Large Multimodal Models (LMMs) have recently gained prominence in autonomous driving research, showcasing promising capabilities across various emerging benchmarks. LMMs specifically designed for this domain have demonstrated effective perception, planning, and prediction skills. However, many of these methods underutilize 3D spatial and temporal elements, relying mainly on image data. As a result, their effectiveness in dynamic driving environments is limited. We propose to integrate tracking information as an additional input to recover 3D spatial and temporal details that are not effectively captured in the images. We introduce a novel approach for embedding this tracking information into LMMs to enhance their spatiotemporal understanding of driving scenarios. By incorporating 3D tracking data through a track encoder, we enrich visual queries with crucial spatial and temporal cues while avoiding the computational overhead associated with processing lengthy video sequences or extensive 3D inputs. Moreover, we employ a self-supervised approach to pretrain the tracking encoder to provide LMMs with additional contextual information, significantly improving their performance in perception, planning, and prediction tasks for autonomous driving. Experimental results demonstrate the effectiveness of our approach, with a gain of 9.5% in accuracy, an increase of 7.04 points in the ChatGPT score, and 9.4% increase in the overall score over baseline models on DriveLM-nuScenes benchmark, along with a 3.7% final score improvement on DriveLM-CARLA. Our code is available at https://github.com/mbzuai-oryx/TrackingMeetsLMM
Escape rooms present a unique cognitive challenge that demands exploration-driven planning: players should actively search their environment, continuously update their knowledge based on new discoveries, and connect disparate clues to determine which elements are relevant to their objectives. Motivated by this, we introduce VisEscape, a benchmark of 20 virtual escape rooms specifically designed to evaluate AI models under these challenging conditions, where success depends not only on solving isolated puzzles but also on iteratively constructing and refining spatial-temporal knowledge of a dynamically changing environment. On VisEscape, we observed that even state-of-the-art multimodal models generally fail to escape the rooms, showing considerable variation in their levels of progress and trajectories. To address this issue, we propose VisEscaper, which effectively integrates Memory, Feedback, and ReAct modules, demonstrating significant improvements by performing 3.7 times more effectively and 5.0 times more efficiently on average.
Recent video diffusion models have enhanced video editing, but it remains challenging to handle instructional editing and diverse tasks (e.g., adding, removing, changing) within a unified framework. In this paper, we introduce VEGGIE, a Video Editor with Grounded Generation from Instructions, a simple end-to-end framework that unifies video concept editing, grounding, and reasoning based on diverse user instructions. Specifically, given a video and text query, VEGGIE first utilizes an MLLM to interpret user intentions in instructions and ground them to the video contexts, generating frame-specific grounded task queries for pixel-space responses. A diffusion model then renders these plans and generates edited videos that align with user intent. To support diverse tasks and complex instructions, we employ a curriculum learning strategy: first aligning the MLLM and video diffusion model with large-scale instructional image editing data, followed by end-to-end fine-tuning on high-quality multitask video data. Additionally, we introduce a novel data synthesis pipeline to generate paired instructional video editing data for model training. It transforms static image data into diverse, high-quality video editing samples by leveraging Image-to-Video models to inject dynamics. VEGGIE shows strong performance in instructional video editing with different editing skills, outperforming the best instructional baseline as a versatile model, while other models struggle with multi-tasking. VEGGIE also excels in video object grounding and reasoning segmentation, where other baselines fail. We further reveal how the multiple tasks help each other and highlight promising applications like zero-shot multimodal instructional and in-context video editing.
Efficient material logistics play a critical role in controlling costs and schedules in the construction industry. However, manual material handling remains prone to inefficiencies, delays, and safety risks. Autonomous forklifts offer a promising solution to streamline on-site logistics, reducing reliance on human operators and mitigating labor shortages. This paper presents the development and evaluation of the Autonomous Dynamic All-terrain Pallet Transporter (ADAPT), a fully autonomous off-road forklift designed for construction environments. Unlike structured warehouse settings, construction sites pose significant challenges, including dynamic obstacles, unstructured terrain, and varying weather conditions. To address these challenges, our system integrates AI-driven perception techniques with traditional approaches for decision making, planning, and control, enabling reliable operation in complex environments. We validate the system through extensive real-world testing, comparing its long-term performance against an experienced human operator across various weather conditions. We also provide a comprehensive analysis of challenges and key lessons learned, contributing to the advancement of autonomous heavy machinery. Our findings demonstrate that autonomous outdoor forklifts can operate near human-level performance, offering a viable path toward safer and more efficient construction logistics.
