Peer Revenue Play credits. Real papers.

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Robotics

cs.RO Watch Robotics

Sunday 26 April

Robotics

LiDAR for Rehabilitation: A Comprehensive Survey of Applications, AI Techniques, and Future Directions

Soumia Siyoucef, Najmeddine Dhieb, Hakim Ghazzai et al. (+3 more)

Rehabilitation aims to help patients with limited mobility regain their physical abilities through targeted movements, exercises, stimulation, and other therapeutic methods. Recent advances in technology have introduced sensor-based systems into rehabilitation and clinical practices, enabling real-time monitoring and providing accurate feedback on movement accuracy. Among these sensors, LiDAR has demonstrated strong potential, offering key advantages over conventional techniques such as camera-based systems, which raise privacy concerns, and wearable sensors, which can be uncomfortable and prone to errors. In this work, we review the applications of LiDAR in rehabilitation, post-injury care, and hospital environments, focusing on studies published between 2019 and 2025. Studies across several areas have been explored: 3D body scanning and gait analysis with standalone LiDAR, LiDAR mounted on robotic systems for rehabilitation, real-time monitoring and environment scanning for safe navigation, and activity and position recognition. We also analyze processing techniques, particularly learning-based approaches, and support the discussion with statistical analysis, highlighting trends, gaps, and future research opportunities. To the best of our knowledge, this is the first comprehensive survey dedicated to LiDAR for rehabilitation applications, providing an overview of current methods, AI-based processing techniques, and open challenges.
Read the full abstract

All authors Soumia Siyoucef, Najmeddine Dhieb, Hakim Ghazzai, Eleonora Guanziroli, Franco Molteni, Gianluca Setti

Robotics

Cooptimizing Safety and Performance Using Safety Value-Constrained Model Predictive Control

Hao Wang, Nam Nguyen, Armand Jordana et al. (+2 more)

Autonomous systems are increasingly deployed in real-world environments, where they must achieve high performance while maintaining safety under state and input constraints. Although Model Predictive Control (MPC) provides a principled framework for constrained optimal control, guaranteeing safety beyond its finite planning horizon remains a fundamental challenge. In this work, we augment MPC with a safety value function-based terminal constraint that enforces membership in a control-invariant safe set at the end of each planning horizon. This formulation enables real-time synthesis of trajectories that are both high-performing and provably safe. We show that, under an exact safety value function and a feasible initialization, the proposed MPC scheme is recursively feasible, thereby ensuring persistent safety. In contrast to traditional terminal set constructions that rely on local linearizations or conservative approximations, our approach incorporates a reachability-based safety value function for terminal constraints, yielding less conservative and more expressive safety guarantees. We validate the proposed framework through simulation and hardware experiments on a Flexiv Rizon 10s manipulator. Results demonstrate improved constraint satisfaction and robustness compared to standard state-constrained MPC and reactive safety filtering, while maintaining competitive task performance. The full implementation and experiments are available on the project website.
Read the full abstract

All authors Hao Wang, Nam Nguyen, Armand Jordana, Ludovic Righetti, Somil Bansal

Robotics

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

Qi Li, Bo Yin, Weiqi Huang et al. (+6 more)

Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence. This shift raises a new class of safety challenges, stemming from the embodied nature of VLA systems, including irreversible physical consequences, a multimodal attack surface across vision, language, and state, real-time latency constraints on defense, error propagation over long-horizon trajectories, and vulnerabilities in the data supply chain. Yet the literature remains fragmented across robotic learning, adversarial machine learning, AI alignment, and autonomous systems safety. This survey provides a unified and up-to-date overview of safety in Vision-Language-Action models. We organize the field along two parallel timing axes, attack timing (training-time vs. inference-time and defense timing (training-time vs. inference-time, linking each class of threat to the stage at which it can be mitigated. We first define the scope of VLA safety, distinguishing it from text-only LLM safety and classical robotic safety, and review the foundations of VLA models, including architectures, training paradigms, and inference mechanisms. We then examine the literature through four lenses: Attacks, Defenses, Evaluation, and Deployment. We survey training-time threats such as data poisoning and backdoors, as well as inference-time attacks including adversarial patches, cross-modal perturbations, semantic jailbreaks, and freezing attacks. We review training-time and runtime defenses, analyze existing benchmarks and metrics, and discuss safety challenges across six deployment domains. Finally, we highlight key open problems, including certified robustness for embodied trajectories, physically realizable defenses, safety-aware training, unified runtime safety architectures, and standardized evaluation.
Read the full abstract

All authors Qi Li, Bo Yin, Weiqi Huang, Ruhao Liu, Bojun Zou, Runpeng Yu, Jingwen Ye, Weihao Yu, Xinchao Wang

Robotics

Unleashing the Agility of Wheeled-Legged Robots for High-Dynamic Reflexive Obstacle Evasion

Yongen Zhao, Zihao Xu, Wenzhi Lu et al. (+4 more)

