RRT) and Probabilistic Roadmaps (PRM) for obstacle-avoidant navigation along with LTL tasks. The approach demonstrates adaptability to various task complexities, though challenges such as graph construction overhead and suboptimal path generation remain. Future directions include extending to considering terrain conditions and incorporating higher-order dynamics.
The Future Circular Hadron Collider (FCC-hh) will probe unprecedented energy regimes, enabling direct searches for new elementary particles at a scale of tens of TeV. FCC-hh is currently in the planning stage, and one of its primary physics goals is to search for physics beyond the Standard Model by exploring a previously inaccessible kinematic domain. While venturing into uncharted high-energy territories promises excitement, reconstructing objects with enormous transverse momenta will require overcoming major experimental challenges. This work investigates the identification of boosted $W$ bosons and boosted top quarks in the context of three beyond the Standard Model scenarios: heavy vector-like quark ($B'$), heavy neutral gauge boson ($Z'$), and heavy neutral Higgs boson ($H$). We employ machine learning techniques, including eXtreme Gradient Boosting (XGBoost) and convolutional neural networks (CNN), to identify these ultra-boosted objects in the collider from their SM background counterpart. We evaluate the performance of these techniques in distinguishing $W$ jets and top jets from QCD jets at extremely high transverse momenta ($p_{T}$) values, demonstrating their potential for future FCC-hh analyses.
This paper addresses the challenge of parking space detection in urban areas, focusing on the city of Granada. Utilizing aerial imagery, we develop and apply semantic segmentation techniques to accurately identify parked cars, moving cars and roads. A significant aspect of our research is the creation of a proprietary dataset specific to Granada, which is instrumental in training our neural network model. We employ Fully Convolutional Networks, Pyramid Networks and Dilated Convolutions, demonstrating their effectiveness in urban semantic segmentation. Our approach involves comparative analysis and optimization of various models, including Dynamic U-Net, PSPNet and DeepLabV3+, tailored for the segmentation of aerial images. The study includes a thorough experimentation phase, using datasets such as UDD5 and UAVid, alongside our custom Granada dataset. We evaluate our models using metrics like Foreground Accuracy, Dice Coefficient and Jaccard Index. Our results indicate that DeepLabV3+ offers the most promising performance. We conclude with future directions, emphasizing the need for a dedicated neural network for parked car detection and the potential for application in other urban environments. This work contributes to the fields of urban planning and traffic management, providing insights into efficient utilization of parking spaces through advanced image processing techniques.
This paper presents a novel method for accelerating path-planning tasks in unknown scenes with obstacles by utilizing Wasserstein Generative Adversarial Networks (WGANs) with Gradient Penalty (GP) to approximate the distribution of waypoints for a collision-free path using the Rapidly-exploring Random Tree algorithm. Our approach involves conditioning the WGAN-GP with a forward diffusion process in a continuous latent space to handle multimodal datasets effectively. We also propose encoding the waypoints of a collision-free path as a matrix, where the multidimensional ordering of the waypoints is naturally preserved. This method not only improves model learning but also enhances training convergence. Furthermore, we propose a method to assess whether the trained model fails to accurately capture the true waypoints. In such cases, we revert to uniform sampling to ensure the algorithm's probabilistic completeness; a process that traditionally involves manually determining an optimal ratio for each scenario in other machine learning-based methods. Our experiments demonstrate promising results in accelerating path-planning tasks under critical time constraints. The source code is openly available at https://bitbucket.org/joro3001/imagewgangpplanning/src/master/.
The increasing demand for high-speed and reliable wireless networks has driven advancements in technologies such as millimeter-wave and 5G radios, which requires efficient planning and timely deployment of wireless access points. A critical tool in this process is the radio map, a graphical representation of radio-frequency signal strengths that plays a vital role in optimizing overall network performance. However, existing methods for estimating radio maps face challenges due to the need for extensive real-world data collection or computationally intensive ray-tracing analyses, which is costly and time-consuming. Inspired by the success of generative AI techniques in large language models and image generation, we explore their potential applications in the realm of wireless networks. In this work, we propose RM-Gen, a novel generative framework leveraging conditional denoising diffusion probabilistic models to synthesize radio maps using minimal and readily collected data. We then introduce an environment-aware method for selecting critical data pieces, enhancing the generative model's applicability and usability. Comprehensive evaluations demonstrate that RM-Gen achieves over 95% accuracy in generating radio maps for networks that operate at 60 GHz and sub-6GHz frequency bands, outperforming the baseline GAN and pix2pix models. This approach offers a cost-effective, adaptable solution for various downstream network optimization tasks.
The residual queue during a given study period (e.g., peak hour) is an important feature that should be considered when solving a traffic assignment problem under equilibrium for strategic traffic planning. Although studies have focused extensively on static or quasi-dynamic traffic assignment models considering the residual queue, they have failed to capture the situation wherein the equilibrium link flow passing through the link is less than the link physical capacity under congested conditions. To address this critical issue, we introduce a novel static traffic assignment model that explicitly incorporates the residual queue and queue-dependent link capacity. The proposed model ensures that equilibrium link flows remain within the physical capacity bounds, yielding estimations more aligned with data observed by traffic detectors, especially in oversaturated scenarios. A generalized link cost function considering queue-dependent capacity, with an additional queuing delay term is proposed. The queuing delay term represents the added travel cost under congestion, offering a framework wherein conventional static models, both with and without physical capacity constraints, become special cases of our model. Our study rigorously analyzes the mathematical properties of the new model, establishing the theoretical uniqueness of solutions for link flow and residual queue under certain conditions. We also introduce a gradient projection-based alternating minimization algorithm tailored for the proposed model. Numerical examples are conducted to demonstrate the superiority and merit of the proposed model and solution algorithm.
We propose the Cooperative Aerial Robot Inspection Challenge (CARIC), a simulation-based benchmark for motion planning algorithms in heterogeneous multi-UAV systems. CARIC features UAV teams with complementary sensors, realistic constraints, and evaluation metrics prioritizing inspection quality and efficiency. It offers a ready-to-use perception-control software stack and diverse scenarios to support the development and evaluation of task allocation and motion planning algorithms. Competitions using CARIC were held at IEEE CDC 2023 and the IROS 2024 Workshop on Multi-Robot Perception and Navigation, attracting innovative solutions from research teams worldwide. This paper examines the top three teams from CDC 2023, analyzing their exploration, inspection, and task allocation strategies while drawing insights into their performance across scenarios. The results highlight the task's complexity and suggest promising directions for future research in cooperative multi-UAV systems.
Efficient motion planning for Aerial Manipulators (AMs) is essential for tackling complex manipulation tasks, yet achieving coupled trajectory planning remains challenging. In this work, we propose, to the best of our knowledge, the first whole-body integrated motion planning framework for aerial manipulators, which is facilitated by an improved Safe Flight Corridor (SFC) generation strategy and high-dimensional collision-free trajectory planning. In particular, we formulate an optimization problem to generate feasible trajectories for both the quadrotor and manipulator while ensuring collision avoidance, dynamic feasibility, kinematic feasibility, and waypoint constraints. To achieve collision avoidance, we introduce a variable geometry approximation method, which dynamically models the changing collision volume induced by different manipulator configurations. Moreover, waypoint constraints in our framework are defined in $\mathrm{SE(3)\times\mathbb{R}^3}$, allowing the aerial manipulator to traverse specified positions while maintaining desired attitudes and end-effector states. The effectiveness of our framework is validated through comprehensive simulations and real-world experiments across various environments.
The next-generation Very Large Array (ngVLA) is intended to be the premier centimeter-wavelength facility for astronomy and astrophysics, building on the substantial scientific legacies of the Karl G. Jansky Very Large Array (VLA) and the Very Long Baseline Array (VLBA). The ngVLA would open a new window on the Universe through ultra-sensitive imaging of thermal line and continuum emission to milliarcsecond resolution, while delivering unprecedented broad-band continuum imaging and polarimetry of non-thermal emission. The ngVLA would provide a critical electromagnetic complement to a suite of particle detectors and gravitational-wave observatories, as well as space- and ground-based telescopes operating from infrared to gamma-ray wavelengths, hence enabling multi-messenger and multi-band astronomy and astrophysics. Current construction plans call for the ngVLA to leverage some of the physical infrastructure of both the VLA and the VLBA, potentially drawing on overlapping personnel and information infrastructure. Multiple options can be envisioned for a VLA+VLBA to ngVLA transition. In order to assess risks and benefits of possible transition plans, the ngVLA project established the VLA+VLBA to ngVLA Transition Advisory Group (TAG). The primary deliverable from the TAG is a ``VLA+VLBA to ngVLA Transition Option Concepts'' report (this report) that includes a prioritized list of transition options.
The accurate estimation of human activity in cities is one of the first steps towards understanding the structure of the urban environment. Human activities are highly granular and dynamic in spatial and temporal dimensions. Estimating confidence is crucial for decision-making in numerous applications such as urban management, retail, transport planning and emergency management. Detecting general trends in the flow of people between spatial locations is neither obvious nor easy due to the high cost of capturing these movements without compromising the privacy of those involved. This research intends to address this problem by examining the movement of people in a SmartStreetSensors network at a fine spatial and temporal resolution using a Transfer Entropy approach.
This research leverages Conformal Prediction (CP) in the form of Conformal Predictive Systems (CPS) to accurately estimate uncertainty in a suite of machine learning (ML)-based radio metric models [1] as well as in a 2-D map-based ML path loss model [2]. Utilizing diverse difficulty estimators, we construct 95% confidence prediction intervals (PIs) that are statistically robust. Our experiments demonstrate that CPS models, trained on Toronto datasets, generalize effectively to other cities such as Vancouver and Montreal, maintaining high coverage and reliability. Furthermore, the employed difficulty estimators identify challenging samples, leading to measurable reductions in RMSE as dataset difficulty decreases. These findings highlight the effectiveness of scalable and reliable uncertainty estimation through CPS in wireless network modeling, offering important potential insights for network planning, operations, and spectrum management.
Being widely adopted by the transportation and planning practitioners, the fundamental diagram (FD) is the primary tool used to relate the key macroscopic traffic variables of speed, flow, and density. We empirically analyze the relation between vehicular space-mean speeds and flows given different signal settings and postulate a parsimonious parametric function form of the traditional FD where its function parameters are explicitly modeled as a function of the signal plan factors. We validate the proposed formulation using data from signalized urban road segments in Salt Lake City, Utah, USA. The proposed formulation builds our understanding of how changes to signal settings impact the FDs, and more generally the congestion patterns, of signalized urban segments.
Micromobility vehicles, such as e-scooters, are increasingly popular in urban communities but present significant challenges in terms of road safety, user privacy, infrastructure planning, and civil engineering. Addressing these critical issues requires a large-scale and easily accessible research infrastructure to collect diverse mobility and contextual data from micromobility users in realistic settings. To this end, we present ScooterLab, a community research testbed comprising a fleet of customizable battery-powered micromobility vehicles retrofitted with advanced sensing, communication, and control capabilities. ScooterLab enables interdisciplinary research at the intersection of computing, mobility, and urban planning by providing researchers with tools to design and deploy customized sensing experiments and access curated datasets. The testbed will enable advances in machine learning, privacy, and urban transportation research while promoting sustainable mobility.
The increasing demand for flexible and efficient urban transportation solutions has spotlighted the limitations of traditional Demand Responsive Transport (DRT) systems, particularly in accommodating diverse passenger needs and dynamic urban environments. Autonomous Mobility-on-Demand (AMoD) systems have emerged as a promising alternative, leveraging connected and autonomous vehicles (CAVs) to provide responsive and adaptable services. However, existing methods primarily focus on either vehicle scheduling or path planning, which often simplify complex urban layouts and neglect the necessity for simultaneous coordination and mutual avoidance among CAVs. This oversimplification poses significant challenges to the deployment of AMoD systems in real-world scenarios. To address these gaps, we propose CoDriveVLM, a novel framework that integrates high-fidelity simultaneous dispatching and cooperative motion planning for future AMoD systems. Our method harnesses Vision-Language Models (VLMs) to enhance multi-modality information processing, and this enables comprehensive dispatching and collision risk evaluation. The VLM-enhanced CAV dispatching coordinator is introduced to effectively manage complex and unforeseen AMoD conditions, thus supporting efficient scheduling decision-making. Furthermore, we propose a scalable decentralized cooperative motion planning method via consensus alternating direction method of multipliers (ADMM) focusing on collision risk evaluation and decentralized trajectory optimization. Simulation results demonstrate the feasibility and robustness of CoDriveVLM in various traffic conditions, showcasing its potential to significantly improve the fidelity and effectiveness of AMoD systems in future urban transportation networks. The code is available at https://github.com/henryhcliu/CoDriveVLM.git.
Carbon Monoxide (CO) is a dominant pollutant in urban areas due to the energy generation from fossil fuels for industry, automobile, and domestic requirements. Forecasting the evolution of CO in real-time can enable the deployment of effective early warning systems and intervention strategies. However, the computational cost associated with the physics and chemistry-based simulation makes it prohibitive to implement such a model at the city and country scale. To address this challenge, here, we present a machine learning model based on neural operator, namely, Complex Neural Operator for Air Quality (CoNOAir), that can effectively forecast CO concentrations. We demonstrate this by developing a country-level model for short-term (hourly) and long-term (72-hour) forecasts of CO concentrations. Our model outperforms state-of-the-art models such as Fourier neural operators (FNO) and provides reliable predictions for both short and long-term forecasts. We further analyse the capability of the model to capture extreme events and generate forecasts in urban cities in India. Interestingly, we observe that the model predicts the next hour CO concentrations with R2 values greater than 0.95 for all the cities considered. The deployment of such a model can greatly assist the governing bodies to provide early warning, plan intervention strategies, and develop effective strategies by considering several what-if scenarios. Altogether, the present approach could provide a fillip to real-time predictions of CO pollution in urban cities.
Portugal's prominent role as a global exporter of football talent is primarily driven by youth academies. Notably, Portugal leads the global ranking in terms of net transfer balance. This study aims to uncover and understand the recruitment strategies of Portuguese clubs for sourcing young talent and evaluate the relative success of different strategies. A comprehensive dataset spanning recent decades of Portuguese youth and professional football provides granular insights, including information such as players' birthplaces and the initial grassroots clubs where they developed. The initial findings suggest a correlation between a club's prominence and the geographic reach of its youth scouting operations, with larger clubs able to cast their net wider. Analysis of the correlation between players' birthplace and high-tier football club location suggests that the performance of senior teams acts as a catalyst for investment in youth teams. Regions without professional clubs are often left underserved. That said, certain clubs have made significant gains by focusing on player recruitment outside their district, such as the Algarve region, demonstrating how geographically targeted strategies can deliver substantial returns on investment. This study underscores data's role in sharpening youth player recruitment operations at football clubs. Clubs have access to in-depth and comprehensive datasets that can be used for resource allocation, territorial coverage planning, and identifying strategic partnerships with other clubs, potentially influencing their future success both on the field and financially. This offers opportunities for growth for individual clubs and holds implications for the continued strength of Portuguese football.
