Robotics
Planning for Change: Reinforcement Learning Combined with Bounded Extremum Seeking for Robotic Control under Distribution Shift
Shaifalee Saxena, Rafael Fierro and Alexander Scheinker
Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test conditions differ from the training distribution. This limitation is especially important for reliable
robot planning and control in contact-rich tasks such as pushing and pick-and-place, where changes in goals, contact conditions, or
robot dynamics can drive the system out-of-distribution at inference time. In this paper, we investigate a hybrid controller that combines reinforcement learning with bounded extremum seeking (ES) to improve robustness under such conditions. In the proposed approach, deep deterministic policy gradient (DDPG) policies are trained under standard conditions on the robotic pushing and pick-and-place tasks, and are then combined with bounded ES during deployment. The RL policy provides fast manipulation behavior, while bounded ES ensures robustness of the overall controller to time variations when operating conditions depart from those seen during training. The resulting controller is evaluated under several out-of-distribution settings, including time-varying goals and spatially varying friction patches. Crucially, under reasonable assumptions, we prove finite time RL-based convergence of a robotic arm to an object after which bounded ES achieves finite-time convergence to a bounded velocity moving target. We provide analytic formulas for both convergence times, and an ability to tune the convergence times by our choice of gains.
Read the full abstract ▾
Robotics
VRUD: A Drone Dataset for Complex Vehicle-VRU Interactions within Mixed Traffic
Ziyu Wang, Hongrui Kou, Cheng Wang et al. (+4 more)
The Operational Design Domain (ODD) of urbanoriented Level 4 (L4) autonomous driving, especially for autonomous robotaxis, confronts formidable challenges in complex urban mixed traffic environments. These challenges stem mainly from the high density of Vulnerable Road Users (VRUs) and their highly uncertain and unpredictable interaction behaviors. However, existing open-source
datasets predominantly focus on structured scenarios such as highways or regulated intersections, leaving a critical gap in data representing chaotic, unstructured urban environments. To address this, this paper proposes an efficient, high-precision method for constructing drone-based
datasets and establishes the Vehicle-Vulnerable Road User Interaction
Dataset (VRUD), as illustrated in Figure 1. Distinct from prior works, VRUD is collected from typical "Urban Villages" in Shenzhen, characterized by loose traffic supervision and extreme occlusion. The
dataset comprises 4 hours of 4K/30Hz recording, containing 11,479 VRU trajectories and 1,939 vehicle trajectories. A key characteristic of VRUD is its composition: VRUs account for about 87% of all traffic participants, significantly exceeding the proportions in existing
benchmarks. Furthermore, unlike
datasets that only provide raw trajectories, we extracted 4,002 multi-
agent interaction scenarios based on a novel Vector Time to Collision (VTTC) threshold, supported by standard OpenDRIVE HD maps. This study provides valuable, rare edge-case resources for enhancing the safety performance of ADS in complex, unstructured urban environments. To facilitate further research, we have made the VRUD
dataset open-source at: https://zzi4.github.io/VRUD/.
Read the full abstract ▾
All authors Ziyu Wang, Hongrui Kou, Cheng Wang, Ruochen Li, Hubert P. H. Shum, Amir Atapour-Abarghouei, Yuxin Zhang
Robotics · Cross-listed from cs.CV
ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction
Yuheng Zhang, Mengfei Duan, Kunyu Peng et al. (+5 more)
3D semantic occupancy prediction is central to autonomous driving, yet current methods are vulnerable to long-tailed class bias and out-of-distribution (OOD) inputs, often overconfidently assigning anomalies to rare classes. We present ProOOD, a lightweight, plug-and-play method that couples prototype-guided refinement with training-free OOD scoring. ProOOD comprises (i) prototype-guided semantic imputation that fills occluded regions with class-consistent features, (ii) prototype-guided tail mining that strengthens rare-class representations to curb OOD absorption, and (iii) EchoOOD, which fuses local logit coherence with local and global prototype matching to produce reliable voxel-level OOD scores. Extensive experiments on five
datasets demonstrate that ProOOD achieves state-of-the-art performance on both in-distribution 3D occupancy prediction and OOD detection. On SemanticKITTI, it surpasses baselines by +3.57% mIoU overall and +24.80% tail-class mIoU; on VAA-KITTI, it improves AuPRCr by +19.34 points, with consistent gains across
benchmarks. These improvements yield more calibrated occupancy estimates and more reliable OOD detection in safety-critical urban driving. The source code is publicly available at https://github.com/7uHeng/ProOOD.