Wheeled-legged robots combine the efficiency of rolling with the adaptability of legged locomotion, offering unique agility for dynamic environments. However, enabling rapid reflexive evasion remains challenging due to the coexistence of heterogeneous wheel-leg dynamics, hybrid locomotion modes, and non-holonomic constraints. In this work, we investigate how wheeled-legged robots can exploit their hybrid morphology for high-dynamic obstacle avoidance. We propose AWARE, a hierarchical reinforcement learning framework that decomposes avoidance into navigation-avoidance and reflexive-evasion regimes coordinated by a threat-conditioned high-level policy. By learning specialized low-level experts, AWARE autonomously discovers distinct rolling-, stepping-, and hybrid-dominated evasive behaviors, including forward lunges and lateral dodges. Simulation experiments across different reaction times and approach directions, together with real-robot evaluations on the M20 platform, demonstrate improved evasion capability and effective online transition between locomotion regimes. These results highlight the potential of exploiting hybrid wheel-leg actuation for agile and reactive mobility in dynamic environments. Paper homepage: https://aware-ral-2026.github.io/.
Read the full abstract

All authors Yongen Zhao, Zihao Xu, Wenzhi Lu, Zhen Chu, Kailin Lyu, Hao Sun, Ce Hao

Robotics

QuietWalk: Physics-Informed Reinforcement Learning for Ground Reaction Force-Aware Humanoid Locomotion Under Diverse Footwear

Hanze Hu, Luying Feng, Silu Chen et al. (+6 more)

Humanoid robots operating in human-centered environments (e.g., homes, hospitals, and offices) must mitigate foot–ground impact transients, as impact-induced vibration and noise degrade user experience and repeated impacts accelerate hardware wear. However, existing low-noise locomotion training often relies on kinematic proxy objectives or fragile force sensors, and footwear-induced changes in contact dynamics introduce distribution shifts that hinder policy generalization.We present QuietWalk, a physics-informed reinforcement learning framework for ground-reaction-force-aware humanoid locomotion under diverse footwear conditions. QuietWalk employs an inverse-dynamics-constrained physics-informed neural network (PINN) to estimate per-foot vertical ground reaction forces (GRFs) from proprioceptive signals, and integrates the frozen predictor into the RL training loop to penalize predicted impact forces without requiring force sensors at deployment.On a held-out real-robot dataset, enforcing inverse-dynamics consistency reduces vertical GRF prediction errors by 82%-86% compared with a purely supervised predictor and improves the coefficient of determination from 0.39/0.67 to 0.99/0.99 for the left/right feet. On hardware at 1.2 m/s (barefoot; averaged over four floor materials), QuietWalk reduces mean A-weighted noise level by 7.17 dB and peak noise level by 4.98 dB under a consistent recording setup. Cross-footwear experiments (barefoot, skate shoes, athletic sneakers, and high heels) across multiple surfaces further demonstrate robust adaptation to footwear-induced contact variations.
Read the full abstract

All authors Hanze Hu, Luying Feng, Silu Chen, Tianjiang Zheng, Dexin Jiang, Wei Chen, Chi Zhang, Guilin Yang, Yaochu Jin

Robotics

Real-Time Non-Contact Force Compensation for Wrist-Mounted Force/Torque Sensors in Haptic-Enabled Robotic Surgery Training

Walid Shaker and Mustafa Suphi Erden

Haptic feedback has been a long-missed feature in robotic-assisted surgery, one that would allow surgeons to perceive tissue properties and apply controlled forces during delicate procedures. Although commercial robotic systems have begun to integrate haptic technologies, their high costs limit accessibility for training and research purposes. To address this gap, we extend our previously developed low-cost robotic surgery training setup, RoboScope, by incorporating a wrist-mounted force/torque (F/T) sensor for haptic feedback training. Wrist-mounted sensing avoids many challenges associated with tip-mounted sensors but introduces additional non-contact forces, such as gravity, sensor bias, installation offsets, and associated torques, which compromise measurement accuracy. In this paper, we propose a robust real-time compensation method based on recursive least squares (RLS). This method eliminates the need for dataset collection and frequent recalibration while adapting to changing operating conditions. Experimental validation demonstrates that the proposed approach achieves over 95% error reduction in non-contact force compensation and more than 91% in non-contact torque compensation, significantly outperforming existing methods. These results highlight the potential of our approach for providing reliable haptic feedback in robotic surgery training and research.
Read the full abstract

Robotics

Decentralized Heterogeneous Multi-Robot Collaborative Exploration for Indoor and Outdoor 3D Environments

Yuxiang Li, Kun Chen, Jiancheng Wang et al. (+3 more)

Heterogeneous multi-robot systems feature significant adaptability for complex environments. However, effective collaboration that fully exploits the robots' potential remains a core challenge. This paper proposes a decentralized collaborative framework for heterogeneous multi-robot systems to autonomously explore indoor and outdoor 3D environments. First, a basic perception map that integrates terrain and observation metrics is designed. Improved supervoxel segmentation is developed to simplify the map structure and form a high-level representation that supports lightweight communication. Second, the traversal and observation capabilities of heterogeneous robots are modeled to evaluate the requirements of task views derived from incomplete supervoxels. These task views are grouped by requirements and clustered to streamline assignment. Subsequently, the view-cluster assignment is formulated as a heterogeneous multi-depot multi-traveling salesman problem (HMDMTSP) that incorporates constraints between view-cluster requirements and robot capabilities. An improved genetic algorithm is developed to efficiently solve this problem while ensuring global consistency. Based on the assignments, redundant views within clusters are eliminated to refine exploration routes. Finally, conflicts between robots' motion paths are resolved. Simulations and field experiments in cluttered indoor and outdoor environments demonstrate that our approach effectively coordinates exploration tasks among heterogeneous robots, achieving superior exploration efficiency and communication savings compared to state-of-the-art approaches.
Read the full abstract