Robust treatment planning algorithms for Intensity Modulated Proton Therapy (IMPT) and Intensity Modulated Radiation Therapy (IMRT) allow for uncertainty reduction in the delivered dose distributions through explicit inclusion of error scenarios. Due to the curse of dimensionality, application of such algorithms can easily become computationally prohibitive. This work proposes a scenario-free probabilistic robust optimization algorithm that overcomes both the runtime and memory limitations typical of traditional robustness algorithms. The scenario-free approach minimizes cost-functions evaluated on expected-dose distributions and total variance. Calculation of these quantities relies on precomputed expected-dose-influence and total-variance-influence matrices, such that no scenarios need to be stored for optimization. The algorithm was developed within matRad and tested in several optimization configurations for photon and proton irradiation plans. A traditional robust optimization algorithm and a margin-based approach are used as a reference to benchmark the performances of the scenario-free algorithm in terms of plan quality, robustness and computational workload. The scenario-free approach achieves plan quality compatible with traditional robust optimization algorithms and it reduces the standard deviation within selected structures when variance reduction objectives are defined. Avoiding the storage of individual scenario information allows for the inclusion of an arbitrary number of error scenarios. The observed optimization time is independent on the number of included scenarios, compatible with a nominal, non-robust algorithm and significantly lower than the traditional robust approach. These properties make the scenario-free approach suitable for the optimization of robust plans involving a high number of error scenarios and CT phases as 4D robust optimization.
In recent years, explainability in machine learning has gained importance. In this context, counterfactual explanation (CE), which is an explanation method that uses examples, has attracted attention. However, it has been pointed out that CE is not robust when there are multiple machine-learning models with similar accuracy. These problems are important when using machine learning to make safe decisions. In this paper, we propose robust CEs that introduce a new viewpoint -- Pareto improvement -- and a method that uses multi-objective optimization to generate it. To evaluate the proposed method, we conducted experiments using both simulated and real data. The results demonstrate that the proposed method is both robust and practical. This study highlights the potential of ensuring robustness in decision-making by applying the concept of social welfare. We believe that this research can serve as a valuable foundation for various fields, including explainability in machine learning, decision-making, and action planning based on machine learning.
The automation of experiments in life sciences and chemistry has significantly advanced with the development of various instruments and AI technologies. However, achieving full laboratory automation, where experiments conceived by scientists are seamlessly executed in automated laboratories, remains a challenge. We identify the lack of automation in planning and operational tasks--critical human-managed processes collectively termed "care"--as a major barrier. Automating care is the key enabler for full laboratory automation. To address this, we propose the concept of self-maintainability (SeM): the ability of a laboratory system to autonomously adapt to internal and external disturbances, maintaining operational readiness akin to living cells. A SeM-enabled laboratory features autonomous recognition of its state, dynamic resource and information management, and adaptive responses to unexpected conditions. This shifts the planning and execution of experimental workflows, including scheduling and reagent allocation, from humans to the system. We present a conceptual framework for implementing SeM-enabled laboratories, comprising three modules--Requirement manager, Labware manager, and Device manager--and a Central manager. SeM not only enables scientists to execute envisioned experiments seamlessly but also provides developers with a design concept that drives the technological innovations needed for full automation.
The paper investigates the problem of path planning techniques for multi-copter uncrewed aerial vehicles (UAV) cooperation in a formation shape to examine surrounding surfaces. We first describe the problem as a joint objective cost for planning a path of the formation centroid working in a complicated space. The path planning algorithm, named the generalized particle swarm optimization algorithm, is then presented to construct an optimal, flyable path while avoiding obstacles and ensuring the flying mission requirements. A path-development scheme is then incorporated to generate a relevant path for each drone to maintain its position in the formation configuration. Simulation, comparison, and experiments have been conducted to verify the proposed approach. Results show the feasibility of the proposed path-planning algorithm with GEPSO.
A common challenge in home-based rehabilitation is muscle compensation induced by pain or fatigue, where patients with weakened primary muscles recruit secondary muscle groups to assist their movement, causing issues such as delayed rehabilitation progress or risk of further injury. In a home-based setting, the subtle compensatory actions may not be perceived since physiotherapists cannot directly observe patients. To address this problem, this study develops a novel wearable strain-sensor-based shoulder patch to detect fatigue-induced muscle compensation during bicep curl exercises. Built on an observation that the amplitude of a strain sensor's resistance is correlated to the motion of a joint that the sensor is attached to, we develop an algorithm that can robustly detect the state when significant changes appear in the shoulder joint motion, which indicates fatigue-induced muscle compensation in bicep curls. The developed shoulder patch is tested on 13 subjects who perform bicep curl exercises with a 5 kg dumbell until reaching fatigue. During the experiment, the performance of the shoulder patch is also benchmarked with optical tracking sensors and surface electromyography (sEMG) sensors. Results reveal that the proposed wearable sensor and detection methods effectively monitor fatigue-induced muscle compensation during bicep curl exercises in both Real-Time and Post Hoc modes. This development marks a significant step toward enhancing the effectiveness of home-based rehabilitation by providing physiotherapists with a tool to monitor and adjust treatment plans remotely.
The application of Multi-modal Large Language Models (MLLMs) in Autonomous Driving (AD) faces significant challenges due to their limited training on traffic-specific data and the absence of dedicated benchmarks for spatiotemporal understanding. This study addresses these issues by proposing TB-Bench, a comprehensive benchmark designed to evaluate MLLMs on understanding traffic behaviors across eight perception tasks from ego-centric views. We also introduce vision-language instruction tuning datasets, TB-100k and TB-250k, along with simple yet effective baselines for the tasks. Through extensive experiments, we show that existing MLLMs underperform in these tasks, with even a powerful model like GPT-4o achieving less than 35% accuracy on average. In contrast, when fine-tuned with TB-100k or TB-250k, our baseline models achieve average accuracy up to 85%, significantly enhancing performance on the tasks. Additionally, we demonstrate performance transfer by co-training TB-100k with another traffic dataset, leading to improved performance on the latter. Overall, this study represents a step forward by introducing a comprehensive benchmark, high-quality datasets, and baselines, thus supporting the gradual integration of MLLMs into the perception, prediction, and planning stages of AD.
Human mobility is a fundamental aspect of social behavior, with broad applications in transportation, urban planning, and epidemic modeling. However, for decades new mathematical formulas to model mobility phenomena have been scarce and usually discovered by analogy to physical processes, such as the gravity model and the radiation model. These sporadic discoveries are often thought to rely on intuition and luck in fitting empirical data. Here, we propose a systematic approach that leverages symbolic regression to automatically discover interpretable models from human mobility data. Our approach finds several well-known formulas, such as the distance decay effect and classical gravity models, as well as previously unknown ones, such as an exponential-power-law decay that can be explained by the maximum entropy principle. By relaxing the constraints on the complexity of model expressions, we further show how key variables of human mobility are progressively incorporated into the model, making this framework a powerful tool for revealing the underlying mathematical structures of complex social phenomena directly from observational data.
Network services are increasingly managed by considering chained-up virtual network functions and relevant traffic flows, known as the Service Function Chains (SFCs). To deal with sequential arrivals of SFCs in an online fashion, we must consider two closely-coupled problems - an SFC placement problem that maps SFCs to servers/links in the network and an SFC scheduling problem that determines when each SFC is executed. Solving the whole SFC problem targeting these two optimizations jointly is extremely challenging. In this paper, we propose a novel network diffuser using conditional generative modeling for this SFC placing-scheduling optimization. Recent advances in generative AI and diffusion models have made it possible to generate high-quality images/videos and decision trajectories from language description. We formulate the SFC optimization as a problem of generating a state sequence for planning and perform graph diffusion on the state trajectories to enable extraction of SFC decisions, with SFC optimization constraints and objectives as conditions. To address the lack of demonstration data due to NP-hardness and exponential problem space of the SFC optimization, we also propose a novel and somewhat maverick approach -- Rather than solving instances of this difficult optimization, we start with randomly-generated solutions as input, and then determine appropriate SFC optimization problems that render these solutions feasible. This inverse demonstration enables us to obtain sufficient expert demonstrations, i.e., problem-solution pairs, through further optimization. In our numerical evaluations, the proposed network diffuser outperforms learning and heuristic baselines, by $\sim$20\% improvement in SFC reward and $\sim$50\% reduction in SFC waiting time and blocking rate.
Existing methods for safe multi-agent control using logic specifications like Signal Temporal Logic (STL) often face scalability issues. This is because they rely either on single-agent perspectives or on Mixed Integer Linear Programming (MILP)-based planners, which are complex to optimize. These methods have proven to be computationally expensive and inefficient when dealing with a large number of agents. To address these limitations, we present a new scalable approach to multi-agent control in this setting. Our method treats the relationships between agents using a graph structure rather than in terms of a single-agent perspective. Moreover, it combines a multi-agent collision avoidance controller with a Graph Neural Network (GNN) based planner, models the system in a decentralized fashion, and trains on STL-based objectives to generate safe and efficient plans for multiple agents, thereby optimizing the satisfaction of complex temporal specifications while also facilitating multi-agent collision avoidance. Our experiments show that our approach significantly outperforms existing methods that use a state-of-the-art MILP-based planner in terms of scalability and performance. The project website is https://jeappen.com/mastl-gcbf-website/ and the code is at https://github.com/jeappen/mastl-gcbf .
The OpenUniverse2024 simulation suite is a cross-collaboration effort to produce matched simulated imaging for multiple surveys as they would observe a common simulated sky. Both the simulated data and associated tools used to produce it are intended to uniquely enable a wide range of studies to maximize the science potential of the next generation of cosmological surveys. We have produced simulated imaging for approximately 70 deg$^2$ of the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) Wide-Fast-Deep survey and the Nancy Grace Roman Space Telescope High-Latitude Wide-Area Survey, as well as overlapping versions of the ELAIS-S1 Deep-Drilling Field for LSST and the High-Latitude Time-Domain Survey for Roman. OpenUniverse2024 includes i) an early version of the updated extragalactic model called Diffsky, which substantially improves the realism of optical and infrared photometry of objects, compared to previous versions of these models; ii) updated transient models that extend through the wavelength range probed by Roman and Rubin; and iii) improved survey, telescope, and instrument realism based on up-to-date survey plans and known properties of the instruments. It is built on a new and updated suite of simulation tools that improves the ease of consistently simulating multiple observatories viewing the same sky. The approximately 400 TB of synthetic survey imaging and simulated universe catalogs are publicly available, and we preview some scientific uses of the simulations.
This paper aims to describe the Pointing Reconstruction Model (PRM) and the prototype Star Tracker, which will be mounted on LSPE-Strip, a microwave Q- and W-band CMB telescope planned for installation at the "Observatorio del Teide" in Tenerife. The PRM integrates information on the instantaneous attitude provided by the telescope control system to determine the actual pointing direction and focal plane orientation of the telescope. It accounts for various non-idealities in the telescope setup, represented by eight configuration angles, which will be calibrated using the Star Tracker. Following the derivation of the PRM formalism and its implementation, we investigate the pointing errors caused by incorrect calibration of these configuration angles to validate the required 1 arcminute maximum systematic pointing error for the LSPE-Strip survey. This paper also describes the main structure and operations of the Star Tracker and presents the results of a campaign of actual sky observations conducted with a prototype. The results demonstrate a Star Tracker RMS accuracy of approximately 3 arcseconds, while systematic errors remain below 10 arcseconds. Based on these results, we analyzed the problem of reconstructing the PRM configuration angles. Two methods for intercalibrating the Star Tracker's pointing direction with respect to the focal plane's pointing direction were examined: (1) observations of planets and (2) observations of a drone carrying both an optical beacon and a radio beacon. In the first case, an intercalibration accuracy between 1/3 arcminute and 1 arcminute is achievable. In the second case, the expected intercalibration accuracy ranges from 0.25 arcminute to 1 arcminute.
This mentoring resource is a guide to establishing and running near-peer mentorship programs. It is based on the working knowledge and best practices developed by the Access Network, a collection of nine student-led communities at universities across the country working towards a vision of a more diverse, equitable, inclusive, and accessible STEM environment. Many of these communities, also referred to as sites, include a near-peer mentoring program that is developed to best support their local context. The format of these programs vary, ranging from structured classes with peer mentoring groups to student clubs supporting 1-on-1 relationships. To further support program participants as both students and as whole people, sites often run additional events such as lecture series, workshops, and social activities guided tailored to each student community's needs. Through this process, student leaders have generated and honed best practices for all aspects of running their sites. This guide is an attempt to synthesize those efforts, offering practical advice for student leaders setting up near-peer mentorship programs in their own departments. It has been written through the lens of undergraduate near-peer mentorship programs, although our framework could easily be extended to other demographics (e.g. high schoolers, graduate students, etc.). Our experience is with STEM mentorship specifically, though these practices can extend to any discipline. In this document, we outline best practices for designing, running, and sustaining near-peer mentorship programs. We provide template resources to assist with this work, and lesson plans to run mentor and mentee training sessions. We hope you find this guide useful in designing, implementing, and re-evaluating community oriented near-peer mentoring programs.
Existing benchmarks for evaluating long-context language models (LCLMs) primarily focus on long-context recall, requiring models to produce short responses based on a few critical snippets while processing thousands of irrelevant tokens. We introduce LongProc (Long Procedural Generation), a new benchmark that requires both the integration of highly dispersed information and long-form generation. LongProc consists of six diverse procedural generation tasks, such as extracting structured information from HTML pages into a TSV format and executing complex search procedures to create travel plans. These tasks challenge LCLMs by testing their ability to follow detailed procedural instructions, synthesize and reason over dispersed information, and generate structured, long-form outputs (up to 8K tokens). Furthermore, as these tasks adhere to deterministic procedures and yield structured outputs, they enable reliable rule-based evaluation. We evaluate 17 LCLMs on LongProc across three difficulty levels, with maximum numbers of output tokens set at 500, 2K, and 8K. Notably, while all tested models claim a context window size above 32K tokens, open-weight models typically falter on 2K-token tasks, and closed-source models like GPT-4o show significant degradation on 8K-token tasks. Further analysis reveals that LCLMs struggle to maintain long-range coherence in long-form generations. These findings highlight critical limitations in current LCLMs and suggest substantial room for improvement. Data and code available at: https://princeton-pli.github.io/LongProc
Q-learning methods are widely used in robot path planning but often face challenges of inefficient search and slow convergence. We propose an Improved Q-learning (IQL) framework that enhances standard Q-learning in two significant ways. First, we introduce the Path Adaptive Collaborative Optimization (PACO) algorithm to optimize Q-table initialization, providing better initial estimates and accelerating learning. Second, we incorporate a Utility-Controlled Heuristic (UCH) mechanism with dynamically tuned parameters to optimize the reward function, enhancing the algorithm's accuracy and effectiveness in path-planning tasks. Extensive experiments in three different raster grid environments validate the superior performance of our IQL framework. The results demonstrate that our IQL algorithm outperforms existing methods, including FIQL, PP-QL-based CPP, DFQL, and QMABC algorithms, in terms of path-planning capabilities.
Simulation of urban wind environments is crucial for urban planning, pollution control, and renewable energy utilization. However, the computational requirements of high-fidelity computational fluid dynamics (CFD) methods make them impractical for real cities. To address these limitations, this study investigates the effectiveness of the Fourier Neural Operator (FNO) model in predicting flow fields under different wind directions and urban layouts. In this study, we investigate the effectiveness of the Fourier Neural Operator (FNO) model in predicting urban wind conditions under different wind directions and urban layouts. By training the model on velocity data from large eddy simulation data, we evaluate the performance of the model under different urban configurations and wind conditions. The results show that the FNO model can provide accurate predictions while significantly reducing the computational time by 99%. Our innovative approach of dividing the wind field into smaller spatial blocks for training improves the ability of the FNO model to capture wind frequency features effectively. The SDF data also provides important spatial building information, enhancing the model's ability to recognize physical boundaries and generate more realistic predictions. The proposed FNO approach enhances the AI model's generalizability for different wind directions and urban layouts.
