Foundation models can provide robust high-level reasoning on appropriate safety interventions in hazardous scenarios beyond a robot's training data, i.e. out-of-distribution (OOD) failures. However, due to the high inference latency of Large Vision and Language Models, current methods rely on manually defined intervention policies to enact fallbacks, thereby lacking the ability to plan generalizable, semantically safe motions. To overcome these challenges we present FORTRESS, a framework that generates and reasons about semantically safe fallback strategies in real time to prevent OOD failures. At a low frequency in nominal operations, FORTRESS uses multi-modal reasoners to identify goals and anticipate failure modes. When a runtime monitor triggers a fallback response, FORTRESS rapidly synthesizes plans to fallback goals while inferring and avoiding semantically unsafe regions in real time. By bridging open-world, multi-modal reasoning with dynamics-aware planning, we eliminate the need for hard-coded fallbacks and human safety interventions. FORTRESS outperforms on-the-fly prompting of slow reasoning models in safety classification accuracy on synthetic benchmarks and real-world ANYmal robot data, and further improves system safety and planning success in simulation and on quadrotor hardware for urban navigation.
While large language models demonstrate impressive performance on static benchmarks, the true potential of large language models as self-learning and reasoning agents in dynamic environments remains unclear. This study systematically evaluates the efficacy of self-reflection, heuristic mutation, and planning as prompting techniques to test the adaptive capabilities of agents. We conduct experiments with various open-source language models in dynamic environments and find that larger models generally outperform smaller ones, but that strategic prompting can close this performance gap. Second, a too-long prompt can negatively impact smaller models on basic reactive tasks, while larger models show more robust behaviour. Third, advanced prompting techniques primarily benefit smaller models on complex games, but offer less improvement for already high-performing large language models. Yet, we find that advanced reasoning methods yield highly variable outcomes: while capable of significantly improving performance when reasoning and decision-making align, they also introduce instability and can lead to big performance drops. Compared to human performance, our findings reveal little evidence of true emergent reasoning. Instead, large language model performance exhibits persistent limitations in crucial areas such as planning, reasoning, and spatial coordination, suggesting that current-generation large language models still suffer fundamental shortcomings that may not be fully overcome through self-reflective prompting alone. Reasoning is a multi-faceted task, and while reasoning methods like Chain of thought improves multi-step reasoning on math word problems, our findings using dynamic benchmarks highlight important shortcomings in general reasoning capabilities, indicating a need to move beyond static benchmarks to capture the complexity of reasoning.
Finding high-quality solutions quickly is an important objective in motion planning. This is especially true for high-degree-of-freedom robots. Satisficing planners have traditionally found feasible solutions quickly but provide no guarantees on their optimality, while almost-surely asymptotically optimal (a.s.a.o.) planners have probabilistic guarantees on their convergence towards an optimal solution but are more computationally expensive. This paper uses the AO-x meta-algorithm to extend the satisficing RRT-Connect planner to optimal planning. The resulting Asymptotically Optimal RRT-Connect (AORRTC) finds initial solutions in similar times as RRT-Connect and uses any additional planning time to converge towards the optimal solution in an anytime manner. It is proven to be probabilistically complete and a.s.a.o. AORRTC was tested with the Panda (7 DoF) and Fetch (8 DoF) robotic arms on the MotionBenchMaker dataset. These experiments show that AORRTC finds initial solutions as fast as RRT-Connect and faster than the tested state-of-the-art a.s.a.o. algorithms while converging to better solutions faster. AORRTC finds solutions to difficult high-DoF planning problems in milliseconds where the other a.s.a.o. planners could not consistently find solutions in seconds. This performance was demonstrated both with and without single instruction/multiple data (SIMD) acceleration.