All authors Yuxiang Li, Kun Chen, Jiancheng Wang, Shihao Fang, Haoyao Chen, Yunhui Liu

Robotics

Safe Navigation in Unknown and Cluttered Environments via Direction-Aware Convex Free-Region Generation

Zhicheng Song, Yongjian Li, Kai Chen et al. (+3 more)

Convex free regions provide a structured and optimization-friendly representation of collision-free space for robot navigation in unknown and cluttered environments. However, existing methods typically enlarge local collision-free regions mainly according to surrounding obstacle geometry. In cluttered environments, such strategies may fail to generate regions that both accommodate robot geometry and preserve traversable extension along candidate motion directions, thereby limiting downstream traversal, especially in narrow passages. Even when such a region is available, safe motion generation remains challenging, because safety checking at discretized trajectory samples does not guarantee continuously collision-free motion when robot geometry is modeled explicitly. To address these issues, we propose a navigation framework that jointly incorporates candidate motion directions and robot geometry into convex free-region generation, and achieves continuously collision-free motion through continuous-safe trajectory generation. Within each region, the framework performs geometry-aware target pose selection and trajectory generation, together with Lipschitz-based continuous safety certification and local refinement. The resulting free regions and candidate motions are maintained in a region-based graph to support incremental planning. Quantitative results in cluttered 2D navigation scenarios show that the proposed method generates free regions better aligned with downstream traversal and enables reliable collision-free navigation, while additional 3D and real-world experiments on a quadrupedal robot and a UAV demonstrate the extensibility and practical applicability of the framework. The open-source project can be found at https://github.com/ZhichengSong6/FRGraph.
Read the full abstract

All authors Zhicheng Song, Yongjian Li, Kai Chen, Yulin Li, Fan Shi, Jun Ma

Robotics

Move-Then-Operate: Behavioral Phasing for Human-Like Robotic Manipulation

Haoming Xu, Lei Lei, Jie Gu et al. (+3 more)

We present Move-Then-Operate, a Vision language action framework that explicitly decouples robotic manipulation into two distinct behavioral phases: coarse relocation (move) and contact-critical interaction (operate). Unlike monolithic policies that conflate these heterogeneous regimes, our architecture employs a dual-expert policy routed by a learnable phase selector, introducing a structural inductive bias that isolates phase-specific dynamics. Phase labels are automatically generated via an MLLM-based pipeline conditioned on lightweight contextual cues such as end-effector velocity and subtask decomposition to ensure alignment with human motor patterns. Evaluated on the RoboTwin2 benchmark, our method achieves an average success rate of $68.9\%$, outperforming the monolithic $\pi_0$ baseline by $24\%$. It matches or exceeds models trained on $10\times$ more data and reaches peak performance in $40\%$ fewer training steps, demonstrating that architectural disentanglement of move and operate phases is a highly effective and efficient strategy for mastering high-precision manipulation. The code is available at: https://github.com/healenrens/Move-then-Operate
Read the full abstract

All authors Haoming Xu, Lei Lei, Jie Gu, Chu Tang, Jingmin Chen, Ruiqi Wang

Robotics

Tube Diffusion Policy: Reactive Visual-Tactile Policy Learning for Contact-rich Manipulation

Teng Xue, Alberto Rigo, Bingjian Huang et al. (+4 more)

Contact-rich manipulation is central to many everyday human activities, requiring continuous adaptation to contact uncertainty and external disturbances through multi-modal perception, particularly vision and tactile feedback. While imitation learning has shown strong potential for learning complex manipulation behaviors, most existing approaches rely on action chunking, which fundamentally limits their ability to react to unforeseen observations during execution. This limitation becomes especially critical in contact-rich scenarios, where physical uncertainty and high-frequency tactile feedback demand rapid, reactive control. To address this challenge, we propose Tube Diffusion Policy (TDP), a novel reactive visual-tactile policy learning framework that bridges diffusion-based imitation learning with tube-based feedback control. By leveraging the expressive power of generative models, TDP learns an observation-conditioned feedback flow around nominal action chunks, forming an action tube that enables fast and adaptive reactions during execution. We evaluate TDP on the widely used Push-T benchmark and three additional challenging visual-tactile dexterous manipulation tasks. Across all benchmarks, TDP consistently outperforms state-of-the-art imitation learning baselines. Two real-world experiments further validate its robust reactivity under contact uncertainty and external disturbances. Moreover, the step-wise correction mechanism enabled by action tube significantly reduces the required denoising steps, making TDP well suited for real-time, high-frequency feedback control in contact-rich manipulation.
Read the full abstract

All authors Teng Xue, Alberto Rigo, Bingjian Huang, Jiayi Shen, Zhengtong Xu, Nick Colonnese, Amirhossein H. Memar