Involving people in energy systems planning can increase the legitimacy and socio-political feasibility of energy transitions. Participatory research in energy modelling offers the opportunity to engage with stakeholders in a comprehensive way, but is limited by how results can be generated and presented without imposing assumptions and discrete scenarios on the participants. To this end, we present a methodology and a framework, based on near-optimal modelling results, that can incorporate stakeholders in a holistic and engaging way. We confront stakeholders with a continuum of modelling-based energy system designs via an interactive interface allowing them to choose essentially any combination of components that meet the system requirements. Together with information on the implications of different technologies, it is possible to assess how participants prioritise different aspects in energy systems planning while also facilitating learning in an engaging and stimulating way. We showcase the methodology for the remote Arctic settlement of Longyearbyen and illustrate how participants deviate consistently from the cost optimum. At the same time, they manage to balance different priorities such as emissions, costs, and system vulnerability leading to a better understanding of the complexity and intertwined nature of decisions.
TinyML has made deploying deep learning models on low-power edge devices feasible, creating new opportunities for real-time perception in constrained environments. However, the adaptability of such deep learning methods remains limited to data drift adaptation, lacking broader capabilities that account for the environment's underlying dynamics and inherent uncertainty. Deep learning's scaling laws, which counterbalance this limitation by massively up-scaling data and model size, cannot be applied when deploying on the Edge, where deep learning limitations are further amplified as models are scaled down for deployment on resource-constrained devices. This paper presents a smart agentic system capable of performing on-device perception and planning, enabling active sensing on the edge. By incorporating active inference into our solution, our approach extends beyond deep learning capabilities, allowing the system to plan in dynamic environments while operating in real time with a modest total model size of 2.3 MB. We showcase our proposed system by creating and deploying a saccade agent connected to an IoT camera with pan and tilt capabilities on an NVIDIA Jetson embedded device. The saccade agent controls the camera's field of view following optimal policies derived from the active inference principles, simulating human-like saccadic motion for surveillance and robotics applications.
Problem definition: Drones, despite being acknowledged as a transformative force in the city logistics sector, are unable to execute the \textit{last-meter delivery} (unloading goods directly to customers' doorsteps) due to airspace restrictions and safety concerns. To leverage advancements and overcome the limitations of drones in providing intra-city express services, we introduce a coordinated drone-courier logistics system where drones operate within a closed network among vertiports, while couriers connect customers to the drone delivery system. This paper aims to shed light on this coordinated system in terms of system feasibility, network interactivity, and long-term sustainability. Methodology/Results: We develop an integrated optimization model to optimize the network planning of the coordinated logistics system. The interplay between network planning and tactical operations is mirrored by a queueing network model, resulting in the nonlinear and nonconvex (partially convex and partially concave) feasible region of the optimization model. An iterative exact algorithm that tightens lower and upper bounds by adaptively refining the linear approximations of nonlinear constraints is developed to provide optimality-guaranteed solutions with finite convergence. The computational experiments demonstrate the scalability and robustness of our algorithm across various network configurations and scenarios.Managerial implications: The case study, based on a real-world dataset from SF Express, a logistics giant in China, validates that the coordinated logistics system efficiently attains cost and time savings by leveraging the effective turnover of drones and the coordination between drones and couriers. The optimal network design features a concentrated structure, streamlining demand consolidation and reducing deadhead repositioning.
It has been shown recently that physics-based simulation significantly enhances the disassembly capabilities of real-world assemblies with diverse 3D shapes and stringent motion constraints. However, the efficiency suffers when tackling intricate disassembly tasks that require numerous simulations and increased simulation time. In this work, we propose a State-Based Disassembly Planning (SBDP) approach, prioritizing physics-based simulation with translational motion over rotational motion to facilitate autonomy, reducing dependency on human input, while storing intermediate motion states to improve search scalability. We introduce two novel evaluation functions derived from new Directional Blocking Graphs (DBGs) enriched with state information to scale up the search. Our experiments show that SBDP with new evaluation functions and DBGs constraints outperforms the state-of-the-art in disassembly planning in terms of success rate and computational efficiency over benchmark datasets consisting of thousands of physically valid industrial assemblies.
Real-time object detection takes an essential part in the decision-making process of numerous real-world applications, including collision avoidance and path planning in autonomous driving systems. This paper presents a novel real-time streaming perception method named CorrDiff, designed to tackle the challenge of delays in real-time detection systems. The main contribution of CorrDiff lies in its adaptive delay-aware detector, which is able to utilize runtime-estimated temporal cues to predict objects' locations for multiple future frames, and selectively produce predictions that matches real-world time, effectively compensating for any communication and computational delays. The proposed model outperforms current state-of-the-art methods by leveraging motion estimation and feature enhancement, both for 1) single-frame detection for the current frame or the next frame, in terms of the metric mAP, and 2) the prediction for (multiple) future frame(s), in terms of the metric sAP (The sAP metric is to evaluate object detection algorithms in streaming scenarios, factoring in both latency and accuracy). It demonstrates robust performance across a range of devices, from powerful Tesla V100 to modest RTX 2080Ti, achieving the highest level of perceptual accuracy on all platforms. Unlike most state-of-the-art methods that struggle to complete computation within a single frame on less powerful devices, CorrDiff meets the stringent real-time processing requirements on all kinds of devices. The experimental results emphasize the system's adaptability and its potential to significantly improve the safety and reliability for many real-world systems, such as autonomous driving. Our code is completely open-sourced and is available at https://anonymous.4open.science/r/CorrDiff.
A Resistive Plate Chamber using Diamond-Like Carbon electrodes (DLC-RPC) has been developed as a background tagging detector in the MEG$~$II experiment. The DLC-RPC is planned to be installed in a high-intensity and low-momentum muon beam. This detector is required to have a detection efficiency above 90 % with four active gaps in the muon beam due to the limitation of the material budget. In such an environment, the high current flowing through the resistive electrodes causes a voltage drop, which reduces the performance of the DLC-RPC. This voltage drop can be suppressed by implementing a current evacuation pattern, though discharges are more likely to occur near the pattern. Therefore the pattern must be covered by a protection cover made of an insulator. In this study, electrode samples with a current evacuation pattern and different widths of protection cover (0.2 mm and 0.8 mm) have been produced, and their performance and stability were measured. The detection efficiency of a single-gap chamber for $\beta$-rays from a $^{90}$Sr source was measured to be up to approximately 60 % in both electrode samples. The target efficiency can be achieved even with a drop of 100 $-$ 150 V. On the other hand, after more than a dozen hours of operation, discharges suddenly occurred and the detector was prevented from further operation. These discharges created current paths on the spacing pillars. This serious problem must be investigated and solved in the future.
The pre-training and fine-tuning paradigm has revolutionized satellite remote sensing applications. However, this approach remains largely underexplored for airborne laser scanning (ALS), an important technology for applications such as forest management and urban planning. In this study, we address this gap by constructing a large-scale ALS point cloud dataset and evaluating its impact on downstream applications. Our dataset comprises ALS point clouds collected across the contiguous United States, provided by the United States Geological Survey's 3D Elevation Program. To ensure efficient data collection while capturing diverse land cover and terrain types, we introduce a geospatial sampling method that selects point cloud tiles based on land cover maps and digital elevation models. As a baseline self-supervised learning model, we adopt BEV-MAE, a state-of-the-art masked autoencoder for 3D outdoor point clouds, and pre-train it on the constructed dataset. The pre-trained models are subsequently fine-tuned for downstream tasks, including tree species classification, terrain scene recognition, and point cloud semantic segmentation. Our results show that the pre-trained models significantly outperform their scratch counterparts across all downstream tasks, demonstrating the transferability of the representations learned from the proposed dataset. Furthermore, we observe that scaling the dataset using our geospatial sampling method consistently enhances performance, whereas pre-training on datasets constructed with random sampling fails to achieve similar improvements. These findings highlight the utility of the constructed dataset and the effectiveness of our sampling strategy in the pre-training and fine-tuning paradigm. The source code and pre-trained models will be made publicly available at \url{https://github.com/martianxiu/ALS_pretraining}.
Quantum computing provides a novel approach to addressing conventionally intractable issues in large-scale optimization. Space logistics missions require the efficient routing of payloads, spacecraft, and resources across complex networks, often resulting in an exponential growth of the solution space that classical methods cannot efficiently solve. This paper leverages entropy quantum computing to model and solve the space logistics problem as a time-dependent multicommodity network flow, enabling the exploration of large solution spaces. The findings highlight quantum computing's potential to address complex aerospace logistics, demonstrating its suitability for complex interplanetary mission planning.
This paper introduce LongViTU, a large-scale (~121k QA pairs, ~900h videos), automatically generated dataset for long-form video understanding. We developed a systematic approach that organizes videos into a hierarchical tree structure and incorporates self-revision mechanisms to ensure high-quality QA pairs. Each QA pair in LongViTU features: 1) long-term context (average certificate length of 4.6 minutes); 2) rich knowledge and condensed reasoning (commonsense, causality, planning, etc.); and 3) explicit timestamp labels for relevant events. LongViTU also serves as a benchmark for instruction following in long-form and streaming video understanding. We evaluate the open-source state-of-the-art long video understanding model, LongVU, and the commercial model, Gemini-1.5-Pro, on our benchmark. They achieve GPT-4 scores of 49.9 and 52.3, respectively, underscoring the substantial challenge posed by our benchmark. Further supervised fine-tuning (SFT) on LongVU led to performance improvements of 12.0% on our benchmark, 2.2% on the in-distribution (ID) benchmark EgoSchema, 1.0%, 2.2% and 1.2% on the out-of-distribution (OOD) benchmarks VideoMME (Long), WorldQA and OpenEQA, respectively. These outcomes demonstrate LongViTU's high data quality and robust OOD generalizability.
The UAV-VLA (Visual-Language-Action) system is a tool designed to facilitate communication with aerial robots. By integrating satellite imagery processing with the Visual Language Model (VLM) and the powerful capabilities of GPT, UAV-VLA enables users to generate general flight paths-and-action plans through simple text requests. This system leverages the rich contextual information provided by satellite images, allowing for enhanced decision-making and mission planning. The combination of visual analysis by VLM and natural language processing by GPT can provide the user with the path-and-action set, making aerial operations more efficient and accessible. The newly developed method showed the difference in the length of the created trajectory in 22% and the mean error in finding the objects of interest on a map in 34.22 m by Euclidean distance in the K-Nearest Neighbors (KNN) approach.
Querying both structured and unstructured data has become a new paradigm in data analytics and recommendation. With unstructured data, such as text and videos, are converted to high-dimensional vectors and queried with approximate nearest neighbor search (ANNS). State-of-the-art database systems implement vector search as a plugin in the relational query engine, which tries to utilize the ANN index to enhance performance. After investigating a broad range of hybrid queries, we find that such designs may miss potential optimization opportunities and achieve suboptimal performance for certain queries. In this paper, we propose CHASE, a query engine that is natively designed to support efficient hybrid queries on structured and unstructured data. CHASE performs specific designs and optimizations on multiple stages in query processing. First, semantic analysis is performed to categorize queries and optimize query plans dynamically. Second, new physical operators are implemented to avoid redundant computations, which is the case with existing operators. Third, compilation-based techniques are adopted for efficient machine code generation. Extensive evaluations using real-world datasets demonstrate that CHASE achieves substantial performance improvements, with speedups ranging from 13% to an extraordinary 7500 times compared to existing systems. These results highlight CHASE's potential as a robust solution for executing hybrid queries.
Continuous harvesting and storage of multiple fruits in a single operation allow robots to significantly reduce the travel distance required for repetitive back-and-forth movements. Traditional collision-free path planning algorithms, such as Rapidly-Exploring Random Tree (RRT) and A-star (A), often fail to meet the demands of efficient continuous fruit harvesting due to their low search efficiency and the generation of excessive redundant points. This paper presents the Interactive Local Minima Search Algorithm (ILMSA), a fast path-planning method designed for the continuous harvesting of table-top grown strawberries. The algorithm featured an interactive node expansion strategy that iteratively extended and refined collision-free path segments based on local minima points. To enable the algorithm to function in 3D, the 3D environment was projected onto multiple 2D planes, generating optimal paths on each plane. The best path was then selected, followed by integrating and smoothing the 3D path segments. Simulations demonstrated that ILMSA outperformed existing methods, reducing path length by 21.5% and planning time by 97.1% compared to 3D-RRT, while achieving 11.6% shorter paths and 25.4% fewer nodes than the Lowest Point of the Strawberry (LPS) algorithm in 3D environments. In 2D, ILMSA achieved path lengths 16.2% shorter than A, 23.4% shorter than RRT, and 20.9% shorter than RRT-Connect, while being over 96% faster and generating significantly fewer nodes. Field tests confirmed ILMSA's suitability for complex agricultural tasks, having a combined planning and execution time and an average path length that were approximately 58% and 69%, respectively, of those achieved by the LPS algorithm.
Autonomous vessels potentially enhance safety and reliability of seaborne trade. To facilitate the development of autonomous vessels, high-fidelity simulations are required to model realistic interactions with other vessels. However, modeling realistic interactive maritime traffic is challenging due to the unstructured environment, coarsely specified traffic rules, and largely varying vessel types. Currently, there is no standard for simulating interactive maritime environments in order to rigorously benchmark autonomous vessel algorithms. In this paper, we introduce the first intelligent sailing model (ISM), which simulates rule-compliant vessels for navigation on the open sea. An ISM vessel reacts to other traffic participants according to maritime traffic rules while at the same time solving a motion planning task characterized by waypoints. In particular, the ISM monitors the applicable rules, generates rule-compliant waypoints accordingly, and utilizes a model predictive control for tracking the waypoints. We evaluate the ISM in two environments: interactive traffic with only ISM vessels and mixed traffic where some vessel trajectories are from recorded real-world maritime traffic data or handcrafted for criticality. Our results show that simulations with many ISM vessels of different vessel types are rule-compliant and scalable. We tested 4,049 critical traffic scenarios. For interactive traffic with ISM vessels, no collisions occurred while goal-reaching rates of about 97 percent were achieved. We believe that our ISM can serve as a standard for challenging and realistic maritime traffic simulation to accelerate autonomous vessel development.
Long-term and Large-scale Wireless Traffic Forecasting (LL-WTF) is pivotal for strategic network management and comprehensive planning on a macro scale. However, LL-WTF poses greater challenges than short-term ones due to the pronounced non-stationarity of extended wireless traffic and the vast number of nodes distributed at the city scale. To cope with this, we propose a Progressive Supervision method based on Label Decomposition (PSLD). Specifically, we first introduce a Random Subgraph Sampling (RSS) algorithm designed to sample a tractable subset from large-scale traffic data, thereby enabling efficient network training. Then, PSLD employs label decomposition to obtain multiple easy-to-learn components, which are learned progressively at shallow layers and combined at deep layers to effectively cope with the non-stationary problem raised by LL-WTF tasks. Finally, we compare the proposed method with various state-of-the-art (SOTA) methods on three large-scale WT datasets. Extensive experimental results demonstrate that the proposed PSLD significantly outperforms existing methods, with an average 2%, 4%, and 11% performance improvement on three WT datasets, respectively. In addition, we built an open source library for WT forecasting (WTFlib) to facilitate related research, which contains numerous SOTA methods and provides a strong benchmark.Experiments can be reproduced through https://github.com/Anoise/WTFlib.