Accurate lymph node metastasis (LNM) assessment in rectal cancer is essential for treatment planning, yet current MRI-based evaluation shows unsatisfactory accuracy, leading to suboptimal clinical decisions. Developing automated systems also faces significant obstacles, primarily the lack of node-level annotations. Previous methods treat lymph nodes as isolated entities rather than as an interconnected system, overlooking valuable spatial and contextual information. To solve this problem, we present WeGA, a novel weakly-supervised global-local affinity learning framework that addresses these challenges through three key innovations: 1) a dual-branch architecture with DINOv2 backbone for global context and residual encoder for local node details; 2) a global-local affinity extractor that aligns features across scales through cross-attention fusion; and 3) a regional affinity loss that enforces structural coherence between classification maps and anatomical regions. Experiments across one internal and two external test centers demonstrate that WeGA outperforms existing methods, achieving AUCs of 0.750, 0.822, and 0.802 respectively. By effectively modeling the relationships between individual lymph nodes and their collective context, WeGA provides a more accurate and generalizable approach for lymph node metastasis prediction, potentially enhancing diagnostic precision and treatment selection for rectal cancer patients.
Incorporating an autonomous auxiliary camera into robot-assisted minimally invasive surgery (RAMIS) enhances spatial awareness and eliminates manual viewpoint control. Existing path planning methods for auxiliary cameras track two-dimensional surgical features but do not simultaneously account for camera orientation, workspace constraints, and robot joint limits. This study presents AutoCam: an automatic auxiliary camera placement method to improve visualization in RAMIS. Implemented on the da Vinci Research Kit, the system uses a priority-based, workspace-constrained control algorithm that combines heuristic geometric placement with nonlinear optimization to ensure robust camera tracking. A user study (N=6) demonstrated that the system maintained 99.84% visibility of a salient feature and achieved a pose error of 4.36 $\pm$ 2.11 degrees and 1.95 $\pm$ 5.66 mm. The controller was computationally efficient, with a loop time of 6.8 $\pm$ 12.8 ms. An additional pilot study (N=6), where novices completed a Fundamentals of Laparoscopic Surgery training task, suggests that users can teleoperate just as effectively from AutoCam's viewpoint as from the endoscope's while still benefiting from AutoCam's improved visual coverage of the scene. These results indicate that an auxiliary camera can be autonomously controlled using the da Vinci patient-side manipulators to track a salient feature, laying the groundwork for new multi-camera visualization methods in RAMIS.
The multi-agent path finding (MAPF) problem asks to find a set of paths on a graph such that when synchronously following these paths the agents never encounter a conflict. In the most widespread MAPF formulation, the so-called Classical MAPF, the agents sizes are neglected and two types of conflicts are considered: occupying the same vertex or using the same edge at the same time step. Meanwhile in numerous practical applications, e.g. in robotics, taking into account the agents' sizes is vital to ensure that the MAPF solutions can be safely executed. Introducing large agents yields an additional type of conflict arising when one agent follows an edge and its body overlaps with the body of another agent that is actually not using this same edge (e.g. staying still at some distinct vertex of the graph). Until now it was not clear how harder the problem gets when such conflicts are to be considered while planning. Specifically, it was known that Classical MAPF problem on an undirected graph can be solved in polynomial time, however no complete polynomial-time algorithm was presented to solve MAPF with large agents. In this paper we, for the first time, establish that the latter problem is NP-hard and, thus, if P!=NP no polynomial algorithm for it can, unfortunately, be presented. Our proof is based on the prevalent in the field technique of reducing the seminal 3SAT problem (which is known to be an NP-complete problem) to the problem at hand. In particular, for an arbitrary 3SAT formula we procedurally construct a dedicated graph with specific start and goal vertices and show that the given 3SAT formula is satisfiable iff the corresponding path finding instance has a solution.