Read the full abstract ▾
All authors Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Di Wen, Danda Pani Paudel, Luc Van Gool, Kailun Yang
Robotics
BAT: Balancing Agility and Stability via Online Policy Switching for Long-Horizon Whole-Body Humanoid Control
Donghoon Baek, Sang-Hun Kim and Sehoon Ha
Despite advances in reinforcement and imitation learning, achieving both precise control and dynamic whole-body behaviors in long-horizon tasks remains challenging. Existing approaches typically follow two paradigms: coupled whole-body policies for global coordination and decoupled policies for modular precision. However, effectively combining these two types of controllers to achieve agility, robustness, and precision remains challenging. In this work, we propose BAT, an online policyswitching framework that dynamically selects between coupled and decoupled whole-body RL generalist controllers according to the evolving motion context. BAT employs two complementary switching predictors: OpVQ-VAE provides motion-
token-based predictions with strong generalization, while OpHRL provides closed-loop, state-aware predictions. A
Token-Familiarity Router (TFR) selects between their predictions, favoring OpHRL for familiar
token sequences and OpVQ-VAE for unfamiliar ones when their predictions disagree. BAT achieves 85.2% success on seen long-horizon motion combinations, while retaining 71.3% success on unseen motions. BAT also outperforms existing whole-body controllers on individual motions and demonstrates successful zero-shot deployment on the Unitree G1
humanoid.
Read the full abstract ▾
Robotics
Stein Variational Uncertainty-Adaptive Model Predictive Control
Hrishikesh Sathyanarayan and Ian Abraham
We propose a Stein variational distributionally robust controller for nonlinear dynamical systems with latent parametric uncertainty. The method is an alternative to conservative worst-case ambiguity-set optimization with a deterministic particle-based approximation of a task-dependent uncertainty distribution, enabling the controller to concentrate on parameter sensitivities that most strongly affect closed-loop performance. Our method yields a controller that is robust to latent parameter uncertainty by coupling optimal control with Stein variational inference, and avoiding restrictive parametric assumptions on the uncertainty model while preserving computational parallelism. In contrast to classical DRO, which can sacrifice nominal performance through worst-case design, we find our approach achieves robustness by shaping the control law around relevant uncertainty that are most critical to the task objective. The proposed framework therefore reconciles robust control and variational inference in a single decision-theoretic formulation for broad classes of control systems with parameter uncertainty. We demonstrate our approach on representative control problems that empirically illustrate improved performance-robustness tradeoffs over nominal, ensemble, and classical distributionally robust baselines.
Read the full abstract ▾
Robotics
Infinite-Horizon Ergodic Control via Kernel Mean Embeddings
Christian Hughes and Ian Abraham
This paper derives an infinite-horizon ergodic controller based on kernel mean
embeddings for long-duration coverage tasks on general domains. While existing kernel-based ergodic control methods provide strong coverage guarantees on general coverage domains, their practical use has been limited to sub-ergodic, finite-time horizons due to intractable computational scaling, prohibiting its use for long-duration coverage. We resolve this scaling by deriving an infinite-horizon ergodic controller equipped with an extended kernel mean
embedding error visitation state that recursively records state visitation. This extended state decouples past visitation from future control synthesis and expands ergodic control to infinite-time settings. In addition, we present a variation of the controller that operates on a receding-horizon control formulation with the extended error state. We demonstrate theoretical proof of asymptotic convergence of the derived controller and show preservation of ergodic coverage guarantees for a class of 2D and 3D coverage problems.
Read the full abstract ▾
Robotics · Cross-listed from astro-ph.IM
Focal plane wavefront control with model-based reinforcement learning
Jalo Nousiainen, Iremsu Taskin, Markus Kasper et al. (+2 more)
The direct imaging of potentially habitable
exoplanets is one
prime science case for high-contrast imaging instruments on extremely large
telescopes. Most such
exoplanets orbit close to their host
stars, where their observation is limited by fast-moving atmospheric speckles and quasi-static non-common-path aberrations (NCPA). Conventional NCPA correction methods often use mechanical mirror probes, which compromise performance during operation. This work presents machine-learning-based NCPA control methods that automatically detect and correct both dynamic and static NCPA errors by leveraging sequential phase diversity. We extend previous work in reinforcement learning for AO to focal plane control. A new model-based RL
algorithm, Policy Optimization for NCPAs (PO4NCPA), interprets the focal-plane image as input data and, through sequential phase diversity, determines phase corrections that optimize both non-coronagraphic and post-coronagraphic PSFs without prior system knowledge. Further, we demonstrate the effectiveness of this approach by numerically simulating static NCPA errors on a ground-based
telescope and an infrared imager affected by water-vapor-induced seeing (dynamic NCPAs). Simulations show that PO4NCPA robustly compensates static and dynamic NCPAs. In static cases, it achieves near-optimal focal-plane light suppression with a coronagraph and near-optimal Strehl without one. With dynamics NCPA, it matches the performance of the modal least-squares reconstruction combined with a 1-step delay integrator in these metrics. The method remains effective for the ELT pupil, vector
vortex coronagraph, and under
photon and background noise. PO4NCPA is model-free and can be directly applied to standard imaging as well as to any coronagraph. Its sub-millisecond inference times and performance also make it suitable for real-time low-order correction of atmospheric
turbulence beyond HCI.
Read the full abstract ▾
All authors Jalo Nousiainen, Iremsu Taskin, Markus Kasper, Gilles Orban De Xivry, Olivier Absil
Robotics
An Integrated Soft Robotic System for Measuring Vital Signs in Search and Rescue Environments
Jorge Francisco García-Samartín, Christyan Cruz Ulloa, Andrés Sánchez-Silva et al. (+2 more)
Robots are frequently utilized in search-and-rescue operations. In recent years, significant advancements have been made in the field of victim assessment. However, there are still open issues regarding heart rate measurement, and no studies have been found that assess pressure in post-disaster scenarios. This work designs a soft gripper and integrates it into a mobile robotic system, thereby creating a device capable of measuring the pulse and blood pressure of victims in post-disaster environments. The gripper is designed to envelop the victim's arm and inflate like a sphygmomanometer, facilitated by a specialized portability system. The utilization of different signal processing
algorithms has enabled the attainment of a pulse bias of \qty{4}{\bpm} and a bias of approximately \qty{5}{\mmHg} for systolic and diastolic pressures. The findings, in conjunction with the other statistical data and the validation of homoscedasticity in the error terms, prove the system's capacity to accurately determine heart rate and blood pressure, thereby rendering it suitable for search and rescue operations. Finally, a post-disaster has been employed as a test to validate the functionality of the entire system and to demonstrate its capacity to adapt to various victim positions, its measurement speed, and its safety for victims.
Read the full abstract ▾
All authors Jorge Francisco García-Samartín, Christyan Cruz Ulloa, Andrés Sánchez-Silva, Jaime del Cerro, Antonio Barrientos
Robotics
PanoAir: A Panoramic Visual-Inertial SLAM with Cross-Time Real-World UAV Dataset
Yiyang Wu, Xiaohu Zhang, Yanjin Du et al. (+5 more)
Accurate pose estimation is fundamental for unmanned aerial vehicle (
UAV) applications, where Visual-Inertial SLAM (VI-SLAM) provides a cost-effective solution for localization and mapping. However, existing VI-SLAM methods mainly rely on sensors with limited fields of view (FoV), which can lead to drift and even failure in complex
UAV scenarios. Although panoramic cameras provide omnidirectional perception to improve robustness, panoramic VI-SLAM and corresponding real-world
datasets for
UAVs remain underexplored. To address this limitation, we first construct a real-world panoramic visual-inertial
dataset covering diverse flight conditions, including varying illumination, altitudes, trajectory lengths, and motion dynamics. To achieve accurate and robust pose estimation under such challenging
UAV scenarios, we propose a panoramic VI-SLAM framework that exploits the omnidirectional FoV via the proposed panoramic feature extraction and panoramic loop closure, enhancing feature constraints and ensuring global consistency. Extensive experiments on both the proposed
dataset and public
benchmarks demonstrate that our method achieves superior accuracy, robustness, and consistency, completing all 17 sequences without tracking failure and reducing the ATE by up to 47.1% compared with the best-performing baseline. Moreover, deployment on an embedded platform validates its practical applicability, achieving comparable computational efficiency to PC implementations. The source code and
dataset are publicly available at https://github.com/YYWumm/PanoAir
Read the full abstract ▾
All authors Yiyang Wu, Xiaohu Zhang, Yanjin Du, Tongsu Zhang, Chujun Li, Siyang Chen, Guoyi Zhang, Xiangpeng Xu
Robotics · Cross-listed from cs.CV
DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale
Sicheng Zuo, Zixun Xie, Wenzhao Zheng et al. (+6 more)
End-to-end autonomous driving has evolved from the conventional paradigm based on sparse perception into
vision-
language-action (VLA) models, which focus on learning
language descriptions as an auxiliary task to facilitate planning. In this paper, we propose an alternative
Vision-Geometry-Action (VGA) paradigm that advocates dense 3D geometry as the critical cue for autonomous driving. As vehicles operate in a 3D world, we think dense 3D geometry provides the most comprehensive information for decision-making. However, most existing geometry reconstruction methods (e.g., DVGT) rely on computationally expensive batch processing of multi-frame inputs and cannot be applied to online planning. To address this, we introduce a streaming Driving Visual Geometry
Transformer (DVGT-2), which processes inputs in an online manner and jointly outputs dense geometry and trajectory planning for the current frame. We employ temporal causal
attention and cache historical features to support on-the-fly inference. To further enhance efficiency, we propose a sliding-window streaming strategy and use historical caches within a certain interval to avoid repetitive computations. Despite the faster speed, DVGT-2 achieves superior geometry reconstruction performance on various
datasets. The same trained DVGT-2 can be directly applied to planning across diverse camera configurations without fine-tuning, including closed-loop NAVSIM and open-loop nuScenes
benchmarks.
Read the full abstract ▾
All authors Sicheng Zuo, Zixun Xie, Wenzhao Zheng, Shaoqing Xu, Fang Li, Hanbing Li, Long Chen, Zhi-Xin Yang, Jiwen Lu
Robotics
Compact Keyframe-Optimized Multi-Agent Gaussian Splatting SLAM
Monica M.Q. Li, Pierre-Yves Lajoie, Jialiang Liu et al. (+1 more)
Efficient multi-
agent 3D mapping is essential for robotic teams operating in unknown environments, but dense representations hinder real-time exchange over constrained communication links. In multi-
agent Simultaneous Localization and Mapping (SLAM), systems typically rely on a centralized server to merge and optimize the local maps produced by individual
agents. However, sharing these large map representations, particularly those generated by recent methods such as Gaussian Splatting, becomes a bottleneck in real-world scenarios with limited bandwidth. We present an improved multi-
agent RGB-D Gaussian Splatting SLAM framework that reduces communication load while preserving map fidelity. First, we incorporate a compaction step into our SLAM system to remove redundant 3D Gaussians, without degrading the rendering quality. Second, our approach performs centralized loop closure computation without initial guess, operating in two modes: a pure rendered-depth mode that requires no data beyond the 3D Gaussians, and a camera-depth mode that includes lightweight depth images for improved registration accuracy and additional Gaussian
pruning. Evaluation on both synthetic and real-world
datasets shows up to 85-95% reduction in transmitted data compared to state-of-the-art approaches in both modes, bringing 3D Gaussian multi-
agent SLAM closer to practical deployment in real-world scenarios. Code: https://github.com/lemonci/coko-slam
Read the full abstract ▾
All authors Monica M.Q. Li, Pierre-Yves Lajoie, Jialiang Liu, Giovanni Beltrame
Robotics
An Ergonomic, Customizable Soft Robotic Glove toward Personalized Hand Rehabilitation
Rui Chen, Firman Isma Serdana, Domenico Chiaradia et al. (+11 more)
Hand impairment following neurological disorders substantially limits independence in activities of daily living, motivating the development of effective assistive and rehabilitation strategies. Soft robotic gloves have attracted growing interest in this context, yet persistent challenges in customization, ergonomic fit, and user comfort constrain their clinical utility. Here, we present an ergonomic, customizable fabric-based soft robotic glove whose actuators can be tailored to individual finger-joint geometry. The glove comprises five dual-action actuators supporting finger flexion and extension, together with a dedicated thumb abduction actuator. Leveraging computer numerical control heat sealing technology, we fabricated symmetrical-chamber actuators that adopt a concave outer surface upon inflation, thereby increasing finger contact area and improving comfort. Characterization confirmed joint moment and grasping force sufficient for ADL-relevant tasks. In ten healthy subjects, active assistance significantly reduced forearm muscle activity during manipulation, and a pilot study in three individuals with cervical spinal cord injury showed more natural grasp patterns and reduced reliance on tenodesis grasp.
Read the full abstract ▾
All authors Rui Chen, Firman Isma Serdana, Domenico Chiaradia, Xianlong Mai, Elena Losanno, Gabriele Righi, Claudia De Santis, Federica Serra, Vincent Mendez, Cristian Camardella, Daniele Leonardis, Giulio Del Popolo, Silvestro Micera, Antonio Frisoli
Robotics
A wearable haptic device for edge and surface simulation
Rui Chen, Xianlong Mai, Alireza Sanaei et al. (+3 more)
Object manipulation is fundamental to virtual reality (VR) applications, yet conventional fingertip haptic devices fail to render certain tactile features relevant for immersive and precise interactions, as i.e. detection of edges. This paper presents a compact, lightweight fingertip haptic device (24.3 g) that delivers distinguishable surface and edge contact feedback through a novel dual-motor mechanism. Pressure distribution characterization using a 6 x 6 flexible sensor array demonstrates distinct contact patterns between the two stimulation modes. A preliminary user study with five participants achieved 93% average classification accuracy across four conditions (edge/surface contact with light/heavy pressure), with mean response times of 2.79 seconds. The results indicate that the proposed device can effectively convey edge and surface tactile cues, potentially enhancing object manipulation fidelity in VR environments.
Read the full abstract ▾
All authors Rui Chen, Xianlong Mai, Alireza Sanaei, Domenico Chiaradia, Antonio Frisoli, Daniele Leonardis
Robotics
How to Train your Tactile Model: Tactile Perception with Multi-fingered Robot Hands
Christopher J. Ford, Kaichen Shi, Laura Butcher et al. (+2 more)
Rapid deployment of new tactile sensors is essential for scalable robotic manipulation, especially in multi-fingered hands equipped with
vision-based tactile sensors. However, current methods for inferring contact properties rely heavily on convolutional neural networks (CNNs), which, while effective on known sensors, require large, sensor-specific
datasets. Furthermore, they require retraining for each new sensor due to differences in lens properties, illumination, and sensor wear. Here we introduce TacViT, a novel tactile perception model based on
Vision Transformers, designed to generalize on new sensor data. TacViT leverages global self-
attention mechanisms to extract robust features from tactile images, enabling accurate contact property inference even on previously unseen sensors. This capability significantly reduces the need for data collection and retraining, accelerating the deployment of new sensors. We evaluate TacViT on sensors for a five-fingered
robot hand and demonstrate its superior generalization performance compared to CNNs. Our results highlight TacViTs potential to make tactile sensing more scalable and practical for real-world robotic applications.
Read the full abstract ▾
All authors Christopher J. Ford, Kaichen Shi, Laura Butcher, Nathan F. Lepora, Efi Psomopoulou
Robotics
SoftHand Model-W: A 3D-Printed, Anthropomorphic, Underactuated Robot Hand with Integrated Wrist and Carpal Tunnel
Dhillon B. Merritt, Christopher J. Ford, Haoran Li et al. (+4 more)
This paper presents the SoftHand Model-W: a 3D-printed, underactuated, anthropomorphic
robot hand based on the Pisa/IIT SoftHand, with an integrated antagonistic tendon mechanism and 2 degree-of-freedom tendon-driven wrist. These four degrees-of-acuation provide active flexion and extension to the five fingers, and active flexion/extension and radial/ulnar deviation of the palm through the wrist, while preserving the synergistic and self-adaptive features of such SoftHands. A carpal tunnel-inspired tendon routing allows remote motor placement in the forearm, reducing distal inertia and maintaining a compact form factor. The SoftHand-W is mounted on a 6-axis
robot arm and tested with two reorientation tasks requiring coordination between the hand and arm's pose: cube stacking and in-plane disc rotation. Results comparing task time, arm joint travel, and configuration changes with and without wrist actuation show that adding the wrist reduces compensatory and reconfiguration movements of the arm for a quicker task-completion time. Moreover, the wrist enables pick-and-place operations that would be impossible otherwise. Overall, the SoftHand Model-W demonstrates how proximal degrees of freedom are key to achieving versatile, human-like manipulation in real world robotic applications, with a compact design enabling deployment in research and assistive settings.
Read the full abstract ▾
All authors Dhillon B. Merritt, Christopher J. Ford, Haoran Li, Malia Smith, Zhixing Chen, Efi Psomopoulou, Nathan F. Lepora
Robotics
LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics
Calvin Galagain, Martyna Poreba, François Goulette et al. (+1 more)
Panoptic
segmentation is a key enabler for robotic perception, as it unifies semantic understanding with object-level
reasoning. However, the increasing complexity of state-of-the-art models makes them unsuitable for deployment on resource-constrained platforms such as mobile
robots. We propose a novel approach called LiPS that addresses the challenge of efficient-to-compute panoptic
segmentation with a lightweight design that retains query-based decoding while introducing a streamlined feature extraction and fusion pathway. It aims at providing a strong panoptic
segmentation performance while substantially lowering the computational demands. Evaluations on standard
benchmarks demonstrate that LiPS attains accuracy comparable to much heavier baselines, while providing up to 4.5 higher throughput, measured in frames per second, and requiring nearly 6.8 times fewer computations. This efficiency makes LiPS a highly relevant bridge between modern panoptic models and real-world robotic applications.
Read the full abstract ▾
All authors Calvin Galagain, Martyna Poreba, François Goulette, Cyrill Stachniss
Robotics
StretchBot: A Neuro-Symbolic Framework for Adaptive Guidance with Assistive Robots
Luca Vogelgesang, Ahmed Mehdi Soltani, Mohammadhossein Khojasteh et al. (+4 more)
Assistive
robots have growing potential to support physical wellbeing in home and healthcare settings, for example, by guiding users through stretching or rehabilitation routines. However, existing systems remain largely scripted, which limits their ability to adapt to user state, environmental context, and interaction dynamics. In this work, we present StretchBot, a hybrid neuro-symbolic robotic coach for adaptive assistive guidance. The system combines
multimodal perception with knowledge-graph-grounded large
language model
reasoning to support context-aware adjustments during short stretching sessions while maintaining a structured routine. To complement the system description, we report an exploratory pilot comparison between scripted and adaptive guidance with three participants. The pilot findings suggest that the adaptive condition improved perceived adaptability and contextual relevance, while scripted guidance remained competitive in smoothness and predictability. These results provide preliminary evidence that structured actionable knowledge can help ground
language-model-based adaptation in
embodied assistive interaction, while also highlighting the need for larger, longitudinal studies to evaluate robustness, generalizability, and long-term user experience.
Read the full abstract ▾
All authors Luca Vogelgesang, Ahmed Mehdi Soltani, Mohammadhossein Khojasteh, Xinrui Zu, Stefano De Giorgis, Madalina Croitoru, Filip Ilievski
Robotics
Physical Imitation Learning: Distilling Control Policies into Passive Elasticity
Huyue Ma, Yurui Jin, Helmut Hauser et al. (+1 more)
Due to
brain-body co-
evolution, animals' intrinsic body dynamics play a crucial role in their energy-efficient locomotion. Specifically, the control effort is shared between active muscles and passive body dynamics–a principle often referred to as Physical Intelligence. As a result, the body dynamics are part of the solution. In contrast,
robot bodies are typically designed to be as simple as possible, but the active control often fights the intrinsic body dynamics, resulting in low energy-efficiency. We introduce Physical Imitation Learning (PIL), a novel approach that brings current robotics control closer to animals. PIL takes learned control policies obtained with Reinforcement Learning (RL) and systematically splits them up into an active and passive control contribution. The passive part can be then directly offloaded to passive Parallel Elastic Joints (PEJs). As a result, the active control contribution is significantly reduced, lowering the overall energy consumption. Furthermore, the policy can be trained via RL to leverage the PEJ assistance by generating gaits that are more readily emulated by the PEJs. This enables co-design of the active and passive control components, shifting a greater share of actuation effort to the PEJs. Here we demonstrate the potential of this approach in simulated quadrupeds. Our results show that the proposed approach can offload up to 95% of mechanical power to passive body dynamics on flat terrain and 13% on rough terrain. PIL thereby provides a generalisable route to task-specific Physical Intelligence applicable to a wide range of joint-based
robot morphologies.
Read the full abstract ▾
All authors Huyue Ma, Yurui Jin, Helmut Hauser, Rui Wu
Robotics
Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning
Yichen Xie, Yixiao Wang, Shuqi Zhao et al. (+4 more)
The generalization ability of imitation learning policies for robotic manipulation is fundamentally constrained by the diversity of expert demonstrations, while collecting demonstrations across varied environments is costly and difficult in practice. In this paper, we propose a practical framework that exploits inherent scene diversity without additional human effort by scaling camera views during demonstration collection. Instead of acquiring more trajectories, multiple synchronized camera perspectives are used to generate pseudo-demonstrations from each expert trajectory, which enriches the training distribution and improves viewpoint invariance in visual representations. We analyze how different action spaces interact with view scaling and show that camera-space representations further enhance diversity. In addition, we introduce a multiview action aggregation method that allows single-view policies to benefit from multiple cameras during deployment. Extensive experiments in simulation and real-world manipulation tasks demonstrate significant gains in data efficiency and generalization compared to single-view baselines. Our results suggest that scaling camera views provides a practical and scalable solution for imitation learning, which requires minimal additional hardware setup and integrates seamlessly with existing imitation learning
algorithms. The website of our project is https://yichen928.github.io/
robot_multiview.
Read the full abstract ▾
All authors Yichen Xie, Yixiao Wang, Shuqi Zhao, Cheng-En Wu, Masayoshi Tomizuka, Jianwen Xie, Hao-Shu Fang
Robotics · Cross-listed from math.MG
Bistable Quad-Nets Composed of Four-Bar Linkages
Gudrun Szewieczek, Daniel Huczala, Martin Pfurner et al. (+1 more)
We study a novel type of mechanical structures, composed of spatial four-bar linkages, that are bistable, that is, they allow for two distinct configurations. These structures have an interpretation as quad nets in the Study quadric which we use to prove existence of assemblies with an unbounded number of links and joints. We propose a purely
geometric construction of such objects, starting from infinitesimally flexible quad nets in Euclidean space and applying Whiteley de-averaging. This point of view situates the problem within the broader framework of discrete differential geometry and enables the construction of bistable structures from well-known classes of quad nets, such as discrete minimal surfaces. In contrast to many other construction methods for bistable structures, our approach does not rely on numerical optimization and it allows for simple control of relevant
geometric parameters such as axis positions and snap angles.
Read the full abstract ▾
All authors Gudrun Szewieczek, Daniel Huczala, Martin Pfurner, Hans-Peter Schröcker
Robotics
Reachability-Aware Time Scaling for Path Tracking
Hossein Gholampour and Logan E. Beaver
This paper studies tracking of collision-free waypoint paths produced by an offline planner for a planar double-integrator system with bounded speed and acceleration. Because sampling-based planners must route around obstacles, the resulting waypoint paths can contain sharp turns and high-
curvature regions, so one-step reachability under acceleration limits becomes critical even when the path geometry is collision-free. We build on a pure-pursuit-style, reachability-guided quadratic-program (QP) tracker with a one-step acceleration margin. Offline, we evaluate this margin along a spline fitted to the waypoint path and update a scalar speed-scaling profile so that the required one-step acceleration remains below the available bound. Online, the same look-ahead tracking structure is used to track the scaled reference.
Read the full abstract ▾
Robotics
Certificate-Driven Closed-Loop Multi-Agent Path Finding with Inheritable Factorization
Jiarui Li, Runyu Zhang and Gioele Zardini
Multi-
agent coordination in automated warehouses and logistics is commonly modeled as the Multi-
Agent Path Finding (MAPF) problem. Closed-loop MAPF
algorithms improve scalability by planning only the next movement and replanning online, but this finite-horizon viewpoint can be shortsighted and makes it difficult to preserve global guarantees and exploit compositional structure. This issue is especially visible in Anytime Closed-Loop Conflict-Based Search (ACCBS), which applies Conflict-Based Search (CBS) over dynamically extended finite horizons but, under finite computational budgets, may terminate with short active prefixes in dense instances. We introduce certificate trajectories and their associated fleet budget as a general mechanism for filtering closed-loop updates. A certificate provides a conflict-free fallback plan and a monotone upper bound on the remaining cost; accepting only certificate-improving updates yields completeness. The same budget information induces a budget-limited factorization that enables global, inheritable decomposition across timesteps. Instantiating the framework on ACCBS yields Certificate-Driven Conflict-Based Search (CDCBS). Experiments on
benchmark maps show that CDCBS achieves more consistent solution quality than ACCBS, particularly in dense settings, while the proposed factorization reduces effective group size.
Read the full abstract ▾
Robotics
Weizhuo Wang, Yanjie Ze, C. Karen Liu et al. (+1 more)
We present EgoNav, a system that enables a
humanoid robot to traverse diverse, unseen environments by learning entirely from 5 hours of human walking data, with no
robot data or finetuning. A
diffusion model predicts distributions of plausible future trajectories conditioned on past trajectory, a 360 deg visual
memory fusing color, depth, and semantics, and
video features from a frozen DINOv3 backbone that capture appearance cues invisible to depth sensors. A hybrid sampling scheme achieves real-time inference in 10 denoising steps, and a receding-horizon controller selects paths from the predicted distribution. We validate EgoNav through offline evaluations, where it outperforms baselines in collision avoidance and multi-modal coverage, and through zero-shot deployment on a Unitree G1
humanoid across unseen indoor and outdoor environments. Behaviors such as waiting for doors to open, navigating around crowds, and avoiding glass walls emerge naturally from the learned prior. We will release the
dataset and trained models. Our website: https://egonav.weizhuowang.com
Read the full abstract ▾
All authors Weizhuo Wang, Yanjie Ze, C. Karen Liu, Monroe Kennedy III
Robotics
Sampling-based Task and Kinodynamic Motion Planning under Semantic Uncertainty
Qi Heng Ho, Zachary N. Sunberg and Morteza Lahijanian
This paper tackles the problem of integrated task and kinodynamic motion planning in uncertain environments. We consider a
robot with nonlinear dynamics tasked with a Linear Temporal Logic over finite traces ($\ltlf$) specification operating in a partially observable environment. Specifically, the uncertainty is in the semantic labels of the environment. We show how the problem can be modeled as a Partially Observable
Stochastic Hybrid System that captures the
robot dynamics, $\ltlf$ task, and uncertainty in the environment state variables. We propose an anytime
algorithm that takes advantage of the structure of the hybrid system, and combines the effectiveness of decision-making techniques and sampling-based motion planning. We prove the soundness and asymptotic optimality of the
algorithm. Results show the efficacy of our
algorithm in uncertain environments, and that it consistently outperforms baseline methods.
Read the full abstract ▾
Robotics
Behavioral Score Diffusion: Model-Free Trajectory Planning via Kernel-Based Score Estimation from Data
Shihao Li, Jiachen Li, Jiamin Xu et al. (+1 more)
Diffusion-based trajectory optimization has emerged as a powerful planning paradigm, but existing methods require either learned score networks trained on large
datasets or analytical dynamics models for score computation. We introduce Behavioral Score
Diffusion (BSD), a training-free and model-free trajectory planner that computes the
diffusion score function directly from a library of trajectory data via kernel-weighted estimation. At each denoising step, BSD retrieves relevant trajectories using a triple-kernel weighting scheme –
diffusion proximity, state context, and goal relevance – and computes a Nadaraya-Watson estimate of the denoised trajectory. The
diffusion noise schedule naturally controls kernel bandwidths, creating a multi-scale nonparametric regression: broad averaging of global behavioral patterns at high noise, fine-grained local interpolation at low noise. This coarse-to-fine structure handles nonlinear dynamics without linearization or parametric assumptions. Safety is preserved by applying shielded rollout on kernel-estimated state trajectories, identical to existing model-based approaches. We evaluate BSD on four robotic systems of increasing complexity (3D–6D state spaces) in a parking scenario. BSD with fixed bandwidth achieves 98.5% of the model-based baseline's average reward across systems while requiring no dynamics model, using only 1{,}000 pre-collected trajectories. BSD substantially outperforms nearest-neighbor
retrieval (18–63% improvement), confirming that the
diffusion denoising mechanism is essential for effective data-driven planning.
Read the full abstract ▾
All authors Shihao Li, Jiachen Li, Jiamin Xu, Dongmei Chen
Robotics · Cross-listed from math.OC
Implicit Primal-Dual Interior-Point Methods for Quadratic Programming
Jon Arrizabalaga and Zachary Manchester
This paper introduces a new method for solving quadratic programs using primal-dual interior-point methods. Instead of handling complementarity as an explicit equation in the Karush-Kuhn-Tucker (KKT) conditions, we ensure that complementarity is implicitly satisfied by construction. This is achieved by introducing an auxiliary variable and relating it to the duals and slacks via a retraction map. Specifically, we prove that the softplus function has favorable numerical properties compared to the commonly used exponential map. The resulting KKT system is guaranteed to be spectrally bounded, thereby eliminating the most pressing limitation of primal-dual methods: ill-conditioning near the solution. These attributes facilitate the solution of the underlying linear system, either by removing the need to compute factorizations at every iteration, enabling factorization-free approaches like indirect solvers, or allowing the solver to achieve high accuracy in low-precision arithmetic. Consequently, this novel perspective opens new opportunities for interior-point methods, especially for solving large-scale problems to high precision.
Read the full abstract ▾
Robotics
A Dual-Stream Transformer Architecture for Illumination-Invariant TIR-LiDAR Person Tracking
Yuki Minase and Kanji Tanaka
Robust person tracking is a critical capability for autonomous mobile
robots operating in diverse and unpredictable environments. While RGB-D tracking has shown high precision, its performance severely degrades under challenging illumination conditions, such as total darkness or intense backlighting. To achieve all-weather robustness, this paper proposes a novel Thermal-Infrared and Depth (TIR-D) tracking architecture that leverages the standard sensor suite of SLAM-capable
robots, namely
LiDAR and TIR cameras. A major challenge in TIR-D tracking is the scarcity of annotated multi-modal
datasets. To address this, we introduce a sequential knowledge transfer strategy that evolves structural priors from a large-scale thermal-trained model into the TIR-D domain. By employing a differential learning rate strategy – referred to as “Fine-grained Differential Learning Rate Strategy” – we effectively preserve pre-trained feature extraction capabilities while enabling rapid adaptation to
geometric depth cues. Experimental results demonstrate that our proposed TIR-D tracker achieves superior performance, with an Average Overlap (AO) of 0.700 and a Success Rate (SR) of 58.7%, significantly outperforming conventional RGB-transfer and single-modality baselines. Our approach provides a practical and resource-efficient solution for robust human-following in all-weather robotics applications.
Read the full abstract ▾
Robotics
Go Big or Go Home: Simulating Mobbing Behavior with Braitenbergian Robots
Elaheh Sanoubari
We used the Webots robotics simulation platform to simulate a dyadic avoiding and mobbing predator behavior in a group of Braitenbergian
robots. Mobbing is an antipredator adaptation used by some animals in which the individuals cooperatively attack or harass a predator to protect themselves. One way of coordinating a mobbing attack is using mobbing calls to summon other individuals of the mobbing species. We imitated this mechanism and simulated Braitenbergian
robots that use mobbing calls when they face a light source (representing an inanimate predator) and mob it if they can summon allies, otherwise, they escape from it. We explore the effects of range of mobbing call (infinite range, mid-range and low-range) and the size of the
robot group (ten
robots vs three) on the overall success of mobbing. Our results suggest that both variables have significant impacts. This work has implications for simulations of action selection in artificial life and designing control architectures for autonomous
agents.
Read the full abstract ▾
Robotics
Real Time Local Wind Inference for Robust Autonomous Navigation
Spencer Folk
This thesis presents a solution that enables aerial
robots to reason about surrounding wind flow fields in real time using on board sensors and embedded flight hardware. The core novelty of this research is the fusion of range measurements with sparse in situ wind measurements to predict surrounding flow fields. We aim to address two fundamental questions: first, the sufficiency of topographical data for accurate wind prediction in dense urban environments; and second, the utility of learned wind models for motion planning with an emphasis on energy efficiency and obstacle avoidance. Drawing on tools from deep learning, fluid mechanics, and optimal control, we establish a framework for local wind prediction using navigational
LiDAR, and then incorporate local wind model priors into a receding-horizon optimal controller to study how local wind knowledge affects energy use and robustness during autonomous
navigation. Through simulated demonstrations in diverse urban wind scenarios we evaluate the predictive capabilities of the wind predictor, and quantify improvements to autonomous urban
navigation in terms of crash rates and energy consumption when local wind information is integrated into the motion planning. Sub-scale free flight experiments in an open-air wind tunnel demonstrate that these
algorithms can run in real time on an embedded flight computer with sufficient bandwidth for stable control of a small aerial
robot. Philosophically, this thesis contributes a new paradigm for localized wind inference and motion planning in unknown windy environments. By enabling
robots to rapidly assess local wind conditions without prior environmental knowledge, this research accelerates the introduction of aerial
robots into increasingly challenging environments.
Read the full abstract ▾