This paper considers risk-sensitive model predictive control for stochastic systems with a decision-dependent distribution. This class of systems is commonly found in human-robot interaction scenarios. We derive computationally tractable convex upper bounds to both the objective function, and to frequently used penalty terms for collision avoidance, allowing us to efficiently solve the generally nonconvex optimal control problem as a sequence of convex problems. Simulations of a robot navigating a corridor demonstrate the effectiveness and the computational advantage of the proposed approach.
In 2024, the UK Government made two striking announcements on its plans to decarbonise the energy system; it pledged GBP22 billion to establish carbon capture and storage hubs on Teesside and Merseyside and released the Clean Power 2030 Action Plan. This paper questions the validity of both plans, arguing that they do not take adequate account of the consequences of the highly variable nature of wind and solar generations. Using dynamic models of future UK electricity systems which are designed to take account of these variabilities, it is shown that the Clean Power 2030 Action Plan overestimates the ability of wind and solar generations to decarbonise the electricity system as they increase in size relative to the demand of the electricity system. More importantly, the dynamic models show that most of the achievable decarbonization is the result of increasing wind generation from the current level of around 10 GW to around 20 GW. Increasing wind generation to only 20 GW, rather than to 30 GW as proposed in the Action Plan, should halve the proposed cost, a saving of perhaps GBP 120 billion, with little disbenefit in terms of reduced decarbonization. Furthermore, the dynamic modelling shows that UK gas storage capacity of 7.5 winter days looks hopeless inadequate in comparison with the storage capacities deemed necessary by its continental neighbors. Concern is expressed that a consequence of the Climate Change Act of 2008 requiring the UK to meet arbitrary decarbonization targets is leading government advisors to propose several unproven and therefore highly risky technological solutions.
Deep learning-based segmentation of genito-pelvic structures in MRI and CT is crucial for applications such as radiation therapy, surgical planning, and disease diagnosis. However, existing segmentation models often struggle with generalizability across imaging modalities, and anatomical variations. In this work, we propose RoMedFormer, a rotary-embedding transformer-based foundation model designed for 3D female genito-pelvic structure segmentation in both MRI and CT. RoMedFormer leverages self-supervised learning and rotary positional embeddings to enhance spatial feature representation and capture long-range dependencies in 3D medical data. We pre-train our model using a diverse dataset of 3D MRI and CT scans and fine-tune it for downstream segmentation tasks. Experimental results demonstrate that RoMedFormer achieves superior performance segmenting genito-pelvic organs. Our findings highlight the potential of transformer-based architectures in medical image segmentation and pave the way for more transferable segmentation frameworks.
Trajectory prediction facilitates effective planning and decision-making, while constrained trajectory prediction integrates regulation into prediction. Recent advances in constrained trajectory prediction focus on structured constraints by constructing optimization objectives. However, handling unstructured constraints is challenging due to the lack of differentiable formal definitions. To address this, we propose a novel method for constrained trajectory prediction using a conditional generative paradigm, named Controllable Trajectory Diffusion (CTD). The key idea is that any trajectory corresponds to a degree of conformity to a constraint. By quantifying this degree and treating it as a condition, a model can implicitly learn to predict trajectories under unstructured constraints. CTD employs a pre-trained scoring model to predict the degree of conformity (i.e., a score), and uses this score as a condition for a conditional diffusion model to generate trajectories. Experimental results demonstrate that CTD achieves high accuracy on the ETH/UCY and SDD benchmarks. Qualitative analysis confirms that CTD ensures adherence to unstructured constraints and can predict trajectories that satisfy combinatorial constraints.