Motion planning problems for physically-coupled multi-robot systems in cluttered environments are challenging due to their high dimensionality. Existing methods combining sampling-based planners with trajectory optimization produce suboptimal results and lack theoretical guarantees. We propose Physically-coupled discontinuity-bounded Conflict-Based Search (pc-dbCBS), an anytime kinodynamic motion planner, that extends discontinuity-bounded CBS to rigidly-coupled systems. Our approach proposes a tri-level conflict detection and resolution framework that includes the physical coupling between the robots. Moreover, pc-dbCBS alternates iteratively between state space representations, thereby preserving probabilistic completeness and asymptotic optimality while relying only on single-robot motion primitives. Across 25 simulated and six real-world problems involving multirotors carrying a cable-suspended payload and differential-drive robots linked by rigid rods, pc-dbCBS solves up to 92% more instances than a state-of-the-art baseline and plans trajectories that are 50-60% faster while reducing planning time by an order of magnitude.
Polars and low-accretion rate polars (LARPs) are strongly magnetic cataclysmic variables. Mediated by the magnetic field of the white dwarf, their spin and binary orbit are (mostly) synchronized. They play an important role in our understanding of close binary evolution and the generation of strong magnetic fields in white dwarfs. Thanks to X-ray all-sky surveys, optical variability, and spectroscopic surveys, the number of polars and LARPs has grown from just a few in the 1980s to more than 200 today. Follow-up studies are facilitated by the systematic compilation of these systems presented here, which is also made available as an online resource. Yearly updates are planned, and community input is highly appreciated.
The charging scheduling problem of Electric Buses (EBs) is investigated based on Deep Reinforcement Learning (DRL). A Markov Decision Process (MDP) is conceived, where the time horizon includes multiple charging and operating periods in a day, while each period is further divided into multiple time steps. To overcome the challenge of long-range multi-phase planning with sparse reward, we conceive Hierarchical DRL (HDRL) for decoupling the original MDP into a high-level Semi-MDP (SMDP) and multiple low-level MDPs. The Hierarchical Double Deep Q-Network (HDDQN)-Hindsight Experience Replay (HER) algorithm is proposed for simultaneously solving the decision problems arising at different temporal resolutions. As a result, the high-level agent learns an effective policy for prescribing the charging targets for every charging period, while the low-level agent learns an optimal policy for setting the charging power of every time step within a single charging period, with the aim of minimizing the charging costs while meeting the charging target. It is proved that the flat policy constructed by superimposing the optimal high-level policy and the optimal low-level policy performs as well as the optimal policy of the original MDP. Since jointly learning both levels of policies is challenging due to the non-stationarity of the high-level agent and the sampling inefficiency of the low-level agent, we divide the joint learning process into two phases and exploit our new HER algorithm to manipulate the experience replay buffers for both levels of agents. Numerical experiments are performed with the aid of real-world data to evaluate the performance of the proposed algorithm.
High-definition (HD) maps offer extensive and accurate environmental information about the driving scene, making them a crucial and essential element for planning within autonomous driving systems. To avoid extensive efforts from manual labeling, methods for automating the map creation have emerged. Recent trends have moved from offline mapping to online mapping, ensuring availability and actuality of the utilized maps. While the performance has increased in recent years, online mapping still faces challenges regarding temporal consistency, sensor occlusion, runtime, and generalization. We propose a novel offline mapping approach that integrates trails - informal routes used by drivers - into the map creation process. Our method aggregates trail data from the ego vehicle and other traffic participants to construct a comprehensive global map using transformer-based deep learning models. Unlike traditional offline mapping, our approach enables continuous updates while remaining sensor-agnostic, facilitating efficient data transfer. Our method demonstrates superior performance compared to state-of-the-art online mapping approaches, achieving improved generalization to previously unseen environments and sensor configurations. We validate our approach on two benchmark datasets, highlighting its robustness and applicability in autonomous driving systems.