Robotics · Cross-listed from cs.CV

Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation

Simone Mosco, Daniel Fusaro and Alberto Pretto

Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previously unseen objects is crucial in real-world environments, as done in Anomaly Segmentation. However, research in the 3D field remains limited, with most existing approaches applying post-processing techniques from 2D vision. To cover this lack, we propose a new efficient approach that directly operates in the feature space, modeling the feature distribution of inlier classes to constrain anomalous samples. Moreover, the only publicly available 3D LiDAR anomaly segmentation dataset contains simple scenarios, with few anomaly instances, and exhibits a severe domain gap due to its sensor resolution. To bridge this gap, we introduce a set of mixed real-synthetic datasets for 3D LiDAR anomaly segmentation, built upon established semantic segmentation benchmarks, with multiple out-of-distribution objects and diverse, complex environments. Extensive experiments demonstrate that our approach achieves state-of-the-art and competitive results on the existing real-world dataset and the newly introduced mixed datasets, respectively, validating the effectiveness of our method and the utility of the proposed datasets. Code and datasets are available at https://simom0.github.io/lido-page/.
Read the full abstract

Robotics

PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement

Tianyidan Xie, Peiyu Wang, Hu Jiaxin et al. (+9 more)

Translating natural-language descriptions of physical phenomena into executable simulation code requires both programming expertise and physical reasoning. Current large language models (LLMs) lack this combination: they frequently produce code that runs but simulates the wrong physics. We introduce PhysCodeBench, the first benchmark for this task, with 1,200 expert-validated examples spanning four physical domains. Its evaluation suite, PhysCodeEval, goes beyond executability and visual fidelity to measure physical correctness directly from the engine state via conservation-law residuals and expert-written assertions, and supports cross-engine evaluation to disentangle physics reasoning from API fluency. As a reference method, we propose the Self-Corrective Multi-Agent Refinement Framework (SMRF), which decouples physics-aware error correction from code generation through specialized agents. This design is motivated by our finding that targeted correction, rather than generic iterative refinement, is the key driver of physical accuracy. SMRF nearly triples the physical-assertion pass rate of the best proprietary baseline (70.6% vs.\ 23.8%) and retains its advantage under cross-engine transfer.
Read the full abstract

All authors Tianyidan Xie, Peiyu Wang, Hu Jiaxin, Yuyi Qian, Yuxuan Wang, Shenyi Wang, Rui Ma, Yanlun Peng, Lanjun Wang, Ying Tai, Jian Yang, Zili Yi

Robotics

EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks

Yihang Li, Xuelong Wei, Jingzhou Luo et al. (+26 more)

The advancement of robot learning is currently hindered by the scarcity of large-scale, high-quality datasets. While established data collection methods such as teleoperation and universal manipulation interfaces dominate current datasets, they suffer from inherent limitations in scalability and real-world deployability. Human egocentric video collection, by contrast, has emerged as a promising approach to enable scalable, natural and in-the-wild data collection. As such, we present EgoLive, a large-scale, high-quality egocentric dataset designed explicitly for robot manipulation learning. EgoLive establishes three distinctive technical advantages over existing egocentric datasets: first, it represents the largest open-source annotated egocentric dataset focused on real-world task-oriented human routines to date; second, it delivers leading data quality via a customized head-mounted capture device and comprehensive high-precision multi-modal annotations; third, all data is collected exclusively in unconstrained real-world scenarios and encompasses vertical field human working data, including home service, retail, and other practical work scenarios, providing superior diversity and ecological validity. With the introduction of EgoLive, we aim to provide the research community with a scalable, high-quality dataset that accelerates breakthroughs in generalizable robotic models and facilitates the real-world deployment of robot systems.
Read the full abstract

All authors Yihang Li, Xuelong Wei, Jingzhou Luo, Yingjing Xiao, Yibo Bai, Guangyuan Zhou, Teng Zou, Chenguang Gui, Jiajun Wen, He Zhang, Kangliang Chen, Xing Pan, Shuaiyan Liu, Daming Wang, Tao An, Jiayi Li, Shibo Jin, Wanwan Zhang, Tianyu Wang, Boren Wei, Zhixuan Huang, Fangsheng Liu, Ruodai Li, Hui Zhang, Anson Li, Yicheng Gong, Peng Cao, Jiaming Liang, Liang Lin

Robotics

Large Language Model based Interactive Decision-Making for Autonomous Driving

Xinwei Dong, Jiyang Li, Jiabin Xie et al. (+5 more)

In high-conflict mixed-traffic scenarios involving human-driven and autonomous vehicles, most existing autonomous driving systems default to overly conservative behaviors, lack proactive interaction, and consequently suffer from limited public acceptance. To mitigate intent misunderstandings and decision failures, we present a Large Language Model based interactive decision-making framework that augments scene understanding and intent-aware interaction to jointly improve safety and efficiency. The approach uses Object-Process Methodology to semantically model complex multi-vehicle scenes, abstracting low-level perceptual data into objects, processes, and relations, thereby streamlining reasoning over latent causal structure. Building on this representation, the Large Language Model parses both explicit and implicit intents of surrounding agents and, under jointly enforced safety and efficiency constraints, selects candidate maneuvers. We further generate perturbed trajectory candidates via Monte Carlo sampling and evaluate them to obtain an optimized executable trajectory. To foster transparency and coordination with nearby road users, the final decision is translated by the Large Language Model into concise natural-language messages and broadcast through an external Human-Machine Interface, completing a closed loop from scene understanding to action to language. Experiments in a cluster driving simulator demonstrate that the proposed method outperforms traditional baselines across safety, comfort, and efficiency metrics, while a Turing-test-style evaluation indicates a high degree of human-likeness in decision making. Besides, these results suggest that coupling semantic scene abstraction with Large Language Model mediated intent reasoning and language-based eHMI communication offers a practical pathway toward interactive, trustworthy autonomous driving in dense mixed traffic.
Read the full abstract

All authors Xinwei Dong, Jiyang Li, Jiabin Xie, Yang Yi, Tianshang Jia, Shiyu Fang, Ye Tian, Peng Hang

Saturday 25 April

Robotics · Cross-listed from cs.HC

Otherness as a Quality in Designing Expressive Robotic Touch

Ran Zhou, Laurens Boer, Daniel Leithinger et al. (+1 more)

Haptic technologies have advanced rapidly, yet exploration of robotic touch remains dominated by replicating realistic environmental cues or hand gestures, which narrows the design space and risks social resistance. This paper argues for alternatives: grounded in the notion of "otherness" from human-robot interaction (HRI), we propose treating robotic touch's inherent otherness as a design quality. Instead of being a limitation in pursuing realism, otherness can be embraced to elicit ambiguity and provoke alternative interpretations, fostering expressive and evocative robotic touch design. To develop this perspective, we analyze inspirational art and design precedents and four design research cases through a reflective Research through Design (RtD) approach. Through this analysis, we articulate a set of design languages structured around why otherness matters for touch meaning-making, how it can be shaped through design strategies, and where it can be embedded within robotic touch systems. We conclude by reflecting on the tensions and risks involved in designing robotic touch with otherness in mind.
Read the full abstract

All authors Ran Zhou, Laurens Boer, Daniel Leithinger, Madeline Balaam

Robotics · Cross-listed from cs.CV

Keypoint-based Dynamic Object 6-DoF Pose Tracking via Event Camera

Zhe Wang, Qijin Song, Zihao Li et al. (+2 more)

Accurate 6-DoF pose estimation of objects is critical for robots to perform precise manipulation tasks. However, for dynamic object pose estimation, conventional camera-based approaches face several major challenges, such as motion blur, sensor noise, and low-light limitation. To address these issues, we employ event cameras, whose high dynamic range and low latency offer a promising solution. Furthermore, we propose a keypoint-based detection and tracking approach for dynamic object pose estimation. Firstly, a keypoint detection network is constructed to extract keypoints from the time surface generated by the event stream. Subsequently, the polarity and spatial coordinates of the events are leveraged, and the event density in the vicinity of each keypoint is utilized to achieve continuous keypoint tracking. Finally, a hash mapping is established between the 2D keypoints and the 3D model keypoints, and the EPnP algorithm is employed to estimate the 6-DoF pose. Experimental results demonstrate that, whether in simulated or real event environments, the proposed method outperforms the event-based state-of-the-art methods in terms of both accuracy and robustness.
Read the full abstract

All authors Zhe Wang, Qijin Song, Zihao Li, Jingyu Xiao, Weibang Bai

Robotics

Learning from Demonstration with Failure Awareness for Safe Robot Navigation

Xianghui Wang, Siwei Cheng, Shanze Wang et al. (+3 more)

Learning from demonstration is widely used for robot navigation, yet it suffers from a fundamental limitation: demonstrations consist predominantly of successful behaviors and provide limited coverage of unsafe states. This limitation leads to poor safety when the robot encounters scenarios beyond the demonstration distribution. Failure experiences, such as collisions, contain essential information about unsafe regions, but remain underutilized. The key difficulty lies in the fact that failure data do not provide valid guidance for action imitation, and their naive incorporation into policy learning often degrades performance. We address this challenge by proposing a failure-aware learning framework that explicitly decouples the roles of success and failure data. In this framework, failure experiences are used to shape value estimation in hazardous regions, while policy learning is restricted to successful demonstrations. This separation enables the effective use of failure data without corrupting policy behavior. We implement this design within an offline reinforcement learning (RL) setting and evaluate it in both simulation and real-world environments. The results show that our framework consistently reduces collision rates while preserving the task success rate, and demonstrate strong generalization across different environments and robot platforms.
Read the full abstract

All authors Xianghui Wang, Siwei Cheng, Shanze Wang, Xinming Zhang, Dan Zhang, Wei Zhang

Robotics

An Efficient Beam Search Algorithm for Active Perception in Mobile Robotics

Kaixian Qu, Han Wang, Victor Klemm et al. (+2 more)

Active perception is a fundamental problem in autonomous robotics in which the robot must decide where to move and what to sense in order to obtain the most informative observations for accomplishing its mission. Existing approaches either solve a computationally expensive traveling salesman problem over heuristically selected informative nodes, or adopt a more efficient but overly constrained shortest path tree formulation. To address these limitations, we explore beam search algorithms as scalable alternatives. While the standard beam search provides scalability by preserving the top-B paths at each depth level, it is prone to local optima and exhibits parameter sensitivity. Our first contribution is a node-wise beam search (NBS) algorithm, which maintains top-B candidates per node to enable more effective exploration of the solution space. Systematic benchmarking on graphs shows that NBS consistently outperforms other baselines and maintains strong performance even at low beam widths. As a second contribution, we integrate the concept of frontiers into the path selection criterion, introducing the expected gain metric, which better balances exploration and exploitation compared to existing alternatives. Our third contribution proposes the rapidly-exploring random annulus graph (RRAG), a novel graph construction method that preserves full orientation sampling and ensures connectivity in cluttered environments through a fallback local sampling-based planner. Extensive experiments demonstrate that NBS combined with RRAG achieves the highest performance across all three representative active perception tasks, outperforming state-of-the-art algorithms by at least 20% in one or more tasks. We further validate the approach on real robotic platforms in different scenarios.
Read the full abstract

All authors Kaixian Qu, Han Wang, Victor Klemm, Cesar Cadena, Marco Hutter

Robotics

Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models

Jimin Lee, Huiwon Jang, Myungkyu Koo et al. (+2 more)

Humans understand and interact with the real world by relying on diverse physical feedback beyond visual perception. Motivated by this, recent approaches attempt to incorporate physical sensory signals into Vision-Language-Action models (VLAs). However, they typically focus on a single type of physical signal, failing to capture the heterogeneous and complementary nature of real-world interactions. In this paper, we propose MoSS, a modular sensory stream framework that adapts VLAs to leverage multiple sensory signals for action prediction. Specifically, we introduce decoupled modality streams that integrate heterogeneous physical signals into the action stream via joint cross-modal self-attention. To enable stable incorporation of new modalities, we adopt a two-stage training scheme that freezes pretrained VLA parameters in the early stage. Furthermore, to better capture contact interaction dynamics, we incorporate an auxiliary task that predicts future physical signals. Through extensive real-world experiments, we demonstrate that MoSS successfully augments VLAs to leverage diverse physical signals (i.e., tactile, force, and torque), integrating multiple signals to achieve synergistic performance gains.
Read the full abstract

All authors Jimin Lee, Huiwon Jang, Myungkyu Koo, Jungwoo Park, Jinwoo Shin

Robotics

BridgeACT: Bridging Human Demonstrations to Robot Actions via Unified Tool-Target Affordances

Yifan Han, Jianxiang Liu, Haoyu Zhang et al. (+3 more)

Learning robot manipulation from human videos is appealing due to the scale and diversity of human demonstrations, but transferring such demonstrations to executable robot behavior remains challenging. Prior work either relies on robot data for downstream adaptation or learns affordance representations that remain at the perception level and do not directly support real-world execution. We present BridgeACT, an affordance-driven framework that learns robotic manipulation directly from human videos without requiring any robot demonstration data. Our key idea is to model affordance as an embodiment-agnostic intermediate representation that bridges human demonstrations and robot actions. BridgeACT decomposes manipulation into two complementary problems: where to grasp and how to move. To this end, BridgeACT first grounds task-relevant affordance regions in the current scene, and then predicts task-conditioned 3D motion affordances from human demonstrations. The resulting affordances are mapped to robot actions through a grasping module and a lightweight closed-loop motion controller, enabling direct deployment on real robots. In addition, we represent complex manipulation tasks as compositions of affordance operations, which allows a unified treatment of diverse tasks and object-to-object interactions. Experiments on real-world manipulation tasks show that BridgeACT outperforms prior baselines and generalizes to unseen objects, scenes, and viewpoints.
Read the full abstract

All authors Yifan Han, Jianxiang Liu, Haoyu Zhang, Yuqi Gu, Yunhan Guo, Wenzhao Lian

Robotics

Cooperative Informative Sensing for Monitoring Dynamic Indoor Environments via Multi-Agent Reinforcement Learning

Kanghoon Lee, Matthew M. Sato, Jinnyeong Yang et al. (+7 more)

Monitoring human activity in indoor environments is important for applications such as facility management, safety assessment, and space utilization analysis. While mobile robot teams offer the potential to actively improve observation quality, existing multi-robot monitoring and active perception approaches typically rely on coverage or visitation based objectives that are weakly aligned with the accuracy requirements of human-centric monitoring tasks. In this work, we formulate cooperative active observation as a decentralized control problem in which multiple robots adjust their motion to directly optimize monitoring accuracy under partial observability. We propose a learning-based framework for cooperative policies from decentralized observations using multi-agent reinforcement learning (MARL), supported by an architecture that handles variable numbers of humans and temporal dependencies. Simulation results across diverse indoor environments and monitoring tasks show that the proposed approach consistently outperforms classical coverage, persistent monitoring, and learning-free multi-robot baselines, while remaining robust to changes in the number of observed humans.
Read the full abstract

All authors Kanghoon Lee, Matthew M. Sato, Jinnyeong Yang, Seungro Lee, Sujin Lee, Jiachen Li, Kuk-Jin Yoon, Jinkyoo Park, Kincho H. Law, Yoonjin Yoon

Robotics

Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training

Suning Huang, Jiaqi Shao, Ke Wang et al. (+5 more)

Have you ever post-trained a generalist vision-language-action (VLA) policy on a small demonstration dataset, only to find that it stops responding to new instructions and is limited to behaviors observed during post-training? We identify this phenomenon as lock-in: after low-data, supervised fine-tuning (SFT), the policy becomes overly specialized to the post-training data and fails to generalize to novel instructions, manifesting as concept lock-in (fixation on training objects/attributes) and spatial lock-in (fixation on training spatial targets). Many existing remedies introduce additional supervision signals, such as those derived from foundation models or auxiliary objectives, or rely on augmented datasets to recover generalization. In this paper, we show that the policy's internal pre-trained knowledge is sufficient: DeLock mitigates lock-in by preserving visual grounding during post-training and applying test-time contrastive prompt guidance to steer the policy's denoising dynamics according to novel instructions. Across eight simulation and real-world evaluations, DeLock consistently outperforms strong baselines and matches or exceeds the performance of a state-of-the-art generalist policy post-trained with substantially more curated demonstrations.
Read the full abstract

All authors Suning Huang, Jiaqi Shao, Ke Wang, Qianzhong Chen, Jiankai Sun, Yanjiang Guo, Mac Schwager, Jeannette Bohg

Friday 24 April

Robotics

A Lightweight Toggleable Adhesion Prototype for Multirotor UAV Landing on Tilting Platforms

Teighin Nordholt and Melissa Greeff

Autonomous multirotor landings on uncrewed surface vessels (USVs) are critical for persistent maritime operations but remain challenging due to wave-induced tilt, wind disturbances, and limited landing area. Many existing approaches exhibit small pose tolerance for reliable landing. This paper presents a lightweight toggleable adhesion mechanism to improve landing reliability. The system uses a motor-driven corkscrew that engages hook-and-loop material on the landing surface, enabling active adhesion during landing and controlled release during takeoff. We evaluate a prototype using a modified Crazyflie 2.0 and a custom tilting platform at fixed angles representative of extreme wave conditions. Using only a simple vertical PID controller, the proposed approach increases landing success from an average of 40% (baseline) to 80% across platform tilts up to 43 degrees using appropriately selected actuation settings.
Read the full abstract

Robotics · Cross-listed from cs.LG

RL Token: Bootstrapping Online RL with Vision-Language-Action Models

Charles Xu, Jost Tobias Springenberg, Michael Equi et al. (+4 more)

Vision-language-action (VLA) models can learn to perform diverse manipulation skills "out of the box," but achieving the precision and speed that real-world tasks demand requires further fine-tuning – for example, via reinforcement learning (RL). We introduce a lightweight method that enables sample-efficient online RL fine-tuning of pretrained VLAs using just a few hours of real-world practice. We (1) adapt the VLA to expose an "RL token," a compact readout representation that preserves task-relevant pretrained knowledge while serving as an efficient interface for online RL, and (2) train a small actor-critic head on this RL token to refine the actions, while anchoring the learned policy to the VLA. Online RL with the RL token (RLT) makes it possible to fine-tune even large VLAs with RL quickly and efficiently. Across four real-robot tasks (screw installation, zip tie fastening, charger insertion, and Ethernet insertion), RLT improves the speed on the hardest part of the task by up to 3x and raises success rates significantly within minutes to a few hours of practice. It can even surpass the speed of human teleoperation on some of the tasks.
Read the full abstract

All authors Charles Xu, Jost Tobias Springenberg, Michael Equi, Ali Amin, Adnan Esmail, Sergey Levine, Liyiming Ke

Robotics

Control Barrier Functions Solved with Hierarchical Quadratic Programming for Safe Physical Human-Robot Interaction

Rui Luo, Jonas Mariager Jakobsen, Wesley Roozing et al. (+2 more)

Physical human-robot interaction offers the potential to leverage human intelligence and robot physical capabilities to enable a range of exciting applications, e.g., collaborative robots for rehabilitation. Safety is critical for the successful deployment of this kind of robotic system. In recent years, Control Barrier Function (CBF) has emerged as an effective approach to enforce safety guarantees, which has been widely applied in various applications, from adaptive cruise control to navigation of legged robots. CBFs can be solved in a Quadratic Programming (QP) problem, which can include many CBF-formulated tasks. To manage a large number of safety tasks, a hierarchical CBF has been used to allow hierarchical relaxation of safety tasks to ensure the feasibility of a solution in the presence of conflicting tasks. In this work, we propose to use a CBF-based Hierarchical Quadratic Programming (HQP) framework in physical human-robot interaction to allow us to design both performance tasks (e.g., preserve the desired behavior at the human-robot interaction point) and safety tasks at any level of a hierarchy to balance the safety and the performance in a more flexible way. Extensive experiments were carried out on a real redundant robot to validate the effectiveness, flexibility, and generality of this approach.
Read the full abstract

All authors Rui Luo, Jonas Mariager Jakobsen, Wesley Roozing, Federico Califano, Cheng Fang

Robotics

Equivariant Filter for Radar-Inertial Odometry

Giulio Delama, Jan Michalczyk, Morten Nissov et al. (+4 more)

Radar-Inertial Odometry (RIO) based on the Extended Kalman Filter (EKF) relies on accurate extrinsic calibration between the radar and the Inertial Measurement Unit (IMU) and is sensitive to disturbances, as large linearization errors can degrade performance or even cause divergence. To address these limitations, this letter proposes an Equivariant Filter (EqF) for RIO based on a Lie group symmetry that geometrically couples navigation states and IMU biases, extending it to incorporate radar-IMU extrinsic calibration and multi-state constraint updates. This equivariant formulation inherently preserves consistency and enhances robustness, enabling reliable state estimation even under poor or completely wrong initialization of calibration states. Real-world experiments on two different Uncrewed Aerial Vehicles (UAVs) show that the proposed EqF-RIO achieves state-of-the-art accuracy under correct extrinsic calibration and offers improved convergence under large calibration errors, where the conventional EKF-RIO fails. Evaluation code is open-sourced.
Read the full abstract

All authors Giulio Delama, Jan Michalczyk, Morten Nissov, Martin Scheiber, Alessandro Fornasier, Kostas Alexis, Stephan Weiss

Robotics · Cross-listed from cs.CV

GenAssets: Generating in-the-wild 3D Assets in Latent Space

Ze Yang, Jingkang Wang, Haowei Zhang et al. (+3 more)

High-quality 3D assets for traffic participants are critical for multi-sensor simulation, which is essential for the safe end-to-end development of autonomy. Building assets from in-the-wild data is key for diversity and realism, but existing neural-rendering based reconstruction methods are slow and generate assets that render well only from viewpoints close to the original observations, limiting their usefulness in simulation. Recent diffusion-based generative models build complete and diverse assets, but perform poorly on in-the-wild driving scenes, where observed actors are captured under sparse and limited fields of view, and are partially occluded. In this work, we propose a 3D latent diffusion model that learns on in-the-wild LiDAR and camera data captured by a sensor platform and generates high-quality 3D assets with complete geometry and appearance. Key to our method is a "reconstruct-then-generate" approach that first leverages occlusion-aware neural rendering trained over multiple scenes to build a high-quality latent space for objects, and then trains a diffusion model that operates on the latent space. We show our method outperforms existing reconstruction and generation based methods, unlocking diverse and scalable content creation for simulation.
Read the full abstract

All authors Ze Yang, Jingkang Wang, Haowei Zhang, Sivabalan Manivasagam, Yun Chen, Raquel Urtasun

Robotics

Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines

Ziyao Wang, Bingying Wang, Hanrong Zhang et al. (+7 more)

Despite remarkable progress in Vision–Language–Action (VLA) models, a central bottleneck remains underexamined: the data infrastructure that underlies embodied learning. In this survey, we argue that future advances in VLA will depend less on model architecture and more on the co-design of high-fidelity data engines and structured evaluation protocols. To this end, we present a systematic, data-centric analysis of VLA research organized around three pillars: datasets, benchmarks, and data engines. For datasets, we categorize real-world and synthetic corpora along embodiment diversity, modality composition, and action space formulation, revealing a persistent fidelity-cost trade-off that fundamentally constrains large-scale collection. For benchmarks, we analyze task complexity and environment structure jointly, exposing structural gaps in compositional generalization and long-horizon reasoning evaluation that existing protocols fail to address. For data engines, we examine simulation-based, video-reconstruction, and automated task-generation paradigms, identifying their shared limitations in physical grounding and sim-to-real transfer. Synthesizing these analyses, we distill four open challenges: representation alignment, multimodal supervision, reasoning assessment, and scalable data generation. Addressing them, we argue, requires treating data infrastructure as a first-class research problem rather than a background concern.
Read the full abstract

All authors Ziyao Wang, Bingying Wang, Hanrong Zhang, Tingting Du, Tianyang Chen, Guoheng Sun, Yexiao He, Zheyu Shen, Wanghao Ye, Ang Li

Robotics

Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning

Soham Kulkarni, Raayan Dhar and Yuchen Cui

In behavioral cloning (BC), policy performance is fundamentally limited by demonstration data quality. Real-world datasets contain trajectories of varying quality due to operator skill differences, teleoperation artifacts, and procedural inconsistencies, yet standard BC treats all demonstrations equally. Existing curation methods require costly policy training in the loop or manual annotation, limiting scalability. We propose RINSE (Ranking and INdexing Smooth Examples), a lightweight framework for scoring demonstrations based on trajectory smoothness that is policy-architecture-agnostic and operates on trajectory data alone, with TED additionally using a phase-boundary/contact signal. Grounded in motor control theory, which establishes smoothness as a hallmark of skilled movement, RINSE uses two complementary metrics: Spectral Arc Length (SAL), a spectral measure of frequency-domain regularity, and Trajectory-Envelope Distance (TED), a spatial measure of contact-aware geometric deviation. We show that smoothness filtering can reduce the conditional action variance of the retained data distribution, with downstream effects that can be amplified by action chunking and compounding error. On RoboMimic benchmarks, SAL filtering achieves 16% higher success using one-sixth of the data. On real-world manipulation, TED filtering achieves 20% improvement with half the data. As a retrieval-stage filter within STRAP on LIBERO-10, RINSE re-ranking improves mean success by 5.6%. As soft weights in Re-Mix domain reweighting, RINSE scores produce domain allocations highly correlated with the learned Re-Mix allocations (Spearman $\rho \geq 0.89$). These results support smoothness as a useful quality signal across filtering, retrieval, and reweighting settings, especially in noisy or heterogeneous data regimes.
Read the full abstract

Robotics · Cross-listed from cs.CV

Efficient Image Annotation via Semi-Supervised Object Segmentation with Label Propagation

Vitalii Tutevych, Raphael Memmesheimer, Luca Eichler et al. (+4 more)

Reliable object perception is necessary for general-purpose service robots. Open-vocabulary detectors struggle to generalize beyond a few classes and fully supervised training of object detectors requires time-intensive annotations. We present a semi-supervised label propagation approach for household object segmentation. A segment proposer generates class-agnostic masks, and an ensemble of Hopfield networks assigns labels by learning representative embeddings in complementary foundation model embedding spaces (CLIP, ViT, Theia). Our approach scales to 50 object classes with limited annotation overhead and can automatically label 60% of the data in a RoboCup@Home setting, where preparation time is severely constrained. Dataset and code are publicly available at https://github.com/ais-bonn/label_propagation.
Read the full abstract

All authors Vitalii Tutevych, Raphael Memmesheimer, Luca Eichler, Dmytro Pavlichenko, Fynn Schilke, Rodja Krudewig, Sven Behnke