Agile trajectory planning can improve the efficiency of multi-rotor Uncrewed Aerial Vehicles (UAVs) in scenarios with combined task-oriented and kinematic trajectory planning, such as monitoring spatio-temporal phenomena or intercepting dynamic targets. Agile planning using existing non-linear model predictive control methods is limited by the number of planning steps as it becomes increasingly computationally demanding. That reduces the prediction horizon length, leading to a decrease in solution quality. Besides, the fixed time-step length limits the utilization of the available UAV dynamics in the target neighborhood. In this paper, we propose to address these limitations by introducing variable time steps and coupling them with the prediction horizon length. A simplified point-mass motion primitive is used to leverage the differential flatness of quadrotor dynamics and the generation of feasible trajectories in the flat output space. Based on the presented evaluation results and experimentally validated deployment, the proposed method increases the solution quality by enabling planning for long flight segments but allowing tightly sampled maneuvering.
End-to-end autonomous driving unifies tasks in a differentiable framework, enabling planning-oriented optimization and attracting growing attention. Current methods aggregate historical information either through dense historical bird's-eye-view (BEV) features or by querying a sparse memory bank, following paradigms inherited from detection. However, we argue that these paradigms either omit historical information in motion planning or fail to align with its multi-step nature, which requires predicting or planning multiple future time steps. In line with the philosophy of future is a continuation of past, we propose BridgeAD, which reformulates motion and planning queries as multi-step queries to differentiate the queries for each future time step. This design enables the effective use of historical prediction and planning by applying them to the appropriate parts of the end-to-end system based on the time steps, which improves both perception and motion planning. Specifically, historical queries for the current frame are combined with perception, while queries for future frames are integrated with motion planning. In this way, we bridge the gap between past and future by aggregating historical insights at every time step, enhancing the overall coherence and accuracy of the end-to-end autonomous driving pipeline. Extensive experiments on the nuScenes dataset in both open-loop and closed-loop settings demonstrate that BridgeAD achieves state-of-the-art performance.
Extensive research has confirmed the positive relationship between exposure to natural environments and human cognitive, behavioral, physical, and mental health. However, only some have easy access to nature. With electronic information and simulation technology advancements, digital nature experiences are widely used across various devices and scenarios. It is essential to explore how to effectively select and utilize natural elements to guide the design of digital nature scenes. This paper examines critical elements in immersive virtual nature (IVN) and their impact on user perception. Through online surveys and design experiments, we identified specific natural elements that promote relaxation and proposed design strategies for virtual environments. We developed several immersive virtual nature scenes for further validation. Finally, we outline our future experimental plans and research directions in digital nature. Our research aims to provide HCI designers insights into creating restorative, immersive virtual scenes.
Autonomous large-scale machine operations require fast, efficient, and collision-free motion planning while addressing unique challenges such as hydraulic actuation limits and underactuated joint dynamics. This paper presents a novel two-step motion planning framework designed for an underactuated forestry crane. The first step employs GPU-accelerated stochastic optimization to rapidly compute a globally shortest collision-free path. The second step refines this path into a dynamically feasible trajectory using a trajectory optimizer that ensures compliance with system dynamics and actuation constraints. The proposed approach is benchmarked against conventional techniques, including RRT-based methods and purely optimization-based approaches. Simulation results demonstrate substantial improvements in computation speed and motion feasibility, making this method highly suitable for complex crane systems.
The increasing reliance on web interfaces presents many challenges for visually impaired users, showcasing the need for more advanced assistive technologies. This paper introduces WebNav, a voice-controlled web navigation agent that leverages a ReAct-inspired architecture and generative AI to provide this framework. WebNav comprises of a hierarchical structure: a Digital Navigation Module (DIGNAV) for high-level strategic planning, an Assistant Module for translating abstract commands into executable actions, and an Inference Module for low-level interaction. A key component is a dynamic labeling engine, implemented as a browser extension, that generates real-time labels for interactive elements, creating mapping between voice commands and Document Object Model (DOM) components. Preliminary evaluations show that WebNav outperforms traditional screen readers in response time and task completion accuracy for the visually impaired. Future work will focus on extensive user evaluations, benchmark development, and refining the agent's adaptive capabilities for real-world deployment.
