Academic Dispatch on Robotics [8.14]

ClickRead the original text at arxivdaily.com, covering CS | Physics | Mathematics | Economics | Statistics | Finance | Biology | Electrical fields, with features like search and collection!

cs.RO Robotics related, a total of 33 papers

【1】Masquerade: Learning from In-the-wild Human Videos using Data-EditingTitle: Masquerade: Learning from In-the-wild Human Videos using Data-EditingLink: https://arxiv.org/abs/2508.09976

Authors: pert, Jiaying Fang, Jeannette BohgNote: Project website at this https URLAbstract: Robot manipulation research still suffers from significant data scarcity: even the largest robot datasets are orders of magnitude smaller and less diverse than those that fueled recent breakthroughs in language and vision. We introduce Masquerade, a method that edits in-the-wild egocentric human videos to bridge the visual embodiment gap between humans and robots and then learns a robot policy with these edited videos. Our pipeline turns each human video into robotized demonstrations by (i) estimating 3-D hand poses, (ii) inpainting the human arms, and (iii) overlaying a rendered bimanual robot that tracks the recovered end-effector trajectories. Pre-training a visual encoder to predict future 2-D robot keypoints on 675K frames of these edited clips, and continuing that auxiliary loss while fine-tuning a diffusion policy head on only 50 robot demonstrations per task, yields policies that generalize significantly better than prior work. On three long-horizon, bimanual kitchen tasks evaluated in three unseen scenes each, Masquerade outperforms baselines by 5-6x. Ablations show that both the robot overlay and co-training are indispensable, and performance scales logarithmically with the amount of edited human video. These results demonstrate that explicitly closing the visual embodiment gap unlocks a vast, readily available source of data from human videos that can be used to improve robot policies.

【2】Vision-driven River Following of UAV via Safe Reinforcement Learning using Semantic Dynamics ModelTitle: Vision-driven River Following of UAV via Safe Reinforcement Learning using Semantic Dynamics ModelLink: https://arxiv.org/abs/2508.09971

Authors: g, Nina MahmoudianNote: Submitted to Robotics and Autonomous Systems (RAS) journalAbstract: Vision-driven autonomous river following by Unmanned Aerial Vehicles is critical for applications such as rescue, surveillance, and environmental monitoring, particularly in dense riverine environments where GPS signals are unreliable. We formalize river following as a coverage control problem in which the reward function is submodular, yielding diminishing returns as more unique river segments are visited, thereby framing the task as a Submodular Markov Decision Process. First, we introduce Marginal Gain Advantage Estimation, which refines the reward advantage function by using a sliding window baseline computed from historical episodic returns, thus aligning the advantage estimation with the agent’s evolving recognition of action value in non-Markovian settings. Second, we develop a Semantic Dynamics Model based on patchified water semantic masks that provides more interpretable and data-efficient short-term prediction of future observations compared to latent vision dynamics models. Third, we present the Constrained Actor Dynamics Estimator architecture, which integrates the actor, the cost estimator, and SDM for cost advantage estimation to form a model-based SafeRL framework capable of solving partially observable Constrained Submodular Markov Decision Processes. Simulation results demonstrate that MGAE achieves faster convergence and superior performance over traditional critic-based methods like Generalized Advantage Estimation. SDM provides more accurate short-term state predictions that enable the cost estimator to better predict potential violations. Overall, CADE effectively integrates safety regulation into model-based RL, with the Lagrangian approach achieving the soft balance of reward and safety during training, while the safety layer enhances performance during inference by hard action overlay.

【3】Online Safety under Multiple Constraints and Input Bounds using gatekeeper: Theory and ApplicationsTitle: Online Safety under Multiple Constraints and Input Bounds using gatekeeper: Theory and ApplicationsLink: https://arxiv.org/abs/2508.09963

Authors: . Agrawal, Dimitra PanagouNote: 6 pages, 2 figures. Accepted for publication in IEEE L-CSS 2025Abstract: This letter presents an approach to guarantee online safety of a cyber-physical system under multiple state and input constraints. Our proposed framework, called gatekeeper, recursively guarantees the existence of an infinite-horizon trajectory that satisfies all constraints and system dynamics. Such trajectory is constructed using a backup controller, which we define formally in this paper. gatekeeper relies on a small number of verifiable assumptions, and is computationally efficient since it requires optimization over a single scalar variable. We make two primary contributions in this letter. (A) First, we develop the theory of gatekeeper: we derive a sub-optimality bound relative to a full nonlinear trajectory optimization problem, and show how this can be used in runtime to validate performance. This also informs the design of the backup controllers and sets. (B) Second, we demonstrate in detail an application of gatekeeper for multi-agent formation flight, where each Dubins agent must avoid multiple obstacles and weapons engagement zones, both of which are nonlinear, nonconvex constraints.