Early-type galaxies (ETGs) are reference systems to understand galaxy formation and evolution processes. The physics of their collapse and internal dynamics are codified in well-known scaling relations. Cosmological hydrodynamical simulations play an important role, providing insights into the 3D distribution of matter and galaxy formation mechanisms, as well as validating methods to infer the properties of real objects. In this work, we present the closest-to-reality sample of ETGs from the IllustrisTNG100-1 simulation, dubbed "virtual-ETGs," based on an observational-like algorithm that combines standard projected and three-dimensional galaxy structural parameters. We extract 2D photometric information by projecting the galaxies' light into three planes and modeling them via S\'ersic profiles. Aperture velocity dispersions, corrected for softened central dynamics, are calculated along the line-of-sight orthogonal to the photometric projection plane. Central mass density profiles assume a power-law model, while 3D masses remain unmodified from the IllustrisTNG catalogue. The final catalogue includes $10121$ galaxies at redshifts $z \leq 0.1$. By comparing the virtual properties with observations, we find that the virtual-ETG scaling relations (e.g., size-mass, size-central surface brightness, and Faber-Jackson), central density slopes, and scaling relations among total density slopes and galaxy structural parameters are generally consistent with observations. We make the virtual-ETG publicly available for galaxy formation studies and plan to use this sample as a training set for machine learning tools to infer galaxy properties in future imaging and spectroscopic surveys.
For self-scheduling cascaded hydropower (S-CHP) facilities, medium-term planning is a critical step that coordinates water availability over the medium-term horizon, providing water usage guidance for their short-term operations in wholesale market participation. Typically, medium-term planning strategies (e.g., reservoir storage targets at the end of each short-term period) are determined by either optimization methods or rules of thumb. However, with the integration of variable renewable energy sources (VRESs), optimization-based methods suffer from deviations between the anticipated and actual reservoir storage, while rules of thumb could be financially conservative, thereby compromising short-term operating profitability in wholesale market participation. This paper presents a deep reinforcement learning (DRL)-based framework to derive medium-term planning policies for VRES-integrated S-CHPs (VS-CHPs), which can leverage contextual information underneath individual short-term periods and train planning policies by their induced short-term operating profits in wholesale market participation. The proposed DRL-based framework offers two practical merits. First, its planning strategies consider both seasonal requirements of reservoir storage and needs for short-term operating profits. Second, it adopts a multi-parametric programming-based strategy to accelerate the expensive training process associated with multi-step short-term operations. Finally, the DRL-based framework is evaluated on a real-world VS-CHP, demonstrating its advantages over current practice.
Power systems are critical infrastructure in modern society, and power outages can cause significant disruptions to communities and individuals' daily lives. The resilience of a power system measures its ability to maintain power supply during highly disruptive events such as hurricanes, earthquakes, and thunderstorms. Traditional methods for quantifying power system resilience include statistics-based and simulation-based approaches. Statistics-based methods offer a retrospective analysis of system performance without requiring a physical model, while simulation-based methods necessitate detailed physical system information and often simplify real-world scenarios. This paper introduces a deep learning-based method for evaluating power system resilience using historical power outage data. The method leverages the generalization capabilities of deep learning models and incorporates socio-economic and demographic factors as weighting terms to highlight the impacts on vulnerable demographic groups. The effectiveness of the proposed method is demonstrated through two case studies: one with real historical outage data and the other with simulated outage records. This approach provides valuable insights into measuring power system resilience against hazardous weather events without requiring a physical model of the target systems. The evaluation results can further guide the planning of distributed energy resources for resilience enhancement.
The official data collection for the Run 3 of the Large Hadron Collider (LHC) at CERN in Geneva commenced on July 5, 2022, following approximately three and a half years of maintenance, upgrades, and commissioning. Among the many upgrades to ALICE (A Large Ion Collider Experiment) is the new Fast Interaction Trigger (FIT) detector. Constant improvements to FIT's hardware, firmware, and software will enable progressively better performance. Between November 2024 and March 2025, during the year-end technical stop, an update to the communication path between the Front-End Electronics (FEE) and the Detector Control System (DCS) is planned. This update will introduce a new approach based on the ALFRED (ALICE Low-Level Front-End Device) software, supported by the central DCS ALICE system. To address the challenge of integrating custom electronics with distributed control systems, this paper describes a novel extension of the Front-End Device (FRED) framework, which can interface bespoke electronics with standard SCADA (Supervisory Control and Data Acquisition) systems using IPbus. This framework can be applied to all detectors utilizing IPbus communication.
The climatic change is one of the serious concerns nowadays. The impacts of climate change are global in scope and unprecedented in scale. Moreover, a small perturbation in climatic changes affects not only the pristine ecosystem but also the socioeconomic sectors. Specifically, the affect of climatic changes is related to frequent casualties. This makes it essential to dwelve deeper into analyzing the socio-climatic trends and variability. This work provides a comprehensive analysis of India's climatic trends, emphasizing on regional variations and specifically delving into the unique climate of Delhi. Specifically, this research unveils the temporal and spatial variations in temperature patterns by amalgamating extensive datasets encompassing India's diverse landscapes. The study uses advanced statistical tools and methodologies to scrutinize temperature's annual and seasonal variability. The insights drawn from this rigorous analysis may offer invaluable contributions to regional planning strategies, adaptive measures, and informed decision-making amidst the complex impacts of climate change. By bridging the gap between broader climatic trends and localized impacts, this research aims to facilitate more effective measures to mitigate and adapt to the multifaceted challenges of climate change, ensuring a more nuanced and tailored approaches. We utilized the Mann-Kendall test and Theil-Sen's slope estimator to analyze the trends and variability of the climatic conditions over the decades. The results demonstrate that temperature variations have increased over 0.58oC on average over the last decade. Moreover, over last decade the variability of Indian states shows that Lakshadweep faced the highest change (0.87oC), highlighting coastal vulnerability, while Tripura observed the least change of 0.07oC.
Despite widespread adoption of deep learning models to address a variety of computer vision tasks, planetary science has yet to see extensive utilization of such tools to address its unique problems. On Titan, the largest moon of Saturn, tracking seasonal trends and weather patterns of clouds provides crucial insights into one of the most complex climates in the Solar System, yet much of the available image data are still analyzed in a conventional way. In this work, we apply a Mask R-CNN trained via transfer learning to perform instance segmentation of clouds in Titan images acquired by the Cassini spacecraft - a previously unexplored approach to a big data problem in planetary science. We demonstrate that an automated technique can provide quantitative measures for clouds, such as areas and centroids, that may otherwise be prohibitively time-intensive to produce by human mapping. Furthermore, despite Titan specific challenges, our approach yields accuracy comparable to contemporary cloud identification studies on Earth and other worlds. We compare the efficiencies of human-driven versus algorithmic approaches, showing that transfer learning provides speed-ups that may open new horizons for data investigation for Titan. Moreover, we suggest that such approaches have broad potential for application to similar problems in planetary science where they are currently under-utilized. Future planned missions to the planets and remote sensing initiatives for the Earth promise to provide a deluge of image data in the coming years that will benefit strongly from leveraging machine learning approaches to perform the analysis.
This paper explores an eclectic range of path-planning methodologies engineered for rolling surfaces. Our focus is on the kinematic intricacies of rolling contact systems, which are investigated through a motion planning lens. Beyond summarizing the approaches to single-contact rotational surfaces, we explore the challenging domain of spin-rolling multi-contact systems. Our work proposes solutions for the higher-dimensional problem of multiple rotating objects in contact. Venturing beyond kinematics, these methodologies find application across a spectrum of domains, including rolling robots, reconfigurable swarm robotics, micro/nano manipulation, and nonprehensile manipulations. Through meticulously examining established planning strategies, we unveil their practical implementations in various real-world scenarios, from intricate dexterous manipulation tasks to the nimble manoeuvring of rolling robots and even shape planning of multi-contact swarms of particles. This study introduces the persistent challenges and unexplored frontiers of robotics, intricately linked to both path planning and mechanism design. As we illuminate existing solutions, we also set the stage for future breakthroughs in this dynamic and rapidly evolving field by highlighting the critical importance of addressing rolling contact problems.
The Deep Web is constituted by data that are accessible through Web pages, but not readily indexable by search engines as they are returned in dynamic pages. In this paper we propose a conceptual framework for answering keyword queries on Deep Web sources represented as relational tables with so-called access limitations. We formalize the notion of optimal answer, characterize queries for which an answer can be found, and present a method for query processing based on the construction of a query plan that minimizes the accesses to the data sources.
Although the star formation process has been studied for decades, many important aspects of the physics involved remain unsolved. Recent advancement of instrumentation in the infrared, far-infrared and sub-millimetre wavelength regimes have contributed to a significantly improved understanding of processes in the interstellar medium (ISM) leading to star formation. The future of research on the ISM and star formation looks exciting with instruments like the JWST, ALMA, etc., already contributing to the topic by gathering high-resolution high-sensitivity data and with several larger ground- and space-bound facilities either being planned or constructed. India has a sizable number of astronomers engaged in research on topics related to the ISM and star formation. In this white paper invited by the Astronomical Society of India to prepare a vision document for Indian astronomy, we review the Indian contributions to the global understanding of the star formation process and suggest areas that require focused efforts both in creating observing facilities and in theoretical front in India, in order to improve the impact of our research in the coming decades.
In daily domestic settings, frequently used objects like cups often have unfixed positions and multiple instances within the same category, and their carriers frequently change as well. As a result, it becomes challenging for a robot to efficiently navigate to a specific instance. To tackle this challenge, the robot must capture and update scene changes and plans continuously. However, current object navigation approaches primarily focus on the semantic level and lack the ability to dynamically update scene representation. In contrast, this paper captures the relationships between frequently used objects and their static carriers. It constructs an open-vocabulary Carrier-Relationship Scene Graph (CRSG) and updates the carrying status during robot navigation to reflect the dynamic changes of the scene. Based on the CRSG, we further propose an instance navigation strategy that models the navigation process as a Markov Decision Process. At each step, decisions are informed by the Large Language Model's commonsense knowledge and visual-language feature similarity. We designed a series of long-sequence navigation tasks for frequently used everyday items in the Habitat simulator. The results demonstrate that by updating the CRSG, the robot can efficiently navigate to moved targets. Additionally, we deployed our algorithm on a real robot and validated its practical effectiveness. The project page can be found here: https://OpenIN-nav.github.io.
An excellent estimate of the lensing signal is expected from the availability of deep and high-resolution polarization data in the near future. This is most important to allow for efficient delensing, needed to detect the primordial B-mode power and with it the famous tensor-to-scalar ratio. Here we discuss in a joint manner estimators of the rotation of polarization, of the second order lensing field rotation, and standard gradient lensing reconstruction. All are most efficient when able to probe the EB power created locally, have comparable reconstruction noise in this regime, and can benefit substantially from delensing. We discuss several ongoing and planned CMB experiments. We determine their noise for lensing field rotation and polarization rotation and discuss their prospects for measuring these effects. There is an on-going controversy on whether the lensing field rotation also rotates the polarization -- if so this will be observed at high significance soon with already on going observations of the South Pole Telescope, SPT-3G, in cross-correlation with tracers of large scale structure, as we show in this paper.
This study aims to optimize meal planning for nutritional health and cost efficiency using linear programming. Linear optimization provides an effective framework for addressing the problem of an optimal diet, as the composition of food can be naturally modeled as a linearly additive system. Leveraging a comprehensive nutrition dataset, our model minimizes meal costs while meeting specific nutritional requirements. We explore additional complexities, such as fractional weights and nutrient ratio constraints, enhancing the robustness of the solution. Case studies address common nutritional challenges, providing tailored diet plans. The significance lies in aiding individuals to form balanced, cost-effective dietary schedules, considering fitness goals and caloric needs. This research contributes to efficient, sustainable, and time-sensitive meal planning, emphasizing the intersection of nutrition, optimization, and real-world applicability.
The NINJA experiment aims to precisely measure neutrino-nucleus interactions using a nuclear emulsion detector to reduce systematic errors in neutrino oscillation experiments. The nuclear emulsion has a sub-micron positional resolution, enabling the detection of low-momentum charged particles such as protons with a threshold of 200 MeV/c. In the NINJA experiment, a muon detector placed downstream of the emulsion detector is used to identify muons from $\nu_{\mu}$ charged-current interactions. The majority of the tracks accumulated in the nuclear emulsion are from cosmic rays. Although the emulsion detector provides highly accurate positional information, it lacks timing information. Therefore, the positional resolution of the muon detector is not enough to identify neutrino interaction tracks that match between the muon detector and the emulsion detector from the enormous background of cosmic rays recorded in the emulsion detector. To address this, a scintillation tracker is used to provide both timing and positional information for the tracks. The NINJA experiment is planning a third physics run with about 130 kg water target from the autumn of 2025 to the spring of 2026. Since the target mass is larger than previous runs, a larger scintillation tracker covering 1.3 m $\times$ 1.4 m is needed. We are developing a newly designed scintillation tracker, consisting of a monolithic plastic scintillator plane including scatterers. In this paper, we will show the preparation status and plan for the next physics run, focusing particularly on the development of the new scintillation tracker.
A Multi-robot system (MRS) provides significant advantages for intricate tasks such as environmental monitoring, underwater inspections, and space missions. However, addressing potential communication failures or the lack of communication infrastructure in these fields remains a challenge. A significant portion of MRS research presumes that the system can maintain communication with proximity constraints, but this approach does not solve situations where communication is either non-existent, unreliable, or poses a security risk. Some approaches tackle this issue using predictions about other robots while not communicating, but these methods generally only permit agents to utilize first-order reasoning, which involves reasoning based purely on their own observations. In contrast, to deal with this problem, our proposed framework utilizes Theory of Mind (ToM), employing higher-order reasoning by shifting a robot's perspective to reason about a belief of others observations. Our approach has two main phases: i) an efficient runtime plan adaptation using active inference to signal intentions and reason about a robot's own belief and the beliefs of others in the system, and ii) a hierarchical epistemic planning framework to iteratively reason about the current MRS mission state. The proposed framework outperforms greedy and first-order reasoning approaches and is validated using simulations and experiments with heterogeneous robotic systems.
The contextual bandit problem, where agents arrive sequentially with personal contexts and the system adapts its arm allocation decisions accordingly, has recently garnered increasing attention for enabling more personalized outcomes. However, in many healthcare and recommendation applications, agents have private profiles and may misreport their contexts to gain from the system. For example, in adaptive clinical trials, where hospitals sequentially recruit volunteers to test multiple new treatments and adjust plans based on volunteers' reported profiles such as symptoms and interim data, participants may misreport severe side effects like allergy and nausea to avoid perceived suboptimal treatments. We are the first to study this issue of private context misreporting in a stochastic contextual bandit game between the system and non-repeated agents. We show that traditional low-regret algorithms, such as UCB family algorithms and Thompson sampling, fail to ensure truthful reporting and can result in linear regret in the worst case, while traditional truthful algorithms like explore-then-commit (ETC) and $\epsilon$-greedy algorithm incur sublinear but high regret. We propose a mechanism that uses a linear program to ensure truthfulness while minimizing deviation from Thompson sampling, yielding an $O(\ln T)$ frequentist regret. Our numerical experiments further demonstrate strong performance in multiple contexts and across other distribution families.
The development of general robotic systems capable of manipulating in unstructured environments is a significant challenge. While Vision-Language Models(VLM) excel in high-level commonsense reasoning, they lack the fine-grained 3D spatial understanding required for precise manipulation tasks. Fine-tuning VLM on robotic datasets to create Vision-Language-Action Models(VLA) is a potential solution, but it is hindered by high data collection costs and generalization issues. To address these challenges, we propose a novel object-centric representation that bridges the gap between VLM's high-level reasoning and the low-level precision required for manipulation. Our key insight is that an object's canonical space, defined by its functional affordances, provides a structured and semantically meaningful way to describe interaction primitives, such as points and directions. These primitives act as a bridge, translating VLM's commonsense reasoning into actionable 3D spatial constraints. In this context, we introduce a dual closed-loop, open-vocabulary robotic manipulation system: one loop for high-level planning through primitive resampling, interaction rendering and VLM checking, and another for low-level execution via 6D pose tracking. This design ensures robust, real-time control without requiring VLM fine-tuning. Extensive experiments demonstrate strong zero-shot generalization across diverse robotic manipulation tasks, highlighting the potential of this approach for automating large-scale simulation data generation.
Effective evaluation of real-time strategy tasks requires adaptive mechanisms to cope with dynamic and unpredictable environments. This study proposes a method to improve evaluation functions for real-time responsiveness to battle-field situation changes, utilizing an online reinforcement learning-based dynam-ic weight adjustment mechanism within the real-time strategy game. Building on traditional static evaluation functions, the method employs gradient descent in online reinforcement learning to update weights dynamically, incorporating weight decay techniques to ensure stability. Additionally, the AdamW optimizer is integrated to adjust the learning rate and decay rate of online reinforcement learning in real time, further reducing the dependency on manual parameter tun-ing. Round-robin competition experiments demonstrate that this method signifi-cantly enhances the application effectiveness of the Lanchester combat model evaluation function, Simple evaluation function, and Simple Sqrt evaluation function in planning algorithms including IDABCD, IDRTMinimax, and Port-folio AI. The method achieves a notable improvement in scores, with the en-hancement becoming more pronounced as the map size increases. Furthermore, the increase in evaluation function computation time induced by this method is kept below 6% for all evaluation functions and planning algorithms. The pro-posed dynamic adaptive evaluation function demonstrates a promising approach for real-time strategy task evaluation.
Robotic-assisted procedures offer numerous advantages over traditional approaches, including improved dexterity, reduced fatigue, minimized trauma, and superior outcomes. However, the main challenge of these systems remains the poor visualization and perception of the surgical field. The goal of this paper is to provide an innovative approach concerning an application able to improve the surgical procedures offering assistance in both preplanning and intraoperative steps of the surgery. The system has been designed to offer a better understanding of the patient through techniques that provide medical images visualization, 3D anatomical structures perception and robotic planning. The application was designed to be intuitive and user friendly, providing an augmented reality experience through the Hololens 2 device. It was tested in laboratory conditions, yielding positive results.
Enterprise Resource Planning (ERP) consultants play a vital role in customizing systems to meet specific business needs by processing large amounts of data and adapting functionalities. However, the process is resource-intensive, time-consuming, and requires continuous adjustments as business demands evolve. This research introduces a Self-Adaptive ERP Framework that automates customization using enterprise process models and system usage analysis. It leverages Artificial Intelligence (AI) & Natural Language Processing (NLP) for Petri nets to transform business processes into adaptable models, addressing both structural and functional matching. The framework, built using Design Science Research (DSR) and a Systematic Literature Review (SLR), reduces reliance on manual adjustments, improving ERP customization efficiency and accuracy while minimizing the need for consultants.
Green hydrogen is thought to be a game changer for reaching sustainability targets. However, the transition to a green hydrogen economy faces a critical challenge known as the `chicken-and-egg dilemma', wherein establishing a hydrogen supply network relies on demand, while demand only grows with reliable supply. In addition, as the hydrogen market is in the early stage, predicting demand distributions is challenging due to lack of data availability. This paper addresses these complex issues through a risk-averse framework with the introduction of a distributionally robust hydrogen network expansion planning problem under decision-dependent demand ambiguity. The problem optimizes location and production capacity decisions of the suppliers considering the moments of the stochastic hydrogen demand as a function of these investment decisions. To obtain tractable representations of this problem, we derive two different reformulations that consider continuous and discrete hydrogen demand support sets under different forms of decision dependencies. To efficiently solve the reformulations, we develop a tailored algorithm based on the column-and-constraint generation approach, and enhance the computational performance through solving the master problems to a relative optimality gap, decomposing the subproblems, and integrating pre-generated columns and constraints. To validate the effectiveness of our approach, we investigate a real case study leveraging data from the "Hydrogen Energy Applications in Valley Environments for Northern Netherlands (HEAVENN)" project. The results reveal that considering the chicken-and-egg dilemma under uncertain hydrogen market conditions leads to earlier and more diverse investments, providing critical insights for policymakers based on the degree of decision dependency.
Accurate segmentation of pulmonary structures iscrucial in clinical diagnosis, disease study, and treatment planning. Significant progress has been made in deep learning-based segmentation techniques, but most require much labeled data for training. Consequently, developing precise segmentation methods that demand fewer labeled datasets is paramount in medical image analysis. The emergence of pre-trained vision-language foundation models, such as CLIP, recently opened the door for universal computer vision tasks. Exploiting the generalization ability of these pre-trained foundation models on downstream tasks, such as segmentation, leads to unexpected performance with a relatively small amount of labeled data. However, exploring these models for pulmonary artery-vein segmentation is still limited. This paper proposes a novel framework called Language-guided self-adaptive Cross-Attention Fusion Framework. Our method adopts pre-trained CLIP as a strong feature extractor for generating the segmentation of 3D CT scans, while adaptively aggregating the cross-modality of text and image representations. We propose a s pecially designed adapter module to fine-tune pre-trained CLIP with a self-adaptive learning strategy to effectively fuse the two modalities of embeddings. We extensively validate our method on a local dataset, which is the largest pulmonary artery-vein CT dataset to date and consists of 718 labeled data in total. The experiments show that our method outperformed other state-of-the-art methods by a large margin. Our data and code will be made publicly available upon acceptance.
Trajectory prediction is crucial to advance autonomous driving, improving safety, and efficiency. Although end-to-end models based on deep learning have great potential, they often do not consider vehicle dynamic limitations, leading to unrealistic predictions. To address this problem, this work introduces a novel hybrid model that combines deep learning with a kinematic motion model. It is able to predict object attributes such as acceleration and yaw rate and generate trajectories based on them. A key contribution is the incorporation of expert knowledge into the learning objective of the deep learning model. This results in the constraint of the available action space, thus enabling the prediction of physically feasible object attributes and trajectories, thereby increasing safety and robustness. The proposed hybrid model facilitates enhanced interpretability, thereby reinforcing the trustworthiness of deep learning methods and promoting the development of safe planning solutions. Experiments conducted on the publicly available real-world Argoverse dataset demonstrate realistic driving behaviour, with benchmark comparisons and ablation studies showing promising results.
Urban segregation refers to the physical and social division of people, often driving inequalities within cities and exacerbating socioeconomic and racial tensions. While most studies focus on residential spaces, they often neglect segregation across "activity spaces" where people work, socialize, and engage in leisure. Human mobility data offers new opportunities to analyze broader segregation patterns, encompassing both residential and activity spaces, but challenges existing methods in capturing the complexity and local nuances of urban segregation. This work introduces InclusiViz, a novel visual analytics system for multi-level analysis of urban segregation, facilitating the development of targeted, data-driven interventions. Specifically, we developed a deep learning model to predict mobility patterns across social groups using environmental features, augmented with explainable AI to reveal how these features influence segregation. The system integrates innovative visualizations that allow users to explore segregation patterns from broad overviews to fine-grained detail and evaluate urban planning interventions with real-time feedback. We conducted a quantitative evaluation to validate the model's accuracy and efficiency. Two case studies and expert interviews with social scientists and urban analysts demonstrated the system's effectiveness, highlighting its potential to guide urban planning toward more inclusive cities.
Foundation models, particularly those that incorporate Transformer architectures, have demonstrated exceptional performance in domains such as natural language processing and image processing. Adapting these models to structured data, like tables, however, introduces significant challenges. These difficulties are even more pronounced when addressing multi-table data linked via foreign key, which is prevalent in the enterprise realm and crucial for empowering business use cases. Despite its substantial impact, research focusing on such linked business tables within enterprise settings remains a significantly important yet underexplored domain. To address this, we introduce a curated dataset sourced from an Enterprise Resource Planning (ERP) system, featuring extensive linked tables. This dataset is specifically designed to support research endeavors in table representation learning. By providing access to authentic enterprise data, our goal is to potentially enhance the effectiveness and applicability of models for real-world business contexts.
Statistical methods for clinical trial design are currently unable to rely on a sufficiently precise and general definition of what is an adequately powered study. Operationally, this definition is needed to ensure an alignment by design between statistical significance and clinical interpretability. To address this gap, this paper shows how to calibrate randomised trial designs to establishing strong clinical equipoise imbalance. Among several equipoise models, the least informed population distribution of the pre-trial odds of the design hypotheses is recommended here as the most practical calibrator. Under this model, primary analysis outcomes of common phase 3 superiority designs are shown to provide at least 90% evidence of equipoise imbalance. Designs carrying 95% power at 5% false positive rate are shown to demonstrate even stronger equipoise imbalance, providing an operational definition of a robustly powered study. Equipoise calibration is then applied to design of clinical development plans comprising randomised phase 2 and phase 3 studies. Development plans using oncology clinical endpoints are shown to provide strong equipoise imbalance when positive outcomes are observed in phase 2 and in phase 3. Establishing equipoise imbalance on a statistical basis when a positive phase 2 is not confirmed in phase 3 is shown to require large sample sizes unlikely to be associated with clinically meaningful effect sizes. Equipoise calibration is proposed as an effective clinical trial methodology ensuring that the statistical properties of clinical trial outcomes are clinically interpretable. Strong equipoise imbalance is achieved for designs carrying 95% power at 5% false positive rate, regardless of whether the primary outcome is positive or negative. Sponsors should consider raising power of their designs beyond current practice to achieve more conclusive results.
Unprecedented agility and dexterous manipulation have been demonstrated with controllers based on deep reinforcement learning (RL), with a significant impact on legged and humanoid robots. Modern tooling and simulation platforms, such as NVIDIA Isaac Sim, have been enabling such advances. This article focuses on demonstrating the applications of Isaac in local planning and obstacle avoidance as one of the most fundamental ways in which a mobile robot interacts with its environments. Although there is extensive research on proprioception-based RL policies, the article highlights less standardized and reproducible approaches to exteroception. At the same time, the article aims to provide a base framework for end-to-end local navigation policies and how a custom robot can be trained in such simulation environment. We benchmark end-to-end policies with the state-of-the-art Nav2, navigation stack in Robot Operating System (ROS). We also cover the sim-to-real transfer process by demonstrating zero-shot transferability of policies trained in the Isaac simulator to real-world robots. This is further evidenced by the tests with different simulated robots, which show the generalization of the learned policy. Finally, the benchmarks demonstrate comparable performance to Nav2, opening the door to quick deployment of state-of-the-art end-to-end local planners for custom robot platforms, but importantly furthering the possibilities by expanding the state and action spaces or task definitions for more complex missions. Overall, with this article we introduce the most important steps, and aspects to consider, in deploying RL policies for local path planning and obstacle avoidance with Isaac Sim training, Gazebo testing, and ROS 2 for real-time inference in real robots. The code is available at https://github.com/sahars93/RL-Navigation.
The manipulation of flexible objects such as cables, wires and fresh food items by robot hands forms a special challenge in robot grasp mechanics. This paper considers the steering of flexible linear objects in planar environments by two robot hands. The flexible linear object, modeled as an elastic non-stretchable rod, is manipulated by varying the gripping endpoint positions while keeping equal endpoint tangents. The flexible linear object shape has a closed form solution in terms of the grasp endpoint positions and tangents, called Euler's elastica. This paper obtains the elastica solutions under the optimal control framework, then uses the elastica solutions to obtain closed-form criteria for non self-intersection, stability and obstacle avoidance of the flexible linear object. The new tools are incorporated into a planning scheme for steering flexible linear objects in planar environments populated by sparsely spaced obstacles. The scheme is fully implemented and demonstrated with detailed examples.
Recent advances of foundation models (FMs) have made navigating mobile applications (apps) based on high-level goal instructions within reach, with significant industrial applications such as UI testing. While existing benchmarks evaluate FM-based UI navigation using the binary pass/fail metric, they have two major limitations: they cannot reflect the complex nature of mobile UI navigation where FMs may fail for various reasons (e.g., misunderstanding instructions and failed planning), and they lack industrial relevance due to oversimplified tasks that poorly represent real-world scenarios. To address the preceding limitations, we propose Sphinx, a comprehensive benchmark for multi-dimensional evaluation of FMs in industrial settings of UI navigation. Sphinx introduces a specialized toolkit that evaluates five essential FM capabilities, providing detailed insights into failure modes such as insufficient app knowledge or planning issues. Using both popular Google Play applications and WeChat's internal UI test cases, we evaluate 8 FMs with 20 different configurations. Our results show that existing FMs universally struggle with goal-based testing tasks, primarily due to insufficient UI-specific capabilities. We summarize seven lessons learned from benchmarking FMs with Sphinx, providing clear directions for improving FM-based mobile UI navigation.
Many countries and institutions are striving to develop tools to monitor their open science policies. Since 2018, with the launch of its National Plan for Open Science, France has been progressively implementing a monitoring framework for its public policy, relying exclusively on reliable, open, and controlled data. Currently, this monitoring focuses on research outputs, particularly publications, as well as theses and clinical trials. Publications serve as a basis for analyzing other dimensions, including research data, code, and software. The metadata associated with publications is therefore particularly valuable, but the methodology for leveraging it raises several challenges. Here, we briefly outline how we have used this metadata to construct the French Open Science Monitor.
Text recognition technology applied to street-view storefront signs is increasingly utilized across various practical domains, including map navigation, smart city planning analysis, and business value assessments in commercial districts. This technology holds significant research and commercial potential. Nevertheless, it faces numerous challenges. Street view images often contain signboards with complex designs and diverse text styles, complicating the text recognition process. A notable advancement in this field was introduced by our team in a recent competition. We developed a novel multistage approach that integrates multimodal feature fusion, extensive self-supervised training, and a Transformer-based large model. Furthermore, innovative techniques such as BoxDQN, which relies on reinforcement learning, and text rectification methods were employed, leading to impressive outcomes. Comprehensive experiments have validated the effectiveness of these methods, showcasing our potential to enhance text recognition capabilities in complex urban environments.
Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial in autonomous warehouse operations. Lifelong MAPF (L-MAPF), where agents are continuously reassigned new targets upon completing their current tasks, offers a more realistic approximation of real-world warehouse scenarios. While cache storage systems can enhance efficiency and reduce operational costs, existing approaches primarily rely on expectations and mathematical models, often without adequately addressing the challenges of multi-robot planning and execution. In this paper, we introduce a novel mechanism called Lifelong MAPF with Cache Mechanism (L-MAPF-CM), which integrates high-level cache storage with low-level path planning. We have involved a new type of map grid called cache for temporary item storage. Additionally, we involved a task assigner (TA) with a locking mechanism to bridge the gap between the new cache grid and L-MAPF algorithm. The TA dynamically allocates target locations to agents based on their status in various scenarios. We evaluated L-MAPF-CM using different cache replacement policies and task distributions. L-MAPF-CM has demonstrated performance improvements particularly with high cache hit rates and smooth traffic conditions.
This paper proposes a novel framework to handle a multi-agent path finding problem under a limited communication range constraint, where all agents must have a connected communication channel to the rest of the team. Many existing approaches to multi-agent path finding (e.g., leader-follower platooning) overcome computational challenges of planning in this domain by planning one agent at a time in a fixed order. However, fixed leader-follower approaches can become stuck during planning, limiting their practical utility in dense-clutter environments. To overcome this limitation, we develop dynamic leading multi-agent path finding, which allows for dynamic reselection of the leading agent during path planning whenever progress cannot be made. The experiments show the efficiency of our framework, which can handle up to 25 agents with more than 90% success-rate across five environment types where baselines routinely fail.