Reinforcement learning control algorithms face significant challenges due to out-of-distribution and inefficient exploration problems. While model-based reinforcement learning enhances the agent's reasoning and planning capabilities by constructing virtual environments, training such virtual environments can be very complex. In order to build an efficient inference model and enhance the representativeness of learning data, we propose the Counterfactual Experience Augmentation (CEA) algorithm. CEA leverages variational autoencoders to model the dynamic patterns of state transitions and introduces randomness to model non-stationarity. This approach focuses on expanding the learning data in the experience pool through counterfactual inference and performs exceptionally well in environments that follow the bisimulation assumption. Environments with bisimulation properties are usually represented by discrete observation and action spaces, we propose a sampling method based on maximum kernel density estimation entropy to extend CEA to various environments. By providing reward signals for counterfactual state transitions based on real information, CEA constructs a complete counterfactual experience to alleviate the out-of-distribution problem of the learning data, and outperforms general SOTA algorithms in environments with difference properties. Finally, we discuss the similarities, differences and properties of generated counterfactual experiences and real experiences. The code is available at https://github.com/Aegis1863/CEA.
Accurate segmentation is essential for effective treatment planning and disease monitoring. Existing medical image segmentation methods predominantly rely on uni-modal visual inputs, such as images or videos, requiring labor-intensive manual annotations. Additionally, medical imaging techniques capture multiple intertwined organs within a single scan, further complicating segmentation accuracy. To address these challenges, MedSAM, a large-scale medical segmentation model based on the Segment Anything Model (SAM), was developed to enhance segmentation accuracy by integrating image features with user-provided prompts. While MedSAM has demonstrated strong performance across various medical segmentation tasks, it primarily relies on geometric prompts (e.g., points and bounding boxes) and lacks support for text-based prompts, which could help specify subtle or ambiguous anatomical structures. To overcome these limitations, we propose the Organ-aware Multi-scale Text-guided Medical Image Segmentation Model (OMT-SAM) for multi-organ segmentation. Our approach introduces CLIP encoders as a novel image-text prompt encoder, operating with the geometric prompt encoder to provide informative contextual guidance. We pair descriptive textual prompts with corresponding images, processing them through pre-trained CLIP encoders and a cross-attention mechanism to generate fused image-text embeddings. Additionally, we extract multi-scale visual features from MedSAM, capturing fine-grained anatomical details at different levels of granularity. We evaluate OMT-SAM on the FLARE 2021 dataset, benchmarking its performance against existing segmentation methods. Empirical results demonstrate that OMT-SAM achieves a mean Dice Similarity Coefficient of 0.937, outperforming MedSAM (0.893) and other segmentation models, highlighting its superior capability in handling complex medical image segmentation tasks.
The engineering community currently encounters significant challenges in the systematic development and validation of autonomy algorithms for off-road ground vehicles. These challenges are posed by unusually high test parameters and algorithmic variants. In order to address these pain points, this work presents an optimized digital engineering framework that tightly couples digital twin simulations with model-based systems engineering (MBSE) and model-based design (MBD) workflows. The efficacy of the proposed framework is demonstrated through an end-to-end case study of an autonomous light tactical vehicle (LTV) performing visual servoing to drive along a dirt road and reacting to any obstacles or environmental changes. The presented methodology allows for traceable requirements engineering, efficient variant management, granular parameter sweep setup, systematic test-case definition, and automated execution of the simulations. The candidate off-road autonomy algorithm is evaluated for satisfying requirements against a battery of 128 test cases, which is procedurally generated based on the test parameters (times of the day and weather conditions) and algorithmic variants (perception, planning, and control sub-systems). Finally, the test results and key performance indicators are logged, and the test report is generated automatically. This then allows for manual as well as automated data analysis with traceability and tractability across the digital thread.
How many simulations do we need to train machine learning methods to extract information available from summary statistics of the cosmological density field? Neural methods have shown the potential to extract non-linear information available from cosmological data. Success depends critically on having sufficient simulations for training the networks and appropriate network architectures. In the first detailed convergence study of neural network training for cosmological inference, we show that currently available simulation suites, such as the Quijote Latin Hypercube(LH) with 2000 simulations, do not provide sufficient training data for a generic neural network to reach the optimal regime, even for the dark matter power spectrum, and in an idealized case. We discover an empirical neural scaling law that predicts how much information a neural network can extract from a highly informative summary statistic, the dark matter power spectrum, as a function of the number of simulations used to train the network, for a wide range of architectures and hyperparameters. We combine this result with the Cramer-Rao information bound to forecast the number of training simulations needed for near-optimal information extraction. To verify our method we created the largest publicly released simulation data set in cosmology, the Big Sobol Sequence(BSQ), consisting of 32,768 $\Lambda$CDM n-body simulations uniformly covering the $\Lambda$CDM parameter space. Our method enables efficient planning of simulation campaigns for machine learning applications in cosmology, while the BSQ dataset provides an unprecedented resource for studying the convergence behavior of neural networks in cosmological parameter inference. Our results suggest that new large simulation suites or new training approaches will be necessary to achieve information-optimal parameter inference from non-linear simulations.
Photo-realistic rendering and novel view synthesis play a crucial role in human-computer interaction tasks, from gaming to path planning. Neural Radiance Fields (NeRFs) model scenes as continuous volumetric functions and achieve remarkable rendering quality. However, NeRFs often struggle in large, low-textured areas, producing cloudy artifacts known as ''floaters'' that reduce scene realism, especially in indoor environments with featureless architectural surfaces like walls, ceilings, and floors. To overcome this limitation, prior work has integrated geometric constraints into the NeRF pipeline, typically leveraging depth information derived from Structure from Motion or Multi-View Stereo. Yet, conventional RGB-feature correspondence methods face challenges in accurately estimating depth in textureless regions, leading to unreliable constraints. This challenge is further complicated in 360-degree ''inside-out'' views, where sparse visual overlap between adjacent images further hinders depth estimation. In order to address these issues, we propose an efficient and robust method for computing dense depth priors, specifically tailored for large low-textured architectural surfaces in indoor environments. We introduce a novel depth loss function to enhance rendering quality in these challenging, low-feature regions, while complementary depth-patch regularization further refines depth consistency across other areas. Experiments with Instant-NGP on two synthetic 360-degree indoor scenes demonstrate improved visual fidelity with our method compared to standard photometric loss and Mean Squared Error depth supervision.
Mobile manipulation is the fundamental challenge for robotics to assist humans with diverse tasks and environments in everyday life. However, conventional mobile manipulation approaches often struggle to generalize across different tasks and environments because of the lack of large-scale training. In contrast, recent advances in vision-language-action (VLA) models have shown impressive generalization capabilities, but these foundation models are developed for fixed-base manipulation tasks. Therefore, we propose an efficient policy adaptation framework named MoManipVLA to transfer pre-trained VLA models of fix-base manipulation to mobile manipulation, so that high generalization ability across tasks and environments can be achieved in mobile manipulation policy. Specifically, we utilize pre-trained VLA models to generate waypoints of the end-effector with high generalization ability. We design motion planning objectives for the mobile base and the robot arm, which aim at maximizing the physical feasibility of the trajectory. Finally, we present an efficient bi-level objective optimization framework for trajectory generation, where the upper-level optimization predicts waypoints for base movement to enhance the manipulator policy space, and the lower-level optimization selects the optimal end-effector trajectory to complete the manipulation task. In this way, MoManipVLA can adjust the position of the robot base in a zero-shot manner, thus making the waypoints predicted from the fixed-base VLA models feasible. Extensive experimental results on OVMM and the real world demonstrate that MoManipVLA achieves a 4.2% higher success rate than the state-of-the-art mobile manipulation, and only requires 50 training cost for real world deployment due to the strong generalization ability in the pre-trained VLA models.
Remote sensing novel view synthesis (NVS) offers significant potential for 3D interpretation of remote sensing scenes, with important applications in urban planning and environmental monitoring. However, remote sensing scenes frequently lack sufficient multi-view images due to acquisition constraints. While existing NVS methods tend to overfit when processing limited input views, advanced few-shot NVS methods are computationally intensive and perform sub-optimally in remote sensing scenes. This paper presents TriDF, an efficient hybrid 3D representation for fast remote sensing NVS from as few as 3 input views. Our approach decouples color and volume density information, modeling them independently to reduce the computational burden on implicit radiance fields and accelerate reconstruction. We explore the potential of the triplane representation in few-shot NVS tasks by mapping high-frequency color information onto this compact structure, and the direct optimization of feature planes significantly speeds up convergence. Volume density is modeled as continuous density fields, incorporating reference features from neighboring views through image-based rendering to compensate for limited input data. Additionally, we introduce depth-guided optimization based on point clouds, which effectively mitigates the overfitting problem in few-shot NVS. Comprehensive experiments across multiple remote sensing scenes demonstrate that our hybrid representation achieves a 30x speed increase compared to NeRF-based methods, while simultaneously improving rendering quality metrics over advanced few-shot methods (7.4% increase in PSNR, 12.2% in SSIM, and 18.7% in LPIPS). The code is publicly available at https://github.com/kanehub/TriDF
This research examines global issues concerning the development of mountain areas considered as territories difficult to manage. The case study area is part of the sub-region of High Alpine Steppes belonging to the Tunisian Ridge and reaching Tebessa Mountains in Algeria. The central question of this article is based on the analysis of the links between the representations produced by mountain landscapes and the construction of a border line that must meet the requirements of sustainable development. Eco-landscape determinants and the role of public authorities and population must be better defined so that the products of this space provide a better quality of life endowed with the alternatives of local and sustainable development. Our hypothesis is that the mountain areas of West Central Tunisia still have a real ecological potential little disturbed by a chimerical development, and can constitute assets for the territorial development of the area. The approach adopted by this work is a scoping audit based on the floristic richness and the monitoring of its spatiotemporal dynamics. The results of this research allowed us to draw rich conclusions; the phyto-ecology approach has shown a relative floristic richness that remains highly dependent on the climatic cycles and intervention of human action; this area must be considered as a priority of the public planning policies aimed at improving the quality of lives in these fragile zones in the context of sustainable development.
Multi-agent Path Finding (MAPF) is the problem of planning collision-free movements of agents such that they get from where they are to where they need to be. Commonly, agents are located on a graph and can traverse edges. This problem has many variations and has been studied for decades. Two such variations are the continuous-time and the lifelong MAPF problems. In the continuous-time MAPF problem, edges can have non-unit lengths and agents can traverse them at any real-valued time. Additionally, agent volumes are often included. In the lifelong MAPF problem, agents must attend to a continuous stream of incoming tasks. Much work has been devoted to designing solution methods within these two areas. However, to our knowledge, the combined problem of continuous-time lifelong MAPF has yet to be addressed. This work addresses continuous-time lifelong MAPF with agent volumes by presenting the fast and sub-optimal Continuous-time Prioritized Lifelong Planner (CPLP). CPLP continuously re-prioritizes tasks, assigns agents to them, and computes agent plans using a combination of two path planners; one based on CCBS and the other on SIPP. Experimental results with up to $400$ agents on graphs with $4000$ vertices demonstrate average computation times below $20$ ms per call. In online settings where available time to compute plans is limited, CPLP ensures collision-free movement even when failing to meet these time limits. Therefore, the robustness of CPLP highlights its potential for real-world applications.
The acquisition of large-scale and diverse demonstration data are essential for improving robotic imitation learning generalization. However, generating such data for complex manipulations is challenging in real-world settings. We introduce HybridGen, an automated framework that integrates Vision-Language Model (VLM) and hybrid planning. HybridGen uses a two-stage pipeline: first, VLM to parse expert demonstrations, decomposing tasks into expert-dependent (object-centric pose transformations for precise control) and plannable segments (synthesizing diverse trajectories via path planning); second, pose transformations substantially expand the first-stage data. Crucially, HybridGen generates a large volume of training data without requiring specific data formats, making it broadly applicable to a wide range of imitation learning algorithms, a characteristic which we also demonstrate empirically across multiple algorithms. Evaluations across seven tasks and their variants demonstrate that agents trained with HybridGen achieve substantial performance and generalization gains, averaging a 5% improvement over state-of-the-art methods. Notably, in the most challenging task variants, HybridGen achieves significant improvement, reaching a 59.7% average success rate, significantly outperforming Mimicgen's 49.5%. These results demonstrating its effectiveness and practicality.