Research on autonomous robotic surgery has largely focused on simple task automation in controlled environments. However, real-world surgical applications require dexterous manipulation over extended time scales while demanding generalization across diverse variations in human tissue. These challenges remain difficult to address using existing logic-based or conventional end-to-end learning strategies. To bridge this gap, we propose a hierarchical framework for dexterous, long-horizon surgical tasks. Our method employs a high-level policy for task planning and a low-level policy for generating task-space controls for the surgical robot. The high-level planner plans tasks using language, producing task-specific or corrective instructions that guide the robot at a coarse level. Leveraging language as a planning modality offers an intuitive and generalizable interface, mirroring how experienced surgeons instruct traineers during procedures. We validate our framework in ex-vivo experiments on a complex minimally invasive procedure, cholecystectomy, and conduct ablative studies to assess key design choices. Our approach achieves a 100% success rate across n=8 different ex-vivo gallbladders, operating fully autonomously without human intervention. The hierarchical approach greatly improves the policy's ability to recover from suboptimal states that are inevitable in the highly dynamic environment of realistic surgical applications. This work represents the first demonstration of step-level autonomy, marking a critical milestone toward autonomous surgical systems for clinical studies. By advancing generalizable autonomy in surgical robotics, our approach brings the field closer to real-world deployment.
In this work, we specialize contributions from prior work on data-driven trajectory generation for a quadrotor system with motor saturation constraints. When motors saturate in quadrotor systems, there is an ``uncontrolled drift" of the vehicle that results in a crash. To tackle saturation, we apply a control decomposition and learn a tracking penalty from simulation data consisting of low, medium and high-cost reference trajectories. Our approach reduces crash rates by around $49\%$ compared to baselines on aggressive maneuvers in simulation. On the Crazyflie hardware platform, we demonstrate feasibility through experiments that lead to successful flights. Motivated by the growing interest in data-driven methods to quadrotor planning, we provide open-source lightweight code with an easy-to-use abstraction of hardware platforms.
This paper investigates training better visual world models for robot manipulation, i.e., models that can predict future visual observations by conditioning on past frames and robot actions. Specifically, we consider world models that operate on RGB-D frames (RGB-D world models). As opposed to canonical approaches that handle dynamics prediction mostly implicitly and reconcile it with visual rendering in a single model, we introduce FlowDreamer, which adopts 3D scene flow as explicit motion representations. FlowDreamer first predicts 3D scene flow from past frame and action conditions with a U-Net, and then a diffusion model will predict the future frame utilizing the scene flow. FlowDreamer is trained end-to-end despite its modularized nature. We conduct experiments on 4 different benchmarks, covering both video prediction and visual planning tasks. The results demonstrate that FlowDreamer achieves better performance compared to other baseline RGB-D world models by 7% on semantic similarity, 11% on pixel quality, and 6% on success rate in various robot manipulation domains.
This work proposes a fast heuristic algorithm for the coupled scheduling and trajectory planning of multiple Cartesian robotic arms harvesting fruits. Our method partitions the workspace, assigns fruit-picking sequences to arms, determines tight and feasible fruit-picking schedules and vehicle travel speed, and generates smooth, collision-free arm trajectories. The fruit-picking throughput achieved by the algorithm was assessed using synthetically generated fruit coordinates and a harvester design featuring up to 12 arms. The throughput increased monotonically as more arms were added. Adding more arms when fruit densities were low resulted in diminishing gains because it took longer to travel from one fruit to another. However, when there were enough fruits, the proposed algorithm achieved a linear speedup as the number of arms increased.
In the Lighthill-Whitham-Richards (LWR) model for single-lane traffic, vehicle trajectories follow the first-in-first-out (FIFO) principle and can be represented by a monotone three-dimensional surface of cumulative vehicle count. In contrast, the generalized bathtub model, which describes congestion dynamics in transportation networks using relative space, typically violates the FIFO principle, making its representation more challenging. Building on the characteristic distance ordering concept, we observe that trips in the generalized bathtub model can be ordered by their characteristic distances (remaining trip distance plus network travel distance). We define a new cumulative number of trips ahead of a trip with a given remaining distance at a time instant, showing it forms a monotone three-dimensional surface despite FIFO violations. Using the inverse function theorem, we derive equivalent formulations with different coordinates and dependent variables, including special cases for Vickrey's bathtub model and the basic bathtub model. We demonstrate numerical methods based on these formulations and discuss trip-based approaches for discrete demand patterns. This study enhances understanding of the generalized bathtub model's properties, facilitating its application in network traffic flow modeling, congestion pricing, and transportation planning.
Ovarian cancer remains a challenging malignancy to diagnose and manage, with prognosis heavily dependent on the stage at detection. Accurate grading and staging, primarily based on histopathological examination of biopsy tissue samples, are crucial for treatment planning and predicting outcomes. However, this manual process is time-consuming and subject to inter-observer variability among pathologists. The increasing volume of digital histopathology slides necessitates the development of robust, automated methods to assist in this critical diagnostic step for ovarian cancer. (Methods) This study presents a deep learning framework for the automated prediction of ovarian cancer stage (classified into five categories: 0, I, II, III, IV) using routine histopathological images. We employed a transfer learning approach, fine-tuning a ResNet-101 convolutional neural network pre-trained on ImageNet. The training process incorporated comprehensive data augmentation, weighted random sampling, and class weighting to address dataset characteristics. Hyperparameter optimization for learning rate, dropout rate, and weight decay was performed using a genetic algorithm to enhance model performance and generalization. (Results) Evaluated on an independent test set of ovarian thin tissue brightfield images, the developed model achieved a high overall classification accuracy of 97.62%.
Ensuring safe and human-like trajectory planning for automated vehicles amidst real-world uncertainties remains a critical challenge. While existing car-following models often struggle to consistently provide rigorous safety proofs alongside human-like acceleration and deceleration patterns, we introduce a novel multi-phase projection-based car-following model. This model is designed to balance safety and performance by incorporating bounded acceleration and deceleration rates while emulating key human driving principles. Building upon a foundation of fundamental driving principles and a multi-phase dynamical systems analysis (detailed in Part 1 of this study \citep{jin2025WA20-02_Part1}), we first highlight the limitations of extending standard models like Newell's with simple bounded deceleration. Inspired by human drivers' anticipatory behavior, we mathematically define and analyze projected braking profiles for both leader and follower vehicles, establishing safety criteria and new phase definitions based on the projected braking lead-vehicle problem. The proposed parsimonious model combines an extended Newell's model for nominal driving with a new control law for scenarios requiring projected braking. Using speed-spacing phase plane analysis, we provide rigorous mathematical proofs of the model's adherence to defined safe and human-like driving principles, including collision-free operation, bounded deceleration, and acceptable safe stopping distance, under reasonable initial conditions. Numerical simulations validate the model's superior performance in achieving both safety and human-like braking profiles for the stationary lead-vehicle problem. Finally, we discuss the model's implications and future research directions.
Trajectory planning is essential for ensuring safe driving in the face of uncertainties related to communication, sensing, and dynamic factors such as weather, road conditions, policies, and other road users. Existing car-following models often lack rigorous safety proofs and the ability to replicate human-like driving behaviors consistently. This article applies multi-phase dynamical systems analysis to well-known car-following models to highlight the characteristics and limitations of existing approaches. We begin by formulating fundamental principles for safe and human-like car-following behaviors, which include zeroth-order principles for comfort and minimum jam spacings, first-order principles for speeds and time gaps, and second-order principles for comfort acceleration/deceleration bounds as well as braking profiles. From a set of these zeroth- and first-order principles, we derive Newell's simplified car-following model. Subsequently, we analyze phases within the speed-spacing plane for the stationary lead-vehicle problem in Newell's model and its extensions, which incorporate both bounded acceleration and deceleration. We then analyze the performance of the Intelligent Driver Model and the Gipps model. Through this analysis, we highlight the limitations of these models with respect to some of the aforementioned principles. Numerical simulations and empirical observations validate the theoretical insights. Finally, we discuss future research directions to further integrate safety, human-like behaviors, and vehicular automation in car-following models, which are addressed in Part 2 of this study \citep{jin2025WA20-02_Part2}, where we develop a novel multi-phase projection-based car-following model that addresses the limitations identified here.
Cancer remains a leading cause of death worldwide, necessitating personalized treatment approaches to improve outcomes. Theranostics, combining molecular-level imaging with targeted therapy, offers potential for precision oncology but requires optimized, patient-specific care plans. This paper investigates state-of-the-art data-driven decision support applications with a reinforcement learning focus in precision oncology. We review current applications, training environments, state-space representation, performance evaluation criteria, and measurement of risk and reward, highlighting key challenges. We propose a framework integrating data-driven modeling with reinforcement learning-based decision support to optimize radiopharmaceutical therapy dosing, addressing identified challenges and setting directions for future research. The framework leverages Neural Ordinary Differential Equations and Physics-Informed Neural Networks to enhance Physiologically Based Pharmacokinetic models while applying reinforcement learning algorithms to iteratively refine treatment policies based on patient-specific data.
The fields of autonomous systems and robotics are receiving considerable attention in civil applications such as construction, logistics, and firefighting. Nevertheless, the widespread adoption of these technologies is hindered by the necessity for robust processing units to run AI models. Edge-AI solutions offer considerable promise, enabling low-power, cost-effective robotics that can automate civil services, improve safety, and enhance sustainability. This paper presents a novel Edge-AI-enabled drone-based surveillance system for autonomous multi-robot operations at construction sites. Our system integrates a lightweight MCU-based object detection model within a custom-built UAV platform and a 5G-enabled multi-agent coordination infrastructure. We specifically target the real-time obstacle detection and dynamic path planning problem in construction environments, providing a comprehensive dataset specifically created for MCU-based edge applications. Field experiments demonstrate practical viability and identify optimal operational parameters, highlighting our approach's scalability and computational efficiency advantages compared to existing UAV solutions. The present and future roles of autonomous vehicles on construction sites are also discussed, as well as the effectiveness of edge-AI solutions. We share our dataset publicly at github.com/egirgin/storaige-b950
In the context of mobile navigation in unstructured environments, the predominant approach entails the avoidance of obstacles. The prevailing path planning algorithms are contingent upon deviating from the intended path for an indefinite duration and returning to the closest point on the route after the obstacle is left behind spatially. However, avoiding an obstacle on a path that will be used repeatedly by multiple agents can hinder long-term efficiency and lead to a lasting reliance on an active path planning system. In this study, we propose an alternative approach to mobile navigation in unstructured environments by leveraging the manipulation capabilities of a robotic manipulator mounted on top of a mobile robot. Our proposed framework integrates exteroceptive and proprioceptive feedback to assess the push affordance of obstacles, facilitating their repositioning rather than avoidance. While our preliminary visual estimation takes into account the characteristics of both the obstacle and the surface it relies on, the push affordance estimation module exploits the force feedback obtained by interacting with the obstacle via a robotic manipulator as the guidance signal. The objective of our navigation approach is to enhance the efficiency of routes utilized by multiple agents over extended periods by reducing the overall time spent by a fleet in environments where autonomous infrastructure development is imperative, such as lunar or Martian surfaces.
In many scientific and industrial applications, we are given a handful of instances (a 'small ensemble') of a spatially distributed quantity (a 'field') but would like to acquire many more. For example, a large ensemble of global temperature sensitivity fields from a climate model can help farmers, insurers, and governments plan appropriately. When acquiring more data is prohibitively expensive -- as is the case with climate models -- statistical emulation offers an efficient alternative for simulating synthetic yet realistic fields. However, parameter inference using maximum likelihood estimation (MLE) is computationally prohibitive, especially for large, non-stationary fields. Thus, many recent works train neural networks to estimate parameters given spatial fields as input, sidestepping MLE completely. In this work we focus on a popular class of parametric, spatially autoregressive (SAR) models. We make a simple yet impactful observation; because the SAR parameters can be arranged on a regular grid, both inputs (spatial fields) and outputs (model parameters) can be viewed as images. Using this insight, we demonstrate that image-to-image (I2I) networks enable faster and more accurate parameter estimation for a class of non-stationary SAR models with unprecedented complexity.
Effective education in radiotherapy plan quality review requires a robust, regularly updated set of examples and the flexibility to demonstrate multiple possible planning approaches and their consequences. However, the current clinic-based paradigm does not support these needs. To address this, we have developed 'Virtual Dosimetrist' models that can both generate training examples of suboptimal treatment plans and then allow trainees to improve the plan quality through simple natural language prompts, as if communicating with a dosimetrist. The dose generation and modification process is accurate, rapid, and requires only modest resources. This work is the first to combine dose distribution prediction with natural language processing; providing a robust pipeline for both generating suboptimal training plans and allowing trainees to practice their critical plan review and improvement skills that addresses the challenges of the current clinic-based paradigm.
High-resolution cross-correlation spectroscopy (HRCCS) is a technique for detecting the atmospheres of close-in planets using the change in the projected planet velocity over a few hours. To date, this technique has most often been applied to hot Jupiters, which show a large change in velocity on short timescales. Applying this technique to planets with longer orbital periods requires an improved understanding of how the size of the velocity shift and the observational signal-to-noise ratio impact detectability. We present grids of simulated Keck/KPIC observations of hot Jupiter systems, varying the observed planet velocity shift and signal-to-noise ratio (SNR), to estimate the minimum thresholds for a successful detection. These simulations realistically model the cross-correlation process, which includes a time-varying telluric spectrum in the simulated data and data detrending via PCA. We test three different planet models based on an ultra-hot Jupiter, a classical hot Jupiter, and a metal-rich hot Saturn. For a ${6}\sigma$ detection suitable for retrieval analysis, we estimate a minimum velocity shift of $\Delta v_\text{pl} \sim {30, 50, 60}$ km/s, compared to an instrumental resolution of 9 km/s, and minimum SNR $\sim 370, 800, 1200$ for the respective planet models. We find that reported KPIC detections to-date fall above or near the ${6}\sigma$ limit. These simulations can be efficiently re-run for other planet models and observational parameters, which can be useful in observation planning and detection validation.
Autonomous navigation in off-road environments remains a significant challenge in field robotics, particularly for Unmanned Ground Vehicles (UGVs) tasked with search and rescue, exploration, and surveillance. Effective long-range planning relies on the integration of onboard perception systems with prior environmental knowledge, such as satellite imagery and LiDAR data. This work introduces Trailblazer, a novel framework that automates the conversion of multi-modal sensor data into costmaps, enabling efficient path planning without manual tuning. Unlike traditional approaches, Trailblazer leverages imitation learning and a differentiable A* planner to learn costmaps directly from expert demonstrations, enhancing adaptability across diverse terrains. The proposed methodology was validated through extensive real-world testing, achieving robust performance in dynamic and complex environments, demonstrating Trailblazer's potential for scalable, efficient autonomous navigation.
Understanding an agent's intent through its behavior is essential in human-robot interaction, interactive AI systems, and multi-agent collaborations. This task, known as Goal Recognition (GR), poses significant challenges in dynamic environments where goals are numerous and constantly evolving. Traditional GR methods, designed for a predefined set of goals, often struggle to adapt to these dynamic scenarios. To address this limitation, we introduce the General Dynamic GR problem - a broader definition of GR - aimed at enabling real-time GR systems and fostering further research in this area. Expanding on this foundation, this paper employs a model-free goal-conditioned RL approach to enable fast adaptation for GR across various changing tasks.
Nanodosimetry relates Ionization Detail (ID) and ionization parameters (Ip) to biological endpoints relevant for charged-particle radiotherapy. This supports a more physics-based modeling of biological effectiveness than traditional dose-response relationships and RBE models. Faddegon et al. (2023) introduced cluster dose g(Ip) as a physical quantity, bridging ID to the treatment planning level, which can be directly optimized. We developed a framework enabling cluster dose optimization via a pencil-beam (PB) algorithm, and validated against Monte Carlo (MC) simulations. The framework, integrated into the treatment planning toolkit matRad, uses precomputed Ip values obtained from MC track-structure simulations. We applied our tool for plan optimization with protons, helium, and carbon ions in a water phantom and a prostate case. Recalculation with TOPAS showed 3D gamma passing rates >97% (phantom) and >98% (patient) using a 3%/3mm criterion and a threshold of 10% of the maximum dose. Cluster dose F5 optimization produced homogeneous target coverage, with heavier ions requiring lower absorbed doses for the same prescribed cluster dose level. This demonstrates the feasibility of fast, accurate cluster dose optimization using PB algorithms.
Autonomous vehicles need a complete map of their surroundings to plan and act. This has sparked research into the tasks of 3D occupancy prediction, 3D scene completion, and 3D panoptic scene completion, which predict a dense map of the ego vehicle's surroundings as a voxel grid. Scene completion extends occupancy prediction by predicting occluded regions of the voxel grid, and panoptic scene completion further extends this task by also distinguishing object instances within the same class; both aspects are crucial for path planning and decision-making. However, 3D panoptic scene completion is currently underexplored. This work introduces a novel framework for 3D panoptic scene completion that extends existing 3D semantic scene completion models. We propose an Object Module and Panoptic Module that can easily be integrated with 3D occupancy and scene completion methods presented in the literature. Our approach leverages the available annotations in occupancy benchmarks, allowing individual object shapes to be learned as a differentiable problem. The code is available at https://github.com/nicolamarinello/OffsetOcc .
The surface of Europa experiences a competition between thermally-induced crystallization and radiation-induced amorphization processes, leading to changes of its crystalline structure. The non-linear crystallization and temperature-dependent amorphization rate, incorporating ions, electrons and UV doses, are integrated into our multiphysics surface model (MSM) LunaIcy, enabling simulations of these coupled processes on icy moons. Thirty simulations spanning 100 000 years, covering the full ranges of albedo and latitude values on Europa, explore the competition between crystallization and irradiation. This is the first modeling of depth-dependent crystallinity profiles on icy moons. The results of our simulations are coherent with existing spectroscopic studies of Europa, both methods showing a primarily amorphous phase at the surface, followed by a crystalline phase after the first millimeter depth. Our method provides quantitative insights into how various parameters found on Europa can influence the subsurface crystallinity profiles. Interpolating upon our simulations, we have generated a crystallinity map of Europa showing, within the top millimeter, highly crystalline ice near the equator, amorphous ice at the poles, and a mix of the two at mid-latitudes. Regions/depths with balanced competition between crystallization and amorphization rates are of high interest due to their periodic fluctuations in crystalline fraction. Our interpolated map reveals periodic variations, with seasonal amplitudes reaching up to 35% of crystalline fraction. These variations could be detected through spectroscopy, and we propose a plan to observe them in forthcoming missions.
This paper presents aUToPath, a unified online framework for global path-planning and control to address the challenge of autonomous navigation in cluttered urban environments. A key component of our framework is a novel hybrid planner that combines pre-computed lattice maps with dynamic free-space sampling to efficiently generate optimal driveable corridors in cluttered scenarios. Our system also features sequential convex programming (SCP)-based model predictive control (MPC) to refine the corridors into smooth, dynamically consistent trajectories. A single optimization problem is used to both generate a trajectory and its corresponding control commands; this addresses limitations of decoupled approaches by guaranteeing a safe and feasible path. Simulation results of the novel planner on randomly generated obstacle-rich scenarios demonstrate the success rate of a free-space Adaptively Informed Trees* (AIT*)-based planner, and runtimes comparable to a lattice-based planner. Real-world experiments of the full system on a Chevrolet Bolt EUV further validate performance in dense obstacle fields, demonstrating no violations of traffic, kinematic, or vehicle constraints, and a 100% success rate across eight trials.