The Lane Keeping Assist (LKA) system has become a standard feature in recent car models. While marketed as providing auto-steering capabilities, the system's operational characteristics and safety performance remain underexplored, primarily due to a lack of real-world testing and comprehensive data. To fill this gap, we extensively tested mainstream LKA systems from leading U.S. automakers in Tampa, Florida. Using an innovative method, we collected a comprehensive dataset that includes full Controller Area Network (CAN) messages with LKA attributes, as well as video, perception, and lateral trajectory data from a high-quality front-facing camera equipped with advanced vision detection and trajectory planning algorithms. Our tests spanned diverse, challenging conditions, including complex road geometry, adverse weather, degraded lane markings, and their combinations. A vision language model (VLM) further annotated the videos to capture weather, lighting, and traffic features. Based on this dataset, we present an empirical overview of LKA's operational features and safety performance. Key findings indicate: (i) LKA is vulnerable to faint markings and low pavement contrast; (ii) it struggles in lane transitions (merges, diverges, intersections), often causing unintended departures or disengagements; (iii) steering torque limitations lead to frequent deviations on sharp turns, posing safety risks; and (iv) LKA systems consistently maintain rigid lane-centering, lacking adaptability on tight curves or near large vehicles such as trucks. We conclude by demonstrating how this dataset can guide both infrastructure planning and self-driving technology. In view of LKA's limitations, we recommend improvements in road geometry and pavement maintenance. Additionally, we illustrate how the dataset supports the development of human-like LKA systems via VLM fine-tuning and Chain of Thought reasoning.
Modeling noise in gravitational-wave observatories is crucial for accurately inferring the properties of gravitational-wave sources. We introduce a transdimensional Bayesian approach to characterise the noise in ground-based gravitational-wave observatories using the Bayesian inference software $\texttt{Bilby}$. The algorithm models broadband noise with a combination of power laws; narrowband features with Lorentzians; and shapelets to capture any additional features in the data. We show that our noise model provides a significantly improved fit of the LIGO and Virgo noise amplitude spectral densities compared to currently available noise fits obtained with on-source data segments. We perform astrophysical inference on well-known events in the third Gravitational-Wave Transient Catalog using our noise model and observe shifts of up to $7\%$ in the $90\%$ boundaries of credible intervals for some parameters. We discuss plans to deploy this framework systematically for gravitational-wave inference along with possible areas of improvement.
To facilitate the integration of distributed energy resources (DERs) into the wholesale market while maintaining the tractability of associated market operation tools such as unit commitment (UC), existing DER aggregation (DERA) studies usually consider that each DERA is presented on a single node of the transmission network. Nevertheless, the increasing scale and geographical distribution of DERs spur the emergence of DERAs covering multiple transmission nodes, posing new challenges in modeling such multi-transmission-node DERAs (M-DERAs). Indeed, assessing the aggregated impact of an M-DERA on power flows is a non-trivial task, because the sensitivities of each transmission line to DERs at different transmission nodes are not identical. Inspired by the distribution factor (DF) based shift factor (SF) aggregation strategy in industry practice, this paper proposes a novel DF-based chance-constrained UC (CCUC) model to determine system optimal operation plans with M-DERAs. DFs, treated as uncertain parameters to describe possible responses of DERs against aggregated dispatch instructions from regional transmission organizations, are modeled via a bounded hetero-dimensional mixture model (BHMM) by leveraging historical DF records distributed on multiple hyperplanes in a bounded space. With this, power flow limits are modeled as chance constraints in CCUC, which is reformulated into a scenarios-based stochastic form and solved by Benders decomposition. The proposed method is tested on an IEEE 24-bus system to illustrate its effectiveness in managing M-DERA integration while ensuring operational economics and mitigating the overloading of transmission lines.
The spectroscopic performance of an X-ray microcalorimeter is compromised at high count rates. In this study, we utilize the Resolve X-ray microcalorimeter onboard the XRISM satellite to examine the effects observed during high count rate measurements and propose modeling approaches to mitigate them. We specifically address the following instrumental effects that impact performance: CPU limit, pile-up, and untriggered electrical cross talk. Experimental data at high count rates were acquired during ground testing using the flight model instrument and a calibration X-ray source. In the experiment, data processing not limited by the performance of the onboard CPU was run in parallel, which cannot be done in orbit. This makes it possible to access the data degradation caused by limited CPU performance. We use these data to develop models that allow for a more accurate estimation of the aforementioned effects. To illustrate the application of these models in observation planning, we present a simulated observation of GX 13+1. Understanding and addressing these issues is crucial to enhancing the reliability and precision of X-ray spectroscopy in situations characterized by elevated count rates.
We study goal-conditioned RL through the lens of generalization, but not in the traditional sense of random augmentations and domain randomization. Rather, we aim to learn goal-directed policies that generalize with respect to the horizon: after training to reach nearby goals (which are easy to learn), these policies should succeed in reaching distant goals (which are quite challenging to learn). In the same way that invariance is closely linked with generalization is other areas of machine learning (e.g., normalization layers make a network invariant to scale, and therefore generalize to inputs of varying scales), we show that this notion of horizon generalization is closely linked with invariance to planning: a policy navigating towards a goal will select the same actions as if it were navigating to a waypoint en route to that goal. Thus, such a policy trained to reach nearby goals should succeed at reaching arbitrarily-distant goals. Our theoretical analysis proves that both horizon generalization and planning invariance are possible, under some assumptions. We present new experimental results and recall findings from prior work in support of our theoretical results. Taken together, our results open the door to studying how techniques for invariance and generalization developed in other areas of machine learning might be adapted to achieve this alluring property.
This paper presents a decentralized, online planning approach for scalable maneuver planning for large constellations. While decentralized, rule-based strategies have facilitated efficient scaling, optimal decision-making algorithms for satellite maneuvers remain underexplored. As commercial satellite constellations grow, there are benefits of online maneuver planning, such as using real-time trajectory predictions to improve state knowledge, thereby reducing maneuver frequency and conserving fuel. We address this gap in the research by treating the satellite maneuver planning problem as a Markov decision process (MDP). This approach enables the generation of optimal maneuver policies online with low computational cost. This formulation is applied to the low Earth orbit collision avoidance problem, considering the problem of an active spacecraft deciding to maneuver to avoid a non-maneuverable object. We test the policies we generate in a simulated low Earth orbit environment, and compare the results to traditional rule-based collision avoidance techniques.
Reinforcement learning (RL) enables an agent interacting with an unknown MDP $M$ to optimise its behaviour by observing transitions sampled from $M$. A natural entity that emerges in the agent's reasoning is $\widehat{M}$, the maximum likelihood estimate of $M$ based on the observed transitions. The well-known \textit{certainty-equivalence} method (CEM) dictates that the agent update its behaviour to $\widehat{\pi}$, which is an optimal policy for $\widehat{M}$. Not only is CEM intuitive, it has been shown to enjoy minimax-optimal sample complexity in some regions of the parameter space for PAC RL with a generative model~\citep{Agarwal2020GenModel}. A seemingly unrelated algorithm is the ``trajectory tree method'' (TTM)~\citep{Kearns+MN:1999}, originally developed for efficient decision-time planning in large POMDPs. This paper presents a theoretical investigation that stems from the surprising finding that CEM may indeed be viewed as an application of TTM. The qualitative benefits of this view are (1) new and simple proofs of sample complexity upper bounds for CEM, in fact under a (2) weaker assumption on the rewards than is prevalent in the current literature. Our analysis applies to both non-stationary and stationary MDPs. Quantitatively, we obtain (3) improvements in the sample-complexity upper bounds for CEM both for non-stationary and stationary MDPs, in the regime that the ``mistake probability'' $\delta$ is small. Additionally, we show (4) a lower bound on the sample complexity for finite-horizon MDPs, which establishes the minimax-optimality of our upper bound for non-stationary MDPs in the small-$\delta$ regime.
Electrooculography (EOG) is an electrophysiological signal that determines the human eye orientation and is therefore widely used in Human Tracking Interfaces (HCI). The purpose of this project is to develop a communication method for quadriplegic patients using EOG signals aimed at text and voice generation. The system consists of 3D eye movement tracking embedded using a custom-built prototype to measure the eyeball's left-right and up-down movements. The ESP32 board, which has a set of parameters to convert the data into content displayed on LCDs and MP3 players, is used to capture and process the signal. helps people by facilitating more natural and efficient symptom expression. The blink system will be able to incorporate face masks and more eye tests as it continues to develop. Even if it might work, more research and clinical trials are needed to evaluate the system's usefulness and ensure that it performs as planned in real-world scenarios. With this project, assistive technology will make significant progress and improve the lives of many who suffer from severe motor impairments.
Large language models hold promise for addressing medical challenges, such as medical diagnosis reasoning, research knowledge acquisition, clinical decision-making, and consumer health inquiry support. However, they often generate hallucinations due to limited medical knowledge. Incorporating external knowledge is therefore critical, which necessitates multi-source knowledge acquisition. We address this challenge by framing it as a source planning problem, which is to formulate context-appropriate queries tailored to the attributes of diverse sources. Existing approaches either overlook source planning or fail to achieve it effectively due to misalignment between the model's expectation of the sources and their actual content. To bridge this gap, we present MedOmniKB, a repository comprising multigenre and multi-structured medical knowledge sources. Leveraging these sources, we propose the Source Planning Optimisation method, which enhances multi-source utilisation. Our approach involves enabling an expert model to explore and evaluate potential plans while training a smaller model to learn source alignment. Experimental results demonstrate that our method substantially improves multi-source planning performance, enabling the optimised small model to achieve state-of-the-art results in leveraging diverse medical knowledge sources.
Unmanned aerial vehicles (UAVs) offer dynamic trajectory control, enabling them to avoid obstacles and establish line-of-sight (LoS) wireless channels with ground nodes (GNs), unlike traditional ground-fixed base stations. This study addresses the joint optimization of scheduling and three-dimensional (3D) trajectory planning for UAV-assisted wireless data harvesting. The objective is to maximize the minimum uplink throughput among GNs while accounting for signal blockages and building avoidance. To achieve this, we first present mathematical models designed to avoid cuboid-shaped buildings and to determine wireless signal blockage by buildings through rigorous mathematical proof. The optimization problem is formulated as nonconvex mixed-integer nonlinear programming and solved using advanced techniques. Specifically, the problem is decomposed into convex subproblems via quadratic transform and successive convex approximation. Building avoidance and signal blockage constraints are incorporated using the separating hyperplane method and an approximated indicator function. These subproblems are then iteratively solved using the block coordinate descent algorithm. Simulation results validate the effectiveness of the proposed approach. The UAV dynamically adjusts its trajectory and scheduling policy to maintain LoS channels with GNs, significantly enhancing network throughput compared to existing schemes. Moreover, the trajectory of the UAV adheres to building avoidance constraints for its continuous trajectory, ensuring uninterrupted operation and compliance with safety requirements.
The testing and quality assurance of cryogenic superconducting detectors is a time- and labor-intensive process. As experiments deploy increasingly larger arrays of detectors, new methods are needed for performing this testing quickly. Here, we propose a process for flagging under-performing detector wafers before they are ever tested cryogenically. Detectors are imaged under an optical microscope, and computer vision techniques are used to analyze the images, searching for visual defects and other predictors of poor performance. Pipeline performance is verified via a suite of images with simulated defects, yielding a detection accuracy of 98.6%. Lastly, results from running the pipeline on prototype microwave kinetic inductance detectors from the planned SPT-3G+ experiment are presented.
Modern sampling methods create ensembles of district maps that score well on discrete compactness scores, whereas the Polsby-Popper and other shape-based scores remain highly relevant for building fair maps and litigating unfair ones. The aim of this paper is twofold. First, we introduce population-weighted versions of shape-based scores and show a precise sense in which this interpolates between shape-based and discrete scores. Second, we introduce a modification of the ReCom sampling method that produces ensembles of maps with improved shape-based compactness scores.
The modelling of human mobility is vital for the understanding of the complexity of urban dynamics and guiding effective interventions to improve quality of life. Traditional modelling approaches focus on `average citizens,' which overlook the multitude of experiences from distinct sociodemographic groups. Recent studies have unveiled significant variations in mobility patterns related to gender and socioeconomic status, yet the impact of parenthood remains under-explored. Parenthood brings profound changes to daily routines, influenced by factors such as increased caregiving responsibilities, altered work-life balance, and the need for family-friendly environments. Parents often prioritise considerations such as cost of living, social wellbeing, environmental quality, and safety. Quantifying how `friendly' a city is becomes more and more important for parents, especially in the context of rising remote work opportunities which, in turn, reverberate on the choices on where to settle. This work investigates whether these considerations lead to distinct mobility patterns between parents and non-parents, also accounting for the impact of partnership. Using extensive census data across American cities, we analyse how parenthood and partnership reshape their urban experiences. Our findings indicate that cities can indeed be classified by their level of friendliness towards parents and partners. For example, Dallas and Nashville can be more suited for single individuals, New York and Chicago can be more accommodating to parents, while Washington and Baltimore favour married people. These insights contribute to the growing body of research advocating for more nuanced and equitable urban planning. By recognising the diverse needs of different demographic groups, particularly parents, our study underscores the importance of tailored urban design strategies over universal solutions.
Ischemic stroke, caused by cerebral vessel occlusion, presents substantial challenges in medical imaging due to the variability and subtlety of stroke lesions. Magnetic Resonance Imaging (MRI) plays a crucial role in diagnosing and managing ischemic stroke, yet existing segmentation techniques often fail to accurately delineate lesions. This study introduces a novel deep learning-based method for segmenting ischemic stroke lesions using multi-channel MRI modalities, including Diffusion Weighted Imaging (DWI), Apparent Diffusion Coefficient (ADC), and enhanced Diffusion Weighted Imaging (eDWI). The proposed architecture integrates DenseNet121 as the encoder with Self-Organized Operational Neural Networks (SelfONN) in the decoder, enhanced by Channel and Space Compound Attention (CSCA) and Double Squeeze-and-Excitation (DSE) blocks. Additionally, a custom loss function combining Dice Loss and Jaccard Loss with weighted averages is introduced to improve model performance. Trained and evaluated on the ISLES 2022 dataset, the model achieved Dice Similarity Coefficients (DSC) of 83.88% using DWI alone, 85.86% with DWI and ADC, and 87.49% with the integration of DWI, ADC, and eDWI. This approach not only outperforms existing methods but also addresses key limitations in current segmentation practices. These advancements significantly enhance diagnostic precision and treatment planning for ischemic stroke, providing valuable support for clinical decision-making.
In this paper, we study a secure integrated sensing and communication (ISAC) system employing a full-duplex base station with sensing capabilities against a mobile proactive adversarial target$\unicode{x2014}$a malicious unmanned aerial vehicle (M-UAV). We develop a game-theoretic model to enhance communication security, radar sensing accuracy, and power efficiency. The interaction between the legitimate network and the mobile adversary is formulated as a non-cooperative Stackelberg game (NSG), where the M-UAV acts as the leader and strategically adjusts its trajectory to improve its eavesdropping ability while conserving power and avoiding obstacles. In response, the legitimate network, acting as the follower, dynamically allocates resources to minimize network power usage while ensuring required secrecy rates and sensing performance. To address this challenging problem, we propose a low-complexity successive convex approximation (SCA) method for network resource optimization combined with a deep reinforcement learning (DRL) algorithm for adaptive M-UAV trajectory planning through sequential interactions and learning. Simulation results demonstrate the efficacy of the proposed method in addressing security challenges of dynamic ISAC systems in 6G, i.e., achieving a Stackelberg equilibrium with robust performance while mitigating the adversary's ability to intercept network signals.