Simulating the complex interactions between soft tissues and rigid anatomy is critical for applications in surgical training, planning, and robotic-assisted interventions. Traditional Finite Element Method (FEM)-based simulations, while accurate, are computationally expensive and impractical for real-time scenarios. Learning-based approaches have shown promise in accelerating predictions but have fallen short in modeling soft-rigid interactions effectively. We introduce MIXPINN, a physics-informed Graph Neural Network (GNN) framework for mixed-material simulations, explicitly capturing soft-rigid interactions using graph-based augmentations. Our approach integrates Virtual Nodes (VNs) and Virtual Edges (VEs) to enhance rigid body constraint satisfaction while preserving computational efficiency. By leveraging a graph-based representation of biomechanical structures, MIXPINN learns high-fidelity deformations from FEM-generated data and achieves real-time inference with sub-millimeter accuracy. We validate our method in a realistic clinical scenario, demonstrating superior performance compared to baseline GNN models and traditional FEM methods. Our results show that MIXPINN reduces computational cost by an order of magnitude while maintaining high physical accuracy, making it a viable solution for real-time surgical simulation and robotic-assisted procedures.
Electrifying demand-responsive transport systems need to plan the charging infrastructure carefully, considering the trade-offs of charging efficiency and charging infrastructure costs. Earlier studies assume a fully electrified fleet and overlook the planning issue in the transition period. This study addresses the joint fleet size and charging infrastructure planning for a demand-responsive feeder service under stochastic demand, given a user-defined targeted CO2 emission reduction policy. We propose a bi-level optimization model where the upper-level determines charging station configuration given stochastic demand patterns, whereas the lower-level solves a mixed fleet dial-a-ride routing problem under the CO2 emission and capacitated charging station constraints. An efficient deterministic annealing metaheuristic is proposed to solve the CO2-constrained mixed fleet routing problem. The performance of the algorithm is validated by a series of numerical test instances with up to 500 requests. We apply the model for a real-world case study in Bettembourg, Luxembourg, with different demand and customised CO2 reduction targets. The results show that the proposed method provides a flexible tool for joint charging infrastructure and fleet size planning under different levels of demand and CO2 emission reduction targets.
The use of unmanned aerial vehicles (UAVs) for smart agriculture is becoming increasingly popular. This is evidenced by recent scientific works, as well as the various competitions organised on this topic. Therefore, in this work we present a system for automatic fruit counting using UAVs. To detect them, our solution uses a vision algorithm that processes streams from an RGB camera and a depth sensor using classical image operations. Our system also allows the planning and execution of flight trajectories, taking into account the minimisation of flight time and distance covered. We tested the proposed solution in simulation and obtained an average score of 87.27/100 points from a total of 500 missions. We also submitted it to the UAV Competition organised as part of the ICUAS 2024 conference, where we achieved an average score of 84.83/100 points, placing 6th in a field of 23 teams and advancing to the finals.
Scientific workflows process extensive data sets over clusters of independent nodes, which requires a complex stack of infrastructure components, especially a resource manager (RM) for task-to-node assignment, a distributed file system (DFS) for data exchange between tasks, and a workflow engine to control task dependencies. To enable a decoupled development and installation of these components, current architectures place intermediate data files during workflow execution independently of the future workload. In data-intensive applications, this separation results in suboptimal schedules, as tasks are often assigned to nodes lacking input data, causing network traffic and bottlenecks. This paper presents WOW, a new scheduling approach for dynamic scientific workflow systems that steers both data movement and task scheduling to reduce network congestion and overall runtime. For this, WOW creates speculative copies of intermediate files to prepare the execution of subsequently scheduled tasks. WOW supports modern workflow systems that gain flexibility through the dynamic construction of execution plans. We prototypically implemented WOW for the popular workflow engine Nextflow using Kubernetes as a resource manager. In experiments with 16 synthetic and real workflows, WOW reduced makespan in all cases, with improvement of up to 94.5% for workflow patterns and up to 53.2% for real workflows, at a moderate increase of temporary storage space. It also has favorable effects on CPU allocation and scales well with increasing cluster size.