【4】GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid ImitationTitle: GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid ImitationLink: https://arxiv.org/abs/2508.09960

Authors: , Chengyuan Luo, Jiaheng Du, Wentao He, Jun-Guo LuAbstract: The creation of human-like humanoid robots is hindered by a fundamental fragmentation: data processing and learning algorithms are rarely universal across different robot morphologies. This paper introduces the Generalized Behavior Cloning (GBC) framework, a comprehensive and unified solution designed to solve this end-to-end challenge. GBC establishes a complete pathway from human motion to robot action through three synergistic innovations. First, an adaptive data pipeline leverages a differentiable IK network to automatically retarget any human MoCap data to any humanoid. Building on this foundation, our novel DAgger-MMPPO algorithm with its MMTransformer architecture learns robust, high-fidelity imitation policies. To complete the ecosystem, the entire framework is delivered as an efficient, open-source platform based on Isaac Lab, empowering the community to deploy the full workflow via simple configuration scripts. We validate the power and generality of GBC by training policies on multiple heterogeneous humanoids, demonstrating excellent performance and transfer to novel motions. This work establishes the first practical and unified pathway for creating truly generalized humanoid controllers.

【5】PPL: Point Cloud Supervised Proprioceptive Locomotion Reinforcement Learning for Legged Robots in Crawl SpacesTitle: PPL: Point Cloud Supervised Proprioceptive Locomotion Reinforcement Learning for Legged Robots in Crawl SpacesLink: https://arxiv.org/abs/2508.09950

Authors: Nuo Xu, Chenkun Qi, Xin Liu, Yule Mo, Jinkai Wang, Chunpeng LuAbstract: The legged locomotion in spatially constrained structures (called crawl spaces) is challenging. In crawl spaces, current exteroceptive locomotion learning methods are limited by large noises and errors of the sensors in possible low visibility conditions, and current proprioceptive locomotion learning methods are difficult in traversing crawl spaces because only ground features are inferred. In this study, a point cloud supervised proprioceptive locomotion reinforcement learning method for legged robots in crawl spaces is proposed. A state estimation network is designed to estimate the robot’s surrounding ground and spatial features as well as the robot’s collision states using historical proprioceptive sensor data. The point cloud is represented in polar coordinate frame and a point cloud processing method is proposed to efficiently extract the ground and spatial features that are used to supervise the state estimation network learning. Comprehensive reward functions that guide the robot to traverse through crawl spaces after collisions are designed. Experiments demonstrate that, compared to existing methods, our method exhibits more agile locomotion in crawl spaces. This study enhances the ability of legged robots to traverse spatially constrained environments without requiring exteroceptive sensors.

【6】Collision-Free Bearing-Driven Formation Tracking for Euler-Lagrange SystemsTitle: Collision-Free Bearing-Driven Formation Tracking for Euler-Lagrange SystemsLink: https://arxiv.org/abs/2508.09908

Authors: eng, Martin Guay, Shimin Wang, Yunhong CheNote: 10 pages, 4 figuresAbstract: In this paper, we investigate the problem of tracking formations driven by bearings for heterogeneous Euler-Lagrange systems with parametric uncertainty in the presence of multiple moving leaders. To estimate the leaders’ velocities and accelerations, we first design a distributed observer for the leader system, utilizing a bearing-based localization condition in place of the conventional connectivity assumption. This observer, coupled with an adaptive mechanism, enables the synthesis of a novel distributed control law that guides the formation towards the target formation, without requiring prior knowledge of the system parameters. Furthermore, we establish a sufficient condition, dependent on the initial formation configuration, that ensures collision avoidance throughout the formation evolution. The effectiveness of the proposed approach is demonstrated through a numerical example.

【7】A Shank Angle-Based Control System Enables Soft Exoskeleton to Assist Human Non-Steady LocomotionTitle: A Shank Angle-Based Control System Enables Soft Exoskeleton to Assist Human Non-Steady LocomotionLink: https://arxiv.org/abs/2508.09876

Authors: an, Weizhong Jiang, Bi Zhang, Wanxin Chen, Yiwen Zhao, Ning Li, Lianqing Liu, Xingang ZhaoNote: 49 pages, 20 figures, 4 tablesAbstract: Exoskeletons have been shown to effectively assist humans during steady locomotion. However, their effects on non-steady locomotion, characterized by nonlinear phase progression within a gait cycle, remain insufficiently explored, particularly across diverse activities. This work presents a shank angle-based control system that enables the exoskeleton to maintain real-time coordination with human gait, even under phase perturbations, while dynamically shaping assistance profiles to match the biological ankle moment patterns across walking, running, stair negotiation tasks. The control system consists of an assistance profile online generation method and a model-based feedforward control method. The assistance profile is formulated as a dual-Gaussian model with the shank angle as the independent variable. Leveraging only IMU measurements, the model parameters are updated online each stride to adapt to inter- and intra-individual biomechanical variability. The profile tracking control employs a human-exoskeleton kinematics and stiffness model as a feedforward component, reducing reliance on historical control data due to the lack of clear and consistent periodicity in non-steady locomotion. Three experiments were conducted using a lightweight soft exoskeleton with multiple subjects. The results validated the effectiveness of each individual method, demonstrated the robustness of the control system against gait perturbations across various activities, and revealed positive biomechanical and physiological responses of human users to the exoskeleton’s mechanical assistance.

【8】Toward Human-Robot Teaming: Learning Handover Behaviors from 3D ScenesTitle: Toward Human-Robot Teaming: Learning Handover Behaviors from 3D ScenesLink: https://arxiv.org/abs/2508.09855

Authors: , Yik Lung Pang, Andrea Cavallaro, Changjae OhNote: 3 pages, 3 figuresAbstract: Human-robot teaming (HRT) systems often rely on large-scale datasets of human and robot interactions, especially for close-proximity collaboration tasks such as human-robot handovers. Learning robot manipulation policies from raw, real-world image data requires a large number of robot-action trials in the physical environment. Although simulation training offers a cost-effective alternative, the visual domain gap between simulation and robot workspace remains a major limitation. We introduce a method for training HRT policies, focusing on human-to-robot handovers, solely from RGB images without the need for real-robot training or real-robot data collection. The goal is to enable the robot to reliably receive objects from a human with stable grasping while avoiding collisions with the human hand. The proposed policy learner leverages sparse-view Gaussian Splatting reconstruction of human-to-robot handover scenes to generate robot demonstrations containing image-action pairs captured with a camera mounted on the robot gripper. As a result, the simulated camera pose changes in the reconstructed scene can be directly translated into gripper pose changes. Experiments in both Gaussian Splatting reconstructed scene and real-world human-to-robot handover experiments demonstrate that our method serves as a new and effective representation for the human-to-robot handover task, contributing to more seamless and robust HRT.

【9】Whole-Body Bilateral Teleoperation with Multi-Stage Object Parameter Estimation for Wheeled Humanoid LocomanipulationTitle: Whole-Body Bilateral Teleoperation with Multi-Stage Object Parameter Estimation for Wheeled Humanoid LocomanipulationLink: https://arxiv.org/abs/2508.09846

Authors: Baek, Amartya Purushottam, Jason J. Choi, Joao RamosAbstract: This paper presents an object-aware whole-body bilateral teleoperation framework for wheeled humanoid loco-manipulation. This framework combines whole-body bilateral teleoperation with an online multi-stage object inertial parameter estimation module, which is the core technical contribution of this work. The multi-stage process sequentially integrates a vision-based object size estimator, an initial parameter guess generated by a large vision-language model (VLM), and a decoupled hierarchical sampling strategy. The visual size estimate and VLM prior offer a strong initial guess of the object’s inertial parameters, significantly reducing the search space for sampling-based refinement and improving the overall estimation speed. A hierarchical strategy first estimates mass and center of mass, then infers inertia from object size to ensure physically feasible parameters, while a decoupled multi-hypothesis scheme enhances robustness to VLM prior errors. Our estimator operates in parallel with high-fidelity simulation and hardware, enabling real-time online updates. The estimated parameters are then used to update the wheeled humanoid’s equilibrium point, allowing the operator to focus more on locomotion and manipulation. This integration improves the haptic force feedback for dynamic synchronization, enabling more dynamic whole-body teleoperation. By compensating for object dynamics using the estimated parameters, the framework also improves manipulation tracking while preserving compliant behavior. We validate the system on a customized wheeled humanoid with a robotic gripper and human-machine interface, demonstrating real-time execution of lifting, delivering, and releasing tasks with a payload weighing approximately one-third of the robot’s body weight.

【10】Embodied Tactile Perception of Soft Objects PropertiesTitle: Embodied Tactile Perception of Soft Objects PropