Peer Revenue An exchange of ideas

Papers

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

Computer Science Robotics

cs.RO Watch Robotics

Wednesday 12 November

Robotics

SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation

Hao Shi, Bin Xie, Yingfei Liu et al. (+5 more)

Robotic manipulation requires precise spatial understanding to interact with objects in the real world. Point-based methods suffer from sparse sampling, leading to the loss of fine-grained semantics. Image-based methods typically feed RGB and depth into 2D backbones pre-trained on 3D auxiliary tasks, but their entangled semantics and geometry are sensitive to inherent depth noise in real-world that disrupts semantic understanding. Moreover, these methods focus on high-level geometry while overlooking low-level spatial cues essential for precise interaction. We propose SpatialActor, a disentangled framework for robust robotic manipulation that explicitly decouples semantics and geometry. The Semantic-guided Geometric Module adaptively fuses two complementary geometry from noisy depth and semantic-guided expert priors. Also, a Spatial Transformer leverages low-level spatial cues for accurate 2D-3D mapping and enables interaction among spatial features. We evaluate SpatialActor on multiple simulation and real-world scenarios across 50+ tasks. It achieves state-of-the-art performance with 87.4% on RLBench and improves by 13.9% to 19.4% under varying noisy conditions, showing strong robustness. Moreover, it significantly enhances few-shot generalization to new tasks and maintains robustness under various spatial perturbations. Project Page: https://shihao1895.github.io/SpatialActor
Read the full abstract

All authors Hao Shi, Bin Xie, Yingfei Liu, Yang Yue, Tiancai Wang, Haoqiang Fan, Xiangyu Zhang, Gao Huang

Robotics

MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation

Runhao Li, Wenkai Guo, Zhenyu Wu et al. (+5 more)

Pre-trained Vision-Language-Action (VLA) models have achieved remarkable success in improving robustness and generalization for end-to-end robotic manipulation. However, these models struggle with long-horizon tasks due to their lack of memory and reliance solely on immediate sensory inputs. To address this limitation, we propose Memory-Augmented Prompting for Vision-Language-Action model (MAP-VLA), a novel framework that empowers pre-trained VLA models with demonstration-derived memory prompts to augment action generation for long-horizon robotic manipulation tasks. To achieve this, MAP-VLA first constructs a memory library from historical demonstrations, where each memory unit captures information about a specific stage of a task. These memory units are implemented as learnable soft prompts optimized through prompt tuning. Then, during real-time task execution, MAP-VLA retrieves relevant memory through trajectory similarity matching and dynamically integrates it into the VLA model for augmented action generation. Importantly, this prompt tuning and retrieval augmentation approach operates as a plug-and-play module for a frozen VLA model, offering a lightweight and flexible solution to improve task performance. Experimental results show that MAP-VLA delivers up to 7.0% absolute performance gains in the simulation benchmark and 25.0% on real robot evaluations for long-horizon tasks, surpassing the current state-of-the-art methods.
Read the full abstract

All authors Runhao Li, Wenkai Guo, Zhenyu Wu, Changyuan Wang, Haoyuan Deng, Zhenyu Weng, Yap-Peng Tan, Ziwei Wang

Robotics

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

Fangqi Zhu, Zhengyang Yan, Zicong Hong et al. (+3 more)

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation, but their reliance on expert demonstrations limits their ability to learn from failures and perform self-corrections. Reinforcement learning (RL) addresses these through self-improving interactions with the physical environment, but suffers from high sample complexity on real robots. We introduce World-Model-based Policy Optimization (WMPO), a principled framework for on-policy VLA RL without interacting with the real environment. In contrast to widely used latent world models, WMPO focuses on pixel-based predictions that align the "imagined" trajectories with the VLA features pretrained with web-scale images. Crucially, WMPO enables the policy to perform on-policy GRPO that provides stronger performance than the often-used off-policy methods. Extensive experiments in both simulation and real-robot settings demonstrate that WMPO (i) substantially improves sample efficiency, (ii) achieves stronger overall performance, (iii) exhibits emergent behaviors such as self-correction, and (iv) demonstrates robust generalization and lifelong learning capabilities.
Read the full abstract

All authors Fangqi Zhu, Zhengyang Yan, Zicong Hong, Quanxin Shou, Xiao Ma, Song Guo

Robotics

SPIDER: Scalable Physics-Informed Dexterous Retargeting

Chaoyi Pan, Changhao Wang, Haozhi Qi et al. (+8 more)

Learning agile robotic policies requires large-scale demonstrations, but translating abundant human motion data to robots is bottlenecked by the embodiment gap and missing dynamic information. To bridge this gap, we propose Scalable Physics-Informed DExterous Retargeting (SPIDER), a physics-based retargeting framework to transform and augment kinematic-only human demonstrations into dynamically feasible robot trajectories at scale. Our key insight is that human demonstrations should provide global task structure and objective, while a sampling-based solver can be used to find the feasible solution given the physics constraints. As a general framework, SPIDER is an efficient physics-based retargeting method that can be applied to both humanoid whole-body loco-manipulation and dexterous manipulation across 9 humanoid/dexterous hand embodiments, 6 datasets and 3 simulators. By bypassing the need for policy optimization, it achieves state-of-the-art performance while being 10x faster than reinforcement learning (RL) baselines. Furthermore, SPIDER enables physics-based data augmentation, such as imposing external payloads, perturbations, and new contact patterns, to generate diverse data. We demonstrate that the retargeted motion can be executed on the robot directly open-loop or serve as feasible reference motion for efficient RL policy learning. Our pipeline enables large-scale generation of robot trajectories from human motion, and we release a dataset of 6,520 simulated demonstrations across four hands and 191 dataset-specific object identities to support future research.
Read the full abstract

All authors Chaoyi Pan, Changhao Wang, Haozhi Qi, Julen Urain, Zixi Liu, Homanga Bharadhwaj, Akash Sharma, Tingfan Wu, Guanya Shi, Jitendra Malik, Francois Hogan

Robotics

CoRL-MPPI: Enhancing MPPI With Learnable Behaviours For Efficient And Provably-Safe Multi-Robot Collision Avoidance

Stepan Dergachev, Artem Pshenitsyn, Aleksandr Panov et al. (+2 more)

Decentralized collision avoidance is a core challenge for scalable multi-robot systems. A promising approach to this problem is Model Predictive Path Integral (MPPI) control - a framework that naturally handles arbitrary motion models and provides strong theoretical guarantees. Still, in practice an MPPI-based controller may produce suboptimal trajectories because its performance relies heavily on uninformed random sampling. We introduce CoRL-MPPI, a fusion of Cooperative Reinforcement Learning and MPPI that addresses this limitation. We train an action policy, approximated by a deep neural network, in simulation to learn local cooperative collision-avoidance behaviors. This learned policy is then embedded into the MPPI framework to guide its sampling distribution, biasing it toward more intelligent and cooperative actions in scenarios that may differ substantially from those used during training. Moreover, CoRL-MPPI preserves the theoretical guarantees of regular MPPI. We evaluate our approach in dense, dynamic setups against classical and learning-based state-of-the-art baselines. Our results demonstrate that CoRL-MPPI outperforms competing methods and significantly improves navigation efficiency, measured by success rate and delay, as well as safety, enabling agile and robust multi-robot navigation.
Read the full abstract

All authors Stepan Dergachev, Artem Pshenitsyn, Aleksandr Panov, Alexey Skrynnik, Konstantin Yakovlev

Robotics

UMIGen: A Unified Framework for Egocentric Point Cloud Generation and Cross-Embodiment Robotic Imitation Learning

Yan Huang, Shoujie Li, Xingting Li et al. (+1 more)

Data-driven robotic learning faces an obvious dilemma: robust policies demand large-scale, high-quality demonstration data, yet collecting such data remains a major challenge owing to high operational costs, dependence on specialized hardware, and the limited spatial generalization capability of current methods. The Universal Manipulation Interface (UMI) relaxes the strict hardware requirements for data collection, but it is restricted to capturing only RGB images of a scene and omits the 3D geometric information on which many tasks rely. Inspired by DemoGen, we propose UMIGen, a unified framework that consists of two key components: (1) Cloud-UMI, a handheld data collection device that requires no visual SLAM and simultaneously records point cloud observation-action pairs; and (2) a visibility-aware optimization mechanism that extends the DemoGen pipeline to egocentric 3D observations by generating only points within the camera's field of view. These two components enable efficient data generation that aligns with real egocentric observations and can be directly transferred across different robot embodiments without any post-processing. Experiments in both simulated and real-world settings demonstrate that UMIGen supports strong cross-embodiment generalization and accelerates data collection in diverse manipulation tasks.
Read the full abstract

All authors Yan Huang, Shoujie Li, Xingting Li, Wenbo Ding

Robotics

Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots

Yuxi Wei, Zirui Wang, Kangning Yin et al. (+3 more)

Data scaling has long remained a critical bottleneck in robot learning. For humanoid robots, human videos and motion data are abundant and widely available, offering a free and large-scale data source. Besides, the semantics related to the motions enable modality alignment and high-level robot control learning. However, how to effectively mine raw video, extract robot-learnable representations, and leverage them for scalable learning remains an open problem. To address this, we introduce Humanoid-Union, a large-scale dataset generated through an autonomous pipeline, comprising over 260 hours of diverse, high-quality humanoid robot motion data with semantic annotations derived from human motion videos. The dataset can be further expanded via the same pipeline. Building on this data resource, we propose SCHUR, a scalable learning framework designed to explore the impact of large-scale data on high-level control in humanoid robots. Experimental results demonstrate that SCHUR achieves high robot motion generation quality and strong text-motion alignment under data and model scaling, with 37% reconstruction improvement under MPJPE and 25% alignment improvement under FID comparing with previous methods. Its effectiveness is further validated through deployment in real-world humanoid robot.
Read the full abstract

All authors Yuxi Wei, Zirui Wang, Kangning Yin, Yue Hu, Jingbo Wang, Siheng Chen

Robotics · Cross-listed from cs.CV

HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests

Ethan Griffiths, Maryam Haghighat, Simon Denman et al. (+2 more)

This article presents HOTFLoc++, an end-to-end hierarchical framework for LiDAR place recognition, re-ranking, and 6-DoF metric localisation in forests. Leveraging an octree-based transformer, our approach extracts features at multiple granularities to increase robustness to clutter, self-similarity, and viewpoint changes in challenging scenarios, including ground-to-ground and ground-to-aerial in forest and urban environments. We propose learnable multi-scale geometric verification to reduce re-ranking failures due to degraded single-scale correspondences. Our joint training protocol enforces multi-scale geometric consistency of the octree hierarchy via joint optimisation of place recognition with re-ranking and localisation, improving place recognition convergence. Our system achieves comparable or lower localisation errors to baselines, with runtime improvements of almost two orders of magnitude over RANSAC-based registration for dense point clouds. Experimental results on public datasets show the superiority of our approach compared to state-of-the-art methods, achieving an average Recall@1 of 90.7% on CS-Wild-Places: an improvement of 29.6 percentage points over baselines, while maintaining high performance on single-source benchmarks with an average Recall@1 of 91.7% and 97.9% on Wild-Places and MulRan, respectively. Our method achieves under 2m and 5$^{\circ}$ error for 97.2% of 6-DoF registration attempts, with our multi-scale re-ranking module reducing localisation errors by ~2x on average. The code is available at https://github.com/csiro-robotics/HOTFLoc.
Read the full abstract

All authors Ethan Griffiths, Maryam Haghighat, Simon Denman, Clinton Fookes, Milad Ramezani

Robotics

LODESTAR: Degeneracy-Aware LiDAR-Inertial Odometry with Adaptive Schmidt-Kalman Filter and Data Exploitation

Eungchang Mason Lee, Kevin Christiansen Marsim and Hyun Myung

LiDAR-inertial odometry (LIO) has been widely used in robotics due to its high accuracy. However, its performance degrades in degenerate environments, such as long corridors and high-altitude flights, where LiDAR measurements are imbalanced or sparse, leading to ill-posed state estimation. In this letter, we present LODESTAR, a novel LIO method that addresses these degeneracies through two key modules: degeneracy-aware adaptive Schmidt-Kalman filter (DA-ASKF) and degeneracy-aware data exploitation (DA-DE). DA-ASKF employs a sliding window to utilize past states and measurements as additional constraints. Specifically, it introduces degeneracy-aware sliding modes that adaptively classify states as active or fixed based on their degeneracy level. Using Schmidt-Kalman update, it partially optimizes active states while preserving fixed states. These fixed states influence the update of active states via their covariances, serving as reference anchors–akin to a lodestar. Additionally, DA-DE prunes less-informative measurements from active states and selectively exploits measurements from fixed states, based on their localizability contribution and the condition number of the Jacobian matrix. Consequently, DA-ASKF enables degeneracy-aware constrained optimization and mitigates measurement sparsity, while DA-DE addresses measurement imbalance. Experimental results show that LODESTAR outperforms existing LiDAR-based odometry methods and degeneracy-aware modules in terms of accuracy and robustness under various degenerate conditions.
Read the full abstract

Robotics

RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation

Xuetao Li, Wenke Huang, Nengyuan Pan et al. (+7 more)

Humanoid robots exhibit significant potential in executing diverse human-level skills. However, current research predominantly relies on data-driven approaches that necessitate extensive training datasets to achieve robust multimodal decision-making capabilities and generalizable visuomotor control. These methods raise concerns due to the neglect of geometric reasoning in unseen scenarios and the inefficient modeling of robot-target relationships within the training data, resulting in significant waste of training resources. To address these limitations, we present the Recurrent Geometric-prior Multimodal Policy (RGMP), an end-to-end framework that unifies geometric-semantic skill reasoning with data-efficient visuomotor control. For perception capabilities, we propose the Geometric-prior Skill Selector, which infuses geometric inductive biases into a vision language model, producing adaptive skill sequences for unseen scenes with minimal spatial common sense tuning. To achieve data-efficient robotic motion synthesis, we introduce the Adaptive Recursive Gaussian Network, which parameterizes robot-object interactions as a compact hierarchy of Gaussian processes that recursively encode multi-scale spatial relationships, yielding dexterous, data-efficient motion synthesis even from sparse demonstrations. Evaluated on both our humanoid robot and desktop dual-arm robot, the RGMP framework achieves 87% task success in generalization tests and exhibits 5x greater data efficiency than the state-of-the-art model. This performance underscores its superior cross-domain generalization, enabled by geometric-semantic reasoning and recursive-Gaussion adaptation.
Read the full abstract

All authors Xuetao Li, Wenke Huang, Nengyuan Pan, Kaiyan Zhao, Songhua Yang, Yiming Wang, Mengde Li, Mang Ye, Jifeng Xuan, Miao Li

Robotics

Data Assessment for Embodied Intelligence

Jiahao Xiao, Bowen Yan, Jianbo Zhang et al. (+4 more)

In embodied intelligence, datasets play a pivotal role, serving as both a knowledge repository and a conduit for information transfer. The two most critical attributes of a dataset are the amount of information it provides and how easily this information can be learned by models. However, the multimodal nature of embodied data makes evaluating these properties particularly challenging. Prior work has largely focused on diversity, typically counting tasks and scenes or evaluating isolated modalities, which fails to provide a comprehensive picture of dataset diversity. On the other hand, the learnability of datasets has received little attention and is usually assessed post-hoc through model training, an expensive, time-consuming process that also lacks interpretability, offering little guidance on how to improve a dataset. In this work, we address both challenges by introducing two principled, data-driven tools. First, we construct a unified multimodal representation for each data sample and, based on it, propose diversity entropy, a continuous measure that characterizes the amount of information contained in a dataset. Second, we introduce the first interpretable, data-driven algorithm to efficiently quantify dataset learnability without training, enabling researchers to assess a dataset's learnability immediately upon its release. We validate our algorithm on both simulated and real-world embodied datasets, demonstrating that it yields faithful, actionable insights that enable researchers to jointly improve diversity and learnability. We hope this work provides a foundation for designing higher-quality datasets that advance the development of embodied intelligence.
Read the full abstract

All authors Jiahao Xiao, Bowen Yan, Jianbo Zhang, Jia Wang, Chunyi Li, Zhengxue Cheng, Guangtao Zhai

Robotics

Decoupling Torque and Stiffness: A Unified Modeling and Control Framework for Antagonistic Artificial Muscles

Amirhossein Kazemipour and Robert K. Katzschmann

Antagonistic artificial muscles can decouple joint torque and stiffness, but contact transients often degrade this independence. We present a unified real-time framework applicable across pneumatic, electrohydraulic, and dielectric elastomer artificial muscle families: a separable Padé force model with a minimal two-state dynamic wrapper, a cascaded inverse-dynamics controller in co-contraction/bias coordinates, and a bio-inspired depth-adaptive interaction policy that schedules stiffness based on penetration depth. The controller runs in under 1 ms per control tick and demonstrates independent torque and stiffness tracking, including a fixed-torque stiffness-step test that preserves torque regulation through stiffness transitions. In a coupled impedance contact protocol simulated across soft-to-rigid environments, comparing depth-adaptive stiffness to fixed-stiffness baselines reveals a shock/load versus stability tradeoff. These results provide a control-oriented foundation for musculoskeletal antagonistic robots to execute adaptive impedance behaviors in dynamic interactions.
Read the full abstract

Robotics

APEX: Action Priors Enable Efficient Exploration for Robust Motion Tracking on Legged Robots

Shivam Sood, Laukik Nakhwa, Sun Ge et al. (+7 more)

Learning natural, animal-like locomotion from demonstrations has become a core paradigm in legged robotics. Despite the recent advancements in motion tracking, most existing methods demand extensive tuning and rely on reference data during deployment, limiting adaptability. We present APEX (Action Priors enable Efficient Exploration), a plug-and-play extension to state-of-the-art motion tracking algorithms that eliminates any dependence on reference data during deployment, improves sample efficiency, and reduces parameter tuning effort. APEX integrates expert demonstrations directly into reinforcement learning (RL) by incorporating decaying action priors, which initially bias exploration toward expert demonstrations but gradually allow the policy to explore independently. This is combined with a multi-critic framework that balances task performance with motion style. Moreover, APEX enables a single policy to learn diverse motions and transfer reference-like styles across different terrains and velocities, while remaining robust to variations in reward design. We validate the effectiveness of our method through extensive experiments in both simulation and on a Unitree Go2 robot. By leveraging demonstrations to guide exploration during RL training, without imposing explicit bias toward them, APEX enables legged robots to learn with greater stability, efficiency, and generalization. We believe this approach paves the way for guidance-driven RL to boost natural skill acquisition in a wide array of robotic tasks, from locomotion to manipulation. Website and code: https://marmotlab.github.io/APEX/.
Read the full abstract

All authors Shivam Sood, Laukik Nakhwa, Sun Ge, Yuhong Cao, Jin Cheng, Fatemah Zargarbashi, Taerim Yoon, Sungjoon Choi, Stelian Coros, Guillaume Sartoretti

Robotics

D-AWSIM: Distributed Autonomous Driving Simulator for Dynamic Map Generation Framework

Shunsuke Ito, Chaoran Zhao, Ryo Okamura et al. (+1 more)

Autonomous driving systems have achieved significant advances, and full autonomy within defined operational design domains near practical deployment. Expanding these domains requires addressing safety assurance under diverse conditions. Information sharing through vehicle-to-vehicle and vehicle-to-infrastructure communication, enabled by a Dynamic Map platform built from vehicle and roadside sensor data, offers a promising solution. Real-world experiments with numerous infrastructure sensors incur high costs and regulatory challenges. Conventional single-host simulators lack the capacity for large-scale urban traffic scenarios. This paper proposes D-AWSIM, a distributed simulator that partitions its workload across multiple machines to support the simulation of extensive sensor deployment and dense traffic environments. A Dynamic Map generation framework on D-AWSIM enables researchers to explore information-sharing strategies without relying on physical testbeds. The evaluation shows that D-AWSIM increases throughput for vehicle count and LiDAR sensor processing substantially compared to a single-machine setup. Integration with Autoware demonstrates applicability for autonomous driving research.
Read the full abstract

All authors Shunsuke Ito, Chaoran Zhao, Ryo Okamura, Takuya Azumi

Robotics

SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields

Sangheon Yang, Yeongin Yoon, Hong Mo Jung et al. (+1 more)

Traditional Visual Odometry (VO) and Visual Inertial Odometry (VIO) methods rely on a 'pose-centric' paradigm, which computes absolute camera poses from the local map thus requires large-scale landmark maintenance and continuous map optimization. This approach is computationally expensive, limiting their real-time performance on resource-constrained devices. To overcome these limitations, we introduce Sparse Motion Field Visual Odometry (SMF-VO), a lightweight, 'motion-centric' framework. Our approach directly estimates instantaneous linear and angular velocity from sparse optical flow, bypassing the need for explicit pose estimation or expensive landmark tracking. We also employed a generalized 3D ray-based motion field formulation that works accurately with various camera models, including wide-field-of-view lenses. SMF-VO demonstrates superior efficiency and competitive accuracy on benchmark datasets, achieving over 100 FPS on a Raspberry Pi 5 using only a CPU. Our work establishes a scalable and efficient alternative to conventional methods, making it highly suitable for mobile robotics and wearable devices.
Read the full abstract

All authors Sangheon Yang, Yeongin Yoon, Hong Mo Jung, Jongwoo Lim

Robotics · Cross-listed from cs.AI

Argus: Resilience-Oriented Safety Assurance Framework for End-to-End ADSs

Dingji Wang, You Lu, Bihuan Chen et al. (+4 more)

End-to-end autonomous driving systems (ADSs), with their strong capabilities in environmental perception and generalizable driving decisions, are attracting growing attention from both academia and industry. However, once deployed on public roads, ADSs are inevitably exposed to diverse driving hazards that may compromise safety and degrade system performance. This raises a strong demand for resilience of ADSs, particularly the capability to continuously monitor driving hazards and adaptively respond to potential safety violations, which is crucial for maintaining robust driving behaviors in complex driving scenarios. To bridge this gap, we propose a runtime resilience-oriented framework, Argus, to mitigate the driving hazards, thus preventing potential safety violations and improving the driving performance of an ADS. Argus continuously monitors the trajectories generated by the ADS for potential hazards and, whenever the EGO vehicle is deemed unsafe, seamlessly takes control through a hazard mitigator. We integrate Argus with three state-of-the-art end-to-end ADSs, i.e., TCP, UniAD and VAD. Our evaluation has demonstrated that Argus effectively and efficiently enhances the resilience of ADSs, improving the driving score of the ADS by up to 150.30% on average, and preventing up to 64.38% of the violations, with little additional time overhead.
Read the full abstract

All authors Dingji Wang, You Lu, Bihuan Chen, Shuo Hao, Haowen Jiang, Yifan Tian, Xin Peng

Robotics

A Quantum Tunneling and Bio-Phototactic Driven Enhanced Dwarf Mongoose Optimizer for UAV Trajectory Planning and Engineering Problem

Mingyang Yu, Haorui Yang, Kangning An et al. (+3 more)

With the widespread adoption of unmanned aerial vehicles (UAV), effective path planning has become increasingly important. Although traditional search methods have been extensively applied, metaheuristic algorithms have gained popularity due to their efficiency and problem-specific heuristics. However, challenges such as premature convergence and lack of solution diversity still hinder their performance in complex scenarios. To address these issues, this paper proposes an Enhanced Multi-Strategy Dwarf Mongoose Optimization (EDMO) algorithm, tailored for three-dimensional UAV trajectory planning in dynamic and obstacle-rich environments. EDMO integrates three novel strategies: (1) a Dynamic Quantum Tunneling Optimization Strategy (DQTOS) to enable particles to probabilistically escape local optima; (2) a Bio-phototactic Dynamic Focusing Search Strategy (BDFSS) inspired by microbial phototaxis for adaptive local refinement; and (3) an Orthogonal Lens Opposition-Based Learning (OLOBL) strategy to enhance global exploration through structured dimensional recombination. EDMO is benchmarked on 39 standard test functions from CEC2017 and CEC2020, outperforming 14 advanced algorithms in convergence speed, robustness, and optimization accuracy. Furthermore, real-world validations on UAV three-dimensional path planning and three engineering design tasks confirm its practical applicability and effectiveness in field robotics missions requiring intelligent, adaptive, and time-efficient planning.
Read the full abstract

All authors Mingyang Yu, Haorui Yang, Kangning An, Xinjian Wei, Xiaoxuan Xu, Jing Xu

Robotics

UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving

Ziyi Song, Chen Xia, Chenbing Wang et al. (+3 more)

Autonomous driving holds transformative potential but remains fundamentally constrained by the limited perception and isolated decision-making with standalone intelligence. While recent multi-agent approaches introduce cooperation, they often focus merely on perception-level tasks, overlooking the alignment with downstream planning and control, or fall short in leveraging the full capacity of the recent emerging end-to-end autonomous driving. In this paper, we present UniMM-V2X, a novel end-to-end multi-agent framework that enables hierarchical cooperation across perception, prediction, and planning. At the core of our framework is a multi-level fusion strategy that unifies perception and prediction cooperation, allowing agents to share queries and reason cooperatively for consistent and safe decision-making. To adapt to diverse downstream tasks and further enhance the quality of multi-level fusion, we incorporate a Mixture-of-Experts (MoE) architecture to dynamically enhance the BEV representations. We further extend MoE into the decoder to better capture diverse motion patterns. Extensive experiments on the DAIR-V2X dataset demonstrate our approach achieves state-of-the-art (SOTA) performance with a 39.7% improvement in perception accuracy, a 7.2% reduction in prediction error, and a 33.2% improvement in planning performance compared with UniV2X, showcasing the strength of our MoE-enhanced multi-level cooperative paradigm.
Read the full abstract

All authors Ziyi Song, Chen Xia, Chenbing Wang, Haibao Yu, Sheng Zhou, Zhisheng Niu

Robotics

Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning

Mobin Habibpour and Fatemeh Afghah

While Vision-Language Models (VLMs) are set to transform robotic navigation, existing methods often underutilize their reasoning capabilities. To unlock the full potential of VLMs in robotics, we shift their role from passive observers to active strategists in the navigation process. Our framework outsources high-level planning to a VLM, which leverages its contextual understanding to guide a frontier-based exploration agent. This intelligent guidance is achieved through a trio of techniques: structured chain-of-thought prompting that elicits logical, step-by-step reasoning; dynamic inclusion of the agent's recent action history to prevent getting stuck in loops; and a novel capability that enables the VLM to interpret top-down obstacle maps alongside first-person views, thereby enhancing spatial awareness. When tested on challenging benchmarks like HM3D, Gibson, and MP3D, this method produces exceptionally direct and logical trajectories, marking a substantial improvement in navigation efficiency over existing approaches and charting a path toward more capable embodied agents.
Read the full abstract

Robotics

Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation

Ningnan Wang, Weihuang Chen, Liming Chen et al. (+4 more)

Embodied visual navigation remains a challenging task, as agents must explore unknown environments with limited knowledge. Existing zero-shot studies have shown that incorporating memory mechanisms to support goal-directed behavior can improve long-horizon planning performance. However, they overlook visual frontier boundaries, which fundamentally dictate future trajectories and observations, and fall short of inferring the relationship between partial visual observations and navigation goals. In this paper, we propose Semantic Cognition Over Potential-based Exploration (SCOPE), a zero-shot framework that explicitly leverages frontier information to drive potential-based exploration, enabling more informed and goal-relevant decisions. SCOPE estimates exploration potential with a Vision-Language Model and organizes it into a spatio-temporal potential graph, capturing boundary dynamics to support long-horizon planning. In addition, SCOPE incorporates a self-reconsideration mechanism that revisits and refines prior decisions, enhancing reliability and reducing overconfident errors. Experimental results on two diverse embodied navigation tasks show that SCOPE outperforms state-of-the-art baselines by 4.6% in accuracy. Further analysis demonstrates that its core components lead to improved calibration, stronger generalization, and higher decision quality.
Read the full abstract

All authors Ningnan Wang, Weihuang Chen, Liming Chen, Haoxuan Ji, Zhongyu Guo, Xuchong Zhang, Hongbin Sun

Robotics · Cross-listed from cs.LG

Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning

Yunchang Ma, Tenglong Liu, Yixing Lan et al. (+4 more)

In offline reinforcement learning, value overestimation caused by out-of-distribution (OOD) actions significantly limits policy performance. Recently, diffusion models have been leveraged for their strong distribution-matching capabilities, enforcing conservatism through behavior policy constraints. However, existing methods often apply indiscriminate regularization to redundant actions in low-quality datasets, resulting in excessive conservatism and an imbalance between the expressiveness and efficiency of diffusion modeling. To address these issues, we propose DIffusion policies with Value-conditional Optimization (DIVO), a novel approach that leverages diffusion models to generate high-quality, broadly covered in-distribution state-action samples while facilitating efficient policy improvement. Specifically, DIVO introduces a binary-weighted mechanism that utilizes the advantage values of actions in the offline dataset to guide diffusion model training. This enables a more precise alignment with the dataset's distribution while selectively expanding the boundaries of high-advantage actions. During policy improvement, DIVO dynamically filters high-return-potential actions from the diffusion model, effectively guiding the learned policy toward better performance. This approach achieves a critical balance between conservatism and explorability in offline RL. We evaluate DIVO on the D4RL benchmark and compare it against state-of-the-art baselines. Empirical results demonstrate that DIVO achieves superior performance, delivering significant improvements in average returns across locomotion tasks and outperforming existing methods in the challenging AntMaze domain, where sparse rewards pose a major difficulty.
Read the full abstract

All authors Yunchang Ma, Tenglong Liu, Yixing Lan, Xin Yin, Changxin Zhang, Xinglong Zhang, Xin Xu

Robotics

A Shared Control Framework for Mobile Robots with Planning-Level Intention Prediction

Jinyu Zhang, Lijun Han, Feng Jian et al. (+2 more)

In mobile robot shared control, effectively understanding human motion intention is critical for seamless human-robot collaboration. This paper presents a novel shared control framework featuring planning-level intention prediction. A path replanning algorithm is designed to adjust the robot's desired trajectory according to inferred human intentions. To represent future motion intentions, we introduce the concept of an intention domain, which serves as a constraint for path replanning. The intention-domain prediction and path replanning problems are jointly formulated as a Markov Decision Process and solved through deep reinforcement learning. In addition, a Voronoi-based human trajectory generation algorithm is developed, allowing the model to be trained entirely in simulation without human participation or demonstration data. Extensive simulations and real-world user studies demonstrate that the proposed method significantly reduces operator workload and enhances safety, without compromising task efficiency compared with existing assistive teleoperation approaches.
Read the full abstract

All authors Jinyu Zhang, Lijun Han, Feng Jian, Lingxi Zhang, Hesheng Wang

Robotics

MirrorLimb: Implementing hand pose acquisition and robot teleoperation based on RealMirror

Cong Tai, Hansheng Wu, Haixu Long et al. (+4 more)

In this work, we present a PICO-based robot remote operating framework that enables low-cost, real-time acquisition of hand motion and pose data, outperforming mainstream visual tracking and motion capture solutions in terms of cost-effectiveness. The framework is natively compatible with the RealMirror ecosystem, offering ready-to-use functionality for stable and precise robotic trajectory recording within the Isaac simulation environment, thereby facilitating the construction of Vision-Language-Action (VLA) datasets. Additionally, the system supports real-time teleoperation of a variety of end-effector-equipped robots, including dexterous hands and robotic grippers. This work aims to lower the technical barriers in the study of upper-limb robotic manipulation, thereby accelerating advancements in VLA-related research.
Read the full abstract

All authors Cong Tai, Hansheng Wu, Haixu Long, Zhengbin Long, Zhaoyu Zheng, Haodong Xiang, Tao Shen

Robotics

XPRESS: X-Band Radar Place Recognition via Elliptical Scan Shaping

Hyesu Jang, Wooseong Yang, Ayoung Kim et al. (+2 more)

X-band radar serves as the primary sensor on maritime vessels, however, its application in autonomous navigation has been limited due to low sensor resolution and insufficient information content. To enable X-band radar-only autonomous navigation in maritime environments, this paper proposes a place recognition algorithm specifically tailored for X-band radar, incorporating an object density-based rule for efficient candidate selection and intentional degradation of radar detections to achieve robust retrieval performance. The proposed algorithm was evaluated on both public maritime radar datasets and our own collected dataset, and its performance was compared against state-of-the-art radar place recognition methods. An ablation study was conducted to assess the algorithm's performance sensitivity with respect to key parameters.
Read the full abstract

All authors Hyesu Jang, Wooseong Yang, Ayoung Kim, Dongje Lee, Hanguen Kim

Tuesday 11 November

Robotics

Real-time Point Cloud Data Transmission via L4S for 5G-Edge-Assisted Robotics

Gerasimos Damigos, Achilleas Santi Seisa, Nikolaos Stathoulopoulos et al. (+2 more)

This article presents a novel framework for real-time Light Detection and Ranging (LiDAR) data transmission that leverages rate-adaptive technologies and point cloud encoding methods to ensure low-latency, and low-loss data streaming. The proposed framework is intended for, but not limited to, robotic applications that require real-time data transmission over the internet for offloaded processing. Specifically, the Low Latency, Low Loss, Scalable Throughput L4S-enabled SCReAM v2 transmission framework is extended to incorporate the Draco geometry compression algorithm, enabling dynamic compression of high-bitrate 3D LiDAR data according to the sensed channel capacity and network load. The low-latency 3D LiDAR streaming system is designed to maintain minimal end-to-end delay while constraining encoding errors to meet the accuracy requirements of robotic applications. We demonstrate the effectiveness of the proposed method through real-world experiments conducted over a public 5G network across multi-kilometer urban environments. The low-latency and low-loss requirements are preserved, while real-time offloading and evaluation of 3D SLAM algorithms are used to validate the framework's performance in practical use cases.
Read the full abstract

All authors Gerasimos Damigos, Achilleas Santi Seisa, Nikolaos Stathoulopoulos, Sara Sandberg, George Nikolakopoulos

Robotics

Low-cost Multi-agent Fleet for Acoustic Cooperative Localization Research

Nelson Durrant, Braden Meyers, Matthew McMurray et al. (+5 more)

Real-world underwater testing for multi-agent autonomy presents substantial financial and engineering challenges. In this work, we introduce the Configurable Underwater Group of Autonomous Robots (CoUGARs) as a low-cost, configurable autonomous-underwater-vehicle (AUV) platform for multi-agent autonomy research. The base design costs less than $3,000 USD (as of May 2025) and is based on commercially-available and 3D-printed parts, enabling quick customization for various sensor payloads and configurations. Our current expanded model is equipped with a doppler velocity log (DVL) and ultra-short-baseline (USBL) acoustic array/transducer to support research on acoustic-based cooperative localization. State estimation, navigation, and acoustic communications software has been developed and deployed using a containerized software stack and is tightly integrated with the HoloOcean simulator. The system was tested both in simulation and via in-situ field trials in Utah lakes and reservoirs.
Read the full abstract

All authors Nelson Durrant, Braden Meyers, Matthew McMurray, Clayton Smith, Brighton Anderson, Tristan Hodgins, Kalliyan Velasco, Joshua G. Mangelson

Robotics

Dual-Arm Whole-Body Motion Planning: Leveraging Overlapping Kinematic Chains

Richard Cheng, Peter Werner and Carolyn Matl

High degree-of-freedom dual-arm robots are becoming increasingly common due to their morphology enabling them to operate effectively in human environments. However, motion planning in real-time within unknown, changing environments remains a challenge for such robots due to the high dimensionality of the configuration space and the complex collision-avoidance constraints that must be obeyed. In this work, we propose a novel way to alleviate the curse of dimensionality by leveraging the structure imposed by shared joints (e.g. torso joints) in a dual-arm robot. First, we build two dynamic roadmaps (DRM) for each kinematic chain (i.e. left arm + torso, right arm + torso) with specific structure induced by the shared joints. Then, we show that we can leverage this structure to efficiently search through the composition of the two roadmaps and largely sidestep the curse of dimensionality. Finally, we run several experiments in a real-world grocery store with this motion planner on a 19 DoF mobile manipulation robot executing a grocery fulfillment task, achieving 0.4s average planning times with 99.9% success rate across more than 2000 motion plans.
Read the full abstract

Robotics

CENIC: Convex Error-controlled Numerical Integration for Contact

Vince Kurtz and Alejandro Castro

State-of-the-art robotics simulators operate in discrete time. This requires users to choose a time step, which is both critical and challenging: large steps can produce non-physical artifacts, while small steps force the simulation to run slowly. Continuous-time error-controlled integration avoids such issues by automatically adjusting the time step to achieve a desired accuracy. But existing error-controlled integrators struggle with the stiff dynamics of contact, and cannot meet the speed and scalability requirements of modern robotics workflows. We introduce CENIC, a new variable-step integrator that brings together recent advances in convex time-stepping and error-controlled integration, inheriting benefits from both continuous integration and discrete time-stepping. CENIC runs at fast real-time rates comparable to discrete-time robotics simulators like MuJoCo, Drake and Isaac Sim, while also providing guarantees on accuracy and convergence.
Read the full abstract

Robotics · Cross-listed from eess.SY

Information-Driven Fault Detection and Identification for Multi-Agent Spacecraft Systems: Collaborative On-Orbit Inspection Mission

Akshita Gupta, Arna Bhardwaj, Yashwanth Kumar Nakka et al. (+2 more)

This work presents a global-to-local, task-aware fault detection and identification (FDI) framework for multi-spacecraft systems conducting collaborative inspection missions in low Earth orbit. The inspection task is represented by a global information-driven cost functional that integrates the sensor model, spacecraft poses, and mission-level information-gain objectives. This formulation links guidance, control, and FDI by using the same cost function to drive both global task allocation and local sensing or motion decisions. Fault detection is achieved through comparisons between expected and observed task metrics, while higher-order cost-gradient measures enable the identification of faults among sensors, actuators, and state estimators. An adaptive thresholding mechanism captures the time-varying inspection geometry and dynamic mission conditions. Simulation results for representative multi-spacecraft inspection scenarios demonstrate the reliability of fault localization and classification under uncertainty, providing a unified, information-driven foundation for resilient autonomous inspection architectures.
Read the full abstract

All authors Akshita Gupta, Arna Bhardwaj, Yashwanth Kumar Nakka, Changrak Choi, Amir Rahmani

Robotics

ATOM-CBF: Adaptive Safe Perception-Based Control under Out-of-Distribution Measurements

Kai S. Yun and Navid Azizan

Ensuring the safety of real-world systems is challenging, especially when they rely on learned perception modules to infer the system state from high-dimensional sensor data. These perception modules are vulnerable to epistemic uncertainty, often failing when encountering out-of-distribution (OoD) measurements not seen during training. To address this gap, we introduce ATOM-CBF (Adaptive-To-OoD-Measurement Control Barrier Function), a novel safe control framework that explicitly computes and adapts to the epistemic uncertainty from OoD measurements, without the need for ground-truth labels or information on distribution shifts. Our approach features two key components: (1) an OoD-aware adaptive perception error margin and (2) a safety filter that integrates this adaptive error margin, enabling the filter to adjust its conservatism in real-time. We provide empirical validation in simulations, demonstrating that ATOM-CBF maintains safety for an F1Tenth vehicle with LiDAR scans and a quadruped robot with RGB images.
Read the full abstract