Species Distribution Models (SDMs) play a vital role in biodiversity research, conservation planning, and ecological niche modeling by predicting species distributions based on environmental conditions. The selection of predictors is crucial, strongly impacting both model accuracy and how well the predictions reflect ecological patterns. To ensure meaningful insights, input variables must be carefully chosen to match the study objectives and the ecological requirements of the target species. However, existing SDMs, including both traditional and deep learning-based approaches, often lack key capabilities for variable selection: (i) flexibility to choose relevant predictors at inference without retraining; (ii) robustness to handle missing predictor values without compromising accuracy; and (iii) explainability to interpret and accurately quantify each predictor's contribution. To overcome these limitations, we introduce MaskSDM, a novel deep learning-based SDM that enables flexible predictor selection by employing a masked training strategy. This approach allows the model to make predictions with arbitrary subsets of input variables while remaining robust to missing data. It also provides a clearer understanding of how adding or removing a given predictor affects model performance and predictions. Additionally, MaskSDM leverages Shapley values for precise predictor contribution assessments, improving upon traditional approximations. We evaluate MaskSDM on the global sPlotOpen dataset, modeling the distributions of 12,738 plant species. Our results show that MaskSDM outperforms imputation-based methods and approximates models trained on specific subsets of variables. These findings underscore MaskSDM's potential to increase the applicability and adoption of SDMs, laying the groundwork for developing foundation models in SDMs that can be readily applied to diverse ecological applications.
We study Multimodal Large Language Models (MLLMs) with in-context learning for food preparation task planning. In this context, we identify two key challenges: cross-modal distraction and geometric feasibility. Cross-modal distraction occurs when the inclusion of visual input degrades the reasoning performance of a MLLM. Geometric feasibility refers to the ability of MLLMs to ensure that the selected skills are physically executable in the environment. To address these issues, we adapt Chain of Thought (CoT) with Self-Consistency to mitigate reasoning loss from cross-modal distractions and use affordance predictor as skill preconditions to guide MLLM on geometric feasibility. We construct a dataset to evaluate the ability of MLLMs on quantity estimation, reachability analysis, relative positioning and collision avoidance. We conducted a detailed evaluation to identify issues among different baselines and analyze the reasons for improvement, providing insights into each approach. Our method reaches a success rate of 76.7% on the entire dataset, showing a substantial improvement over the CoT baseline at 36.7%.
Directly generating planning results from raw sensors has become increasingly prevalent due to its adaptability and robustness in complex scenarios. Scene representation, as a key module in the pipeline, has traditionally relied on conventional perception, which focus on the global scene. However, in driving scenarios, human drivers typically focus only on regions that directly impact driving, which often coincide with those required for end-to-end autonomous driving. In this paper, a novel end-to-end autonomous driving method called InsightDrive is proposed, which organizes perception by language-guided scene representation. We introduce an instance-centric scene tokenizer that transforms the surrounding environment into map- and object-aware instance tokens. Scene attention language descriptions, which highlight key regions and obstacles affecting the ego vehicle's movement, are generated by a vision-language model that leverages the cognitive reasoning capabilities of foundation models. We then align scene descriptions with visual features using the vision-language model, guiding visual attention through these descriptions to give effectively scene representation. Furthermore, we employ self-attention and cross-attention mechanisms to model the ego-agents and ego-map relationships to comprehensively build the topological relationships of the scene. Finally, based on scene understanding, we jointly perform motion prediction and planning. Extensive experiments on the widely used nuScenes benchmark demonstrate that the proposed InsightDrive achieves state-of-the-art performance in end-to-end autonomous driving. The code is available at https://github.com/songruiqi/InsightDrive