Liquefaction is a significant geological hazard in earthquake-prone locations like Padang City, Indonesia. The phenomenon happens when saturated soil loses strength owing to seismic shaking, resulting in substantial infrastructure damage. Accurate identification of sensitive locations is critical to catastrophe mitigation. This study aims to map water distribution using optical satellite data and estimate its importance as a crucial element in determining liquefaction vulnerability. The Normalized Difference Water Index (NDWI) was used to assess water and vegetation indexes, taking advantage of its sensitivity to water content in varied land surfaces. We recommended using the NIR (near-infrared) and SWIR (short wave infrared) bands with 832.8 nm and 2202.4 nm, respectively, which are sensitive to soil water content. High-resolution satellite data were used to create NDWI maps, highlighting locations with high water saturation. These findings were combined with geological and seismic data to identify liquefaction-prone zones. The study found that locations with high water content, as measured by NDWI, are highly associated with greater liquefaction susceptibility. The findings highlight the importance of water distribution in determining soil behavior during seismic occurrences. This study highlights the value of NDWI as a low-cost and efficient tool for measuring liquefaction vulnerability at the regional level. The technique offers insights into Padang City's urban planning, catastrophe risk reduction, and community preparedness.
Localizing the seizure onset zone (SOZ) as a step of presurgical planning leads to higher efficiency in surgical and stimulation treatments. However, the clinical localization including structural, ictal, and invasive data acquisition and assessment is a difficult and long procedure with increasing challenges in patients with complex epileptic foci. The interictal methods are proposed to assist in presurgical planning with simpler data acquisition and higher speed. This study presents a spatiotemporal component classification for the localization of epileptic foci using resting-state functional magnetic resonance imaging data. This method is based on spatiotemporal independent component analysis on rsfMRI with a component-sorting procedure upon dominant power frequency, biophysical constraints, spatial lateralization, local connectivity, temporal energy, and functional non-Gaussianity. This method utilized the rs-fMRI potential to reach a high spatial accuracy in localizing epileptic foci from interictal data while retaining the reliability of results for clinical usage. Thirteen patients with temporal lobe epilepsy who underwent surgical resection and had seizure-free surgical outcomes after a 12-month follow-up were included in this study. All patients had presurgical structural MRI and rsfMRI while postsurgical MRI images were available for ten. Based on the relationship between the localized foci and resection, the results were classified into three groups fully concordant, partially concordant, and discordant. These groups had the resulting cluster aligned with, in the same lobe with, and outside the lobe of the resection area, respectively.
Humanoid robots have great potential to perform various human-level skills. These skills involve locomotion, manipulation, and cognitive capabilities. Driven by advances in machine learning and the strength of existing model-based approaches, these capabilities have progressed rapidly, but often separately. Therefore, a timely overview of current progress and future trends in this fast-evolving field is essential. This survey first summarizes the model-based planning and control that have been the backbone of humanoid robotics for the past three decades. We then explore emerging learning-based methods, with a focus on reinforcement learning and imitation learning that enhance the versatility of loco-manipulation skills. We examine the potential of integrating foundation models with humanoid embodiments, assessing the prospects for developing generalist humanoid agents. In addition, this survey covers emerging research for whole-body tactile sensing that unlocks new humanoid skills that involve physical interactions. The survey concludes with a discussion of the challenges and future trends.
The Vera C. Rubin Observatory will generate an unprecedented volume of data, including approximately 60 petabytes of raw data and around 30 trillion observed sources, posing a significant challenge for large-scale and end-user scientific analysis. As part of the LINCC Frameworks Project we are addressing these challenges with the development of the HATS (Hierarchical Adaptive Tiling Scheme) format and analysis package LSDB (Large Scale Database). HATS partitions data adaptively using a hierarchical tiling system to balance the file sizes, enabling efficient parallel analysis. Recent updates include improved metadata consistency, support for incremental updates, and enhanced compatibility with evolving datasets. LSDB complements HATS by providing a scalable, user-friendly interface for large catalog analysis, integrating spatial queries, crossmatching, and time-series tools while utilizing Dask for parallelization. We have successfully demonstrated the use of these tools with datasets such as ZTF and Pan-STARRS data releases on both cluster and cloud environments. We are deeply involved in several ongoing collaborations to ensure alignment with community needs, with future plans for IVOA standardization and support for upcoming Rubin, Euclid and Roman data. We provide our code and materials at lsdb.io.
We present a graph-theoretic modeling approach for hierarchical optimization that leverages the OptiGraph abstraction implemented in the Julia package Plasmo$.$jl. We show that the abstraction is flexible and can effectively capture complex hierarchical connectivity that arises from decision-making over multiple spatial and temporal scales (e.g., integration of planning, scheduling, and operations in manufacturing and infrastructures). We also show that the graph abstraction facilitates the conceptualization and implementation of decomposition and approximation schemes. Specifically, we propose a graph-based Benders decomposition (gBD) framework that enables the exploitation of hierarchical (nested) structures and that uses graph aggregation/partitioning procedures to discover such structures. In addition, we provide a Julia implementation of gBD, which we call PlasmoBenders$.$jl. We illustrate the capabilities using examples arising in the context of energy and power systems.
Osteosarcoma, the most common primary bone cancer, often requires accurate necrosis assessment from whole slide images (WSIs) for effective treatment planning and prognosis. However, manual assessments are subjective and prone to variability. In response, we introduce FDDM, a novel framework bridging the gap between patch classification and region-based segmentation. FDDM operates in two stages: patch-based classification, followed by region-based refinement, enabling cross-patch information intergation. Leveraging a newly curated dataset of osteosarcoma images, FDDM demonstrates superior segmentation performance, achieving up to a 10% improvement mIOU and a 32.12% enhancement in necrosis rate estimation over state-of-the-art methods. This framework sets a new benchmark in osteosarcoma assessment, highlighting the potential of foundation models and diffusion-based refinements in complex medical imaging tasks.
Conventional Public Transport (PT) cannot support the mobility needs in weak demand areas. Such areas could be better served by integrating, within PT, Demand-Responsive Transport (DRT), in which bus routes dynamically adapt to user demand. While the literature has focused on the level of service of DRT, it has overlooked its contribution to accessibility, which measures the ease of accessing opportunities (e.g, schools, jobs, other residents). Therefore, the following simple question remains unanswered: How many additional opportunities per hour can be reached when DRT is deployed? However, no method exists to quantify the accessibility resulting from the integration of conventional PT and DRT. We propose a novel method to compute isochrone-based accessibility. The main challenge is that, while accessibility isochrones are computed on top of a graph-model of the transport system, no graph can model DRT, since its routes are dynamic and stochastic. To overcome this issue, we propose a data-driven method, based on the analysis of multiple days of DRT operation. The methodology is tested on a case study in Acireale (Italy) simulated in Visum, where a many-to-many DRT service is integrated with a metropolitan mass transit. We show that, regarding the currently deployed conventional bus lines, the accessibility provided by DRT is much higher and its geographical distribution more equal. While current DRT planning is based exclusively on level of service and cost, our approach allows DRT planners and operators to shift their focus on accessibility.
Path planning is essential for unmanned aerial vehicles (UAVs) as it determines the path that the UAV needs to follow to complete a task. This work addresses this problem by introducing a new algorithm called navigation variable-based multi-objective particle swarm optimization (NMOPSO). It first models path planning as an optimization problem via the definition of a set of objective functions that include optimality and safety requirements for UAV operation. The NMOPSO is then used to minimize those functions through Pareto optimal solutions. The algorithm features a new path representation based on navigation variables to include kinematic constraints and exploit the maneuverable characteristics of the UAV. It also includes an adaptive mutation mechanism to enhance the diversity of the swarm for better solutions. Comparisons with various algorithms have been carried out to benchmark the proposed approach. The results indicate that the NMOPSO performs better than not only other particle swarm optimization variants but also other state-of-the-art multi-objective and metaheuristic optimization algorithms. Experiments have also been conducted with real UAVs to confirm the validity of the approach for practical flights. The source code of the algorithm is available at https://github.com/ngandng/NMOPSO.
Electric Vertical Take-off and Landing vehicles (eVTOLs) are driving Advanced Air Mobility (AAM) toward transforming urban transportation by extending travel from congested ground networks to low-altitude airspace. This transition promises to reduce traffic congestion and significantly shorten commute times. To ensure aviation safety, eVTOLs must fly within prescribed flight corridors. These corridors are managed by ground-based Air Traffic Control (ATCo) stations, which oversee air-ground communication and flight scheduling. However, one critical challenge remains: the lack of high rate air-ground communication and safe flight planning within these corridors. The introduction of 6G-oriented Stacked Intelligent Metasurface (SIM) technology presents a high rate communication solution. With advanced phase-shifting capabilities, SIM enables precise wireless signal control and supports beam-tracking communication with eVTOLs. Leveraging this technology, we propose a Composite Potential Field (CPF) approach. This method dynamically integrates target, separation, and communication fields to optimize both SIM communication efficiency and flight safety. Simulation results validate the effectiveness of this DT-based approach. Compared to the potential field flight control benchmark, it improves the transmission rate by 8.3\%. Additionally, it reduces flight distance deviation from the prescribed corridor by 10\% compared to predetermined optimization methods.
The advancement of machine learning and the availability of large-scale reaction datasets have accelerated the development of data-driven models for computer-aided synthesis planning (CASP) in the past decade. Here, we detail the newest version of ASKCOS, an open source software suite for synthesis planning that makes available several research advances in a freely available, practical tool. Four one-step retrosynthesis models form the basis of both interactive planning and automatic planning modes. Retrosynthetic planning is complemented by other modules for feasibility assessment and pathway evaluation, including reaction condition recommendation, reaction outcome prediction, and auxiliary capabilities such as solubility prediction and quantum mechanical descriptor prediction. ASKCOS has assisted hundreds of medicinal, synthetic, and process chemists in their day-to-day tasks, complementing expert decision making. It is our belief that CASP tools like ASKCOS are an important part of modern chemistry research, and that they offer ever-increasing utility and accessibility.
This paper presents a case study on how to process cooking recipes (and more generally, how-to instructions) in a way that makes it possible for a robot or artificial cooking assistant to support human chefs in the kitchen. Such AI assistants would be of great benefit to society, as they can help to sustain the autonomy of aging adults or people with a physical impairment, or they may reduce the stress in a professional kitchen. We propose a novel approach to computational recipe understanding that mimics the human sense-making process, which is narrative-based. Using an English recipe for almond crescent cookies as illustration, we show how recipes can be modelled as rich narrative structures by integrating various knowledge sources such as language processing, ontologies, and mental simulation. We show how such narrative structures can be used for (a) dealing with the challenges of recipe language, such as zero anaphora, (b) optimizing a robot's planning process, (c) measuring how well an AI system understands its current tasks, and (d) allowing recipe annotations to become language-independent.
Unstructured environments such as mountains, caves, construction sites, or disaster areas are challenging for autonomous navigation because of terrain irregularities. In particular, it is crucial to plan a path to avoid risky terrain and reach the goal quickly and safely. In this paper, we propose a method for safe and distance-efficient path planning, leveraging Traversal Risk Graph (TRG), a novel graph representation that takes into account geometric traversability of the terrain. TRG nodes represent stability and reachability of the terrain, while edges represent relative traversal risk-weighted path candidates. Additionally, TRG is constructed in a wavefront propagation manner and managed hierarchically, enabling real-time planning even in large-scale environments. Lastly, we formulate a graph optimization problem on TRG that leads the robot to navigate by prioritizing both safe and short paths. Our approach demonstrated superior safety, distance efficiency, and fast processing time compared to the conventional methods. It was also validated in several real-world experiments using a quadrupedal robot. Notably, TRG-planner contributed as the global path planner of an autonomous navigation framework for the DreamSTEP team, which won the Quadruped Robot Challenge at ICRA 2023. The project page is available at https://trg-planner.github.io .
Customer Identity and Access Management (CIAM) systems play a pivotal role in securing enterprise infrastructures. However, the complexity of implementing these systems requires careful architectural planning to ensure positive Return on Investment (RoI) and avoid costly delays. The proliferation of Active Persistent cyber threats, coupled with advancements in AI, cloud computing, and geographically distributed customer populations, necessitates a paradigm shift towards adaptive and zero-trust security frameworks. This paper introduces the Combined Hyper-Extensible Extremely-Secured Zero-Trust (CHEZ) CIAM-PAM architecture, designed specifically for large-scale enterprises. The CHEZ PL CIAM-PAM framework addresses critical security gaps by integrating federated identity management (private and public identities), password-less authentication, adaptive multi-factor authentication (MFA), microservice-based PEP (Policy Entitlement Point), multi-layer RBAC (Role Based Access Control) and multi-level trust systems. This future-proof design also includes end-to-end data encryption, and seamless integration with state-of-the-art AI-based threat detection systems, while ensuring compliance with stringent regulatory standards.
Humanoid robots must master numerous tasks with sparse rewards, posing a challenge for reinforcement learning (RL). We propose a method combining RL and automated planning to address this. Our approach uses short goal-conditioned policies (GCPs) organized hierarchically, with Monte Carlo Tree Search (MCTS) planning using high-level actions (HLAs). Instead of primitive actions, the planning process generates HLAs. A single plan-tree, maintained during the agent's lifetime, holds knowledge about goal achievement. This hierarchy enhances sample efficiency and speeds up reasoning by reusing HLAs and anticipating future actions. Our Hierarchical Goal-Conditioned Policy Planning (HGCPP) framework uniquely integrates GCPs, MCTS, and hierarchical RL, potentially improving exploration and planning in complex tasks.
This work presents Kinodynamic Adaptive Robot Coordination (K-ARC), a novel algorithm for multi-robot kinodynamic planning. Our experimental results show the capability of K-ARC to plan for up to 32 planar mobile robots, while achieving up to an order of magnitude of speed-up compared to previous methods in various scenarios. K-ARC is able to achieve this due to its two main properties. First, K-ARC constructs its solution iteratively by planning in segments, where initial kinodynamic paths are found through optimization-based approaches and the inter-robot conflicts are resolved through sampling-based approaches. The interleaving use of sampling-based and optimization-based approaches allows K-ARC to leverage the strengths of both approaches in different sections of the planning process where one is more suited than the other, while previous methods tend to emphasize on one over the other. Second, K-ARC builds on a previously proposed multi-robot motion planning framework, Adaptive Robot Coordination (ARC), and inherits its strength of focusing on coordination between robots only when needed, saving computation efforts. We show how the combination of these two properties allows K-ARC to achieve overall better performance in our simulated experiments with increasing numbers of robots, increasing degrees of problem difficulties, and increasing complexities of robot dynamics.
This paper presents a suite of machine learning models, CRC-ML-Radio Metrics, designed for modeling RSRP, RSRQ, and RSSI wireless radio metrics in 4G environments. These models utilize crowdsourced data with local environmental features to enhance prediction accuracy across both indoor at elevation and outdoor urban settings. They achieve RMSE performance of 9.76 to 11.69 dB for RSRP, 2.90 to 3.23 dB for RSRQ, and 9.50 to 10.36 dB for RSSI, evaluated on over 300,000 data points in the Toronto, Montreal, and Vancouver areas. These results demonstrate the robustness and adaptability of the models, supporting precise network planning and quality of service optimization in complex Canadian urban environments.
This paper reports an analysis of aspects of the project planning stage. The object of research is the decision-making processes that take place at this stage. This work considers the problem of building a hierarchy of tasks, their distribution among performers, taking into account restrictions on financial costs and duration of project implementation. Verbal and mathematical models of the task of constructing a hierarchy of tasks and other tasks that take place at the stage of project planning were constructed. Such indicators of the project implementation process efficiency were introduced as the time, cost, and cost-time efficiency. In order to be able to apply these criteria, the tasks of estimating the minimum value of the duration of the project and its minimum required cost were considered. Appropriate methods have been developed to solve them. The developed iterative method for assessing the minimum duration of project implementation is based on taking into account the possibility of simultaneous execution of various tasks. The method of estimating the minimum cost of the project is to build and solve the problem of Boolean programming. The values obtained as a result of solving these problems form an {\guillemotleft}ideal point{\guillemotright}, approaching which is enabled by the developed iterative method of constructing a hierarchy of tasks based on the method of sequential concessions. This method makes it possible to devise options for management decisions to obtain valid solutions to the problem. According to them, the decision maker can introduce a concession on the value of one or both components of the {\guillemotleft}ideal point{\guillemotright} or change the input data to the task. The models and methods built can be used when planning projects in education, science, production, etc.
Mortality forecasting is crucial for demographic planning and actuarial studies, particularly for predicting population ageing rates and future longevity risks. Traditional approaches largely rely on extrapolative methods, such as the Lee-Carter model and its variants which use mortality rates as inputs. In recent years, compositional data analysis (CoDA), which adheres to summability and non-negativity constraints, has gained increasing attention from researchers for its application in mortality forecasting. This study explores the use of the {\alpha}-transformation as an alternative to the commonly applied centered log-ratio (CLR) transformation for converting compositional data from the Aitchison simplex to unconstrained real space. The {\alpha}-transformation offers greater flexibility through the inclusion of the {\alpha} parameter, enabling better adaptation to the underlying data structure and handling of zero values, which are the limitations inherent to the CLR transformation. Using age-specific life table death counts for males and females in 31 selected European countries/regions from 1983 to 2018, the proposed method demonstrates comparable performance to the CLR transformation in most countries with improved forecast accuracy in some cases. These findings highlight the potential of the {\alpha}-transformation as a competitive alternative transformation technique for real-world mortality data within a non-functional CoDA framework.
Winter road maintenance is a critical priority for the Indiana Department of Transportation, which manages an extensive fleet across thousands of lane miles. The current manual tracking of snowplow workloads is inefficient and prone to errors. To address these challenges, we developed an in-browser web application that automates the creation and verification of work orders using a large-scale GPS dataset from telematics systems. The application processes millions of GPS data points from hundreds of vehicles over winter, significantly reducing manual labor and minimizing errors. Key features include geohashing for efficient road segment identification, detailed segment-level work records, and robust visualization of vehicle movements, even on repeated routes. Our proposed solution has the potential to enhance the accuracy and granularity of work records, support more effective resource allocation, ensure timely compensation for drivers, alleviate administrative burdens, and allow managers to focus on strategic planning and real-time challenges. The web application can be accessed at https://github.com/oats-center/arrtrack/
Large language models are increasingly being integrated into applications that shape the production and discovery of societal knowledge such as search, online education, and travel planning. As a result, language models will shape how people learn about, perceive and interact with global cultures making it important to consider whose knowledge systems and perspectives are represented in models. Recognizing this importance, increasingly work in Machine Learning and NLP has focused on evaluating gaps in global cultural representational distribution within outputs. However, more work is needed on developing benchmarks for cross-cultural impacts of language models that stem from a nuanced sociologically-aware conceptualization of cultural impact or harm. We join this line of work arguing for the need of metricizable evaluations of language technologies that interrogate and account for historical power inequities and differential impacts of representation on global cultures, particularly for cultures already under-represented in the digital corpora. We look at two concepts of erasure: omission: where cultures are not represented at all and simplification i.e. when cultural complexity is erased by presenting one-dimensional views of a rich culture. The former focuses on whether something is represented, and the latter on how it is represented. We focus our analysis on two task contexts with the potential to influence global cultural production. First, we probe representations that a language model produces about different places around the world when asked to describe these contexts. Second, we analyze the cultures represented in the travel recommendations produced by a set of language model applications. Our study shows ways in which the NLP community and application developers can begin to operationalize complex socio-cultural considerations into standard evaluations and benchmarks.
Designing structured visuals such as presentation slides is essential for communicative needs, necessitating both content creation and visual planning skills. In this work, we tackle the challenge of automated slide generation, where models produce slide presentations from natural language (NL) instructions. We first introduce the SlidesBench benchmark, the first benchmark for slide generation with 7k training and 585 testing examples derived from 310 slide decks across 10 domains. SlidesBench supports evaluations that are (i)reference-based to measure similarity to a target slide, and (ii)reference-free to measure the design quality of generated slides alone. We benchmark end-to-end image generation and program generation methods with a variety of models, and find that programmatic methods produce higher-quality slides in user-interactable formats. Built on the success of program generation, we create AutoPresent, an 8B Llama-based model trained on 7k pairs of instructions paired with code for slide generation, and achieve results comparable to the closed-source model GPT-4o. We further explore iterative design refinement where the model is tasked to self-refine its own output, and we found that this process improves the slide's quality. We hope that our work will provide a basis for future work on generating structured visuals.
This White Paper documents the discussion and consensus conclusions of the workshop "Software Infrastructure for Advanced Nuclear Physics Computing" (SANPC 24), which was held at Jefferson Lab on June 20-22, 2024. The workshop brought together members of the US Nuclear Physics community with data scientists and funding agency representatives to discuss the challenges and opportunities in advanced computing for Nuclear Physics in the coming decade. Opportunities for sustainable support and growth are identified within the context of existing and currently planned DOE and NSF programs.
Avionics systems of an Unmanned Aerial Vehicle (UAV) or drone are the critical electronic components found onboard that regulate, navigate, and control UAV travel while ensuring public safety. Contemporary UAV avionics work together to facilitate success of UAV missions by enabling stable communication, secure identification protocols, novel energy solutions, multi-sensor accurate perception and autonomous navigation, precise path planning, that guarantees collision avoidance, reliable trajectory control, and efficient data transfer within the UAV system. Moreover, special consideration must be given to electronic warfare threats prevention, detection, and mitigation, and the regulatory framework associated with UAV operations. This review presents the role and taxonomy of each UAV avionics system while covering shortcomings and benefits of available alternatives within each system. UAV communication systems, antennas, and location communication tracking are surveyed. Identification systems that respond to air-to-air or air-to-ground interrogating signals are presented. UAV classical and more innovative power sources are discussed. The rapid development of perception systems improves UAV autonomous navigation and control capabilities. The paper reviews common perception systems, navigation techniques, path planning approaches, obstacle avoidance methods, and tracking control. Modern electronic warfare uses advanced techniques and has to be counteracted by equally advanced methods to keep the public safe. Consequently, this work presents a detailed overview of common electronic warfare threats and state-of-the-art countermeasures and defensive aids. UAV safety occurrences are analyzed in the context of national regulatory framework and the certification process. Databus communication and standards for UAVs are reviewed as they enable efficient and fast real-time data transfer.
Modern configurable systems provide tremendous opportunities for engineering future intelligent software systems. A key difficulty thereof is how to effectively self-adapt the configuration of a running system such that its performance (e.g., runtime and throughput) can be optimized under time-varying workloads. This unfortunately remains unaddressed in existing approaches as they either overlook the available past knowledge or rely on static exploitation of past knowledge without reasoning the usefulness of information when planning for self-adaptation. In this paper, we tackle this challenging problem by proposing DLiSA, a framework that self-adapts configurable systems. DLiSA comes with two properties: firstly, it supports lifelong planning, and thereby the planning process runs continuously throughout the lifetime of the system, allowing dynamic exploitation of the accumulated knowledge for rapid adaptation. Secondly, the planning for a newly emerged workload is boosted via distilled knowledge seeding, in which the knowledge is dynamically purified such that only useful past configurations are seeded when necessary, mitigating misleading information. Extensive experiments suggest that the proposed DLiSA significantly outperforms state-of-the-art approaches, demonstrating a performance improvement of up to 229% and a resource acceleration of up to 2.22x on generating promising adaptation configurations. All data and sources can be found at our repository: https://github.com/ideas-labo/dlisa.
In this work, we use publicly available data from ATLAS collaboration collected at LHC run 2 at a center-of-mass energy of $\sqrt{s}=13$TeV with an integrated luminosity of $139 fb^{-1}$ to derive lower mass limits on the $Z^\prime$ gauge boson associated with the B-L gauge symmetry. Using dilepton data we find that $M_{Z^\prime} > 4$TeV ($6$TeV) for $g_{BL}=0.1$ ($g_{BL}=0.5$) in the absence of invisible decays. Once invisible decays are turned on these limits are substantially relaxed. Assuming an invisible branching ratio of $BR_{inv}=0.9$, the LHC bound is loosened up to $M_{Z^\prime}> 4.8$TeV for $g_{BL}=0.5$. This analysis confirms that the LHC now imposes stricter constraints than the longstanding bounds established by LEP. We also estimate the projected HL-LHC bounds that will operate with at $\sqrt{s}=14$TeV and a planned integrated luminosity of $\mathcal{L}=3 ab^{-1}$ that will probe $Z^\prime$ masses up to $7.5$TeV.
Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize geometry-consistent driving videos through neural rendering, but their dependence on costly object annotations limits their ability to generalize to in-the-wild driving scenarios. On the other hand, generative models can synthesize action-conditioned driving videos in a more generalizable way but often struggle with maintaining 3D visual consistency. In this paper, we present DreamDrive, a 4D spatial-temporal scene generation approach that combines the merits of generation and reconstruction, to synthesize generalizable 4D driving scenes and dynamic driving videos with 3D consistency. Specifically, we leverage the generative power of video diffusion models to synthesize a sequence of visual references and further elevate them to 4D with a novel hybrid Gaussian representation. Given a driving trajectory, we then render 3D-consistent driving videos via Gaussian splatting. The use of generative priors allows our method to produce high-quality 4D scenes from in-the-wild driving data, while neural rendering ensures 3D-consistent video generation from the 4D scenes. Extensive experiments on nuScenes and street view images demonstrate that DreamDrive can generate controllable and generalizable 4D driving scenes, synthesize novel views of driving videos with high fidelity and 3D consistency, decompose static and dynamic elements in a self-supervised manner, and enhance perception and planning tasks for autonomous driving.
This paper addresses the scarcity of large-scale datasets for accurate object-in-hand pose estimation, which is crucial for robotic in-hand manipulation within the ``Perception-Planning-Control" paradigm. Specifically, we introduce VinT-6D, the first extensive multi-modal dataset integrating vision, touch, and proprioception, to enhance robotic manipulation. VinT-6D comprises 2 million VinT-Sim and 0.1 million VinT-Real splits, collected via simulations in MuJoCo and Blender and a custom-designed real-world platform. This dataset is tailored for robotic hands, offering models with whole-hand tactile perception and high-quality, well-aligned data. To the best of our knowledge, the VinT-Real is the largest considering the collection difficulties in the real-world environment so that it can bridge the gap of simulation to real compared to the previous works. Built upon VinT-6D, we present a benchmark method that shows significant improvements in performance by fusing multi-modal information. The project is available at https://VinT-6D.github.io/.
In this paper, we present the main features of Dynamic Rapidly-exploring Generalized Bur Tree (DRGBT) algorithm, a sampling-based planner for dynamic environments. We provide a detailed time analysis and appropriate scheduling to facilitate a real-time operation. To this end, an extensive analysis is conducted to identify the time-critical routines and their dependence on the number of obstacles. Furthermore, information about the distance to obstacles is used to compute a structure called dynamic expanded bubble of free configuration space, which is then utilized to establish sufficient conditions for a guaranteed safe motion of the robot while satisfying all kinematic constraints. An extensive randomized simulation trial is conducted to compare the proposed algorithm to a competing state-of-the-art method. Finally, an experimental study on a real robot is carried out covering a variety of scenarios including those with human presence. The results show the effectiveness and feasibility of real-time execution of the proposed motion planning algorithm within a typical sensor-based arrangement, using cheap hardware and sequential architecture, without the necessity for GPUs or heavy parallelization.
It is not uncommon for a logic to be invented multiple times, hinting at its robustness. This trend is followed also by the expansion BD+ of Belnap-Dunn logic by Boolean negation. Ending up in the same logic, however, does not mean that the semantic interpretations are always the same as well. In particular, different interpretations can bring us to different logics, once the basic setting is moved from a classical one to an intuitionistic one. For BD+, two such paths seem to have been taken; one (BDi) by N. Kamide along the so-called American plan, and another (HYPE) by G. Moisil and H. Leitgeb along the so-called Australian plan. The aim of this paper is to better understand this divergence. This task is approached mainly by (i) formulating a semantics for first-order BD+ that provides an Australian view of the system; (ii) showing connections of the less explored (first-order) BDi with neighbouring systems, including an intermediate logic and variants of Nelson's logics.
In this paper, we prove the semantic incompleteness of the Hilbert-style system for the minimal normal term-modal logic with equality and non-rigid terms that was proposed in Liberman et al. (2020) "Dynamic Term-modal Logics for First-order Epistemic Planning." Term-modal logic is a family of first-order modal logics having term-modal operators indexed with terms in the first-order language. While some first-order formula is valid over the class of all frames in the Kripke semantics for the term-modal logic proposed there, it is not derivable in Liberman et al. (2020)'s Hilbert-style system. We show this fact by introducing a non-standard Kripke semantics which makes the meanings of constants and function symbols relative to the meanings of relation symbols combined with them.
High-energy collisions at the high-luminosity Large Hadron Collider (HL-LHC) will generate a vast flux of particles along the beam collision axis, a region not accessible by current LHC experiments. The study of multi-particle production in the far-forward region is especially important for astroparticle physics. High-energy cosmic rays create extensive air showers (EAS) in the atmosphere, driven by hadron-ion collisions in the non-perturbative QCD regime. Therefore, understanding high-energy hadronic interactions in the forward region is crucial for interpreting EAS data and estimating backgrounds for searches of astrophysical neutrinos, among other applications. The Forward Physics Facility (FPF) is a proposal to construct a new underground cavern at the HL-LHC, hosting various far-forward experiments designed to detect particles outside the current LHC acceptance. We will outline the current plans for the FPF and highlight its synergies with astroparticle physics. Specifically, we will discuss how FPF measurements will enhance the modeling of high-energy interactions in the atmosphere, helping to reduce the associated uncertainties in multi-messenger astrophysics.
The number of parameters in large-scale language models based on transformers is gradually increasing, and the scale of computing clusters is also growing. The technology of quickly mobilizing large amounts of computing resources for parallel computing is becoming increasingly important. In this paper, we propose an automatic parallel algorithm that automatically plans the parallel strategy with maximum throughput based on model and hardware information. By decoupling the training time into computation, communication, and overlap, we established a training duration simulation model. Based on this simulation model, we prune the parallel solution space to shorten the search time required. The multi-node experiment results show that the algorithm can estimate the parallel training duration in real time with an average accuracy of 96%. In our test, the recommendation strategy provided by the algorithm is always globally optimal.
Accurate water consumption forecasting is a crucial tool for water utilities and policymakers, as it helps ensure a reliable supply, optimize operations, and support infrastructure planning. Urban Water Distribution Networks (WDNs) are divided into District Metered Areas (DMAs), where water flow is monitored to efficiently manage resources. This work focuses on short-term forecasting of DMA consumption using deep learning and aims to address two key challenging issues. First, forecasting based solely on a DMA's historical data may lack broader context and provide limited insights. Second, DMAs may experience sensor malfunctions providing incorrect data, or some DMAs may not be monitored at all due to computational costs, complicating accurate forecasting. We propose a novel method that first identifies DMAs with correlated consumption patterns and then uses these patterns, along with the DMA's local data, as input to a deep learning model for forecasting. In a real-world study with data from five DMAs, we show that: i) the deep learning model outperforms a classical statistical model; ii) accurate forecasting can be carried out using only correlated DMAs' consumption patterns; and iii) even when a DMA's local data is available, including correlated DMAs' data improves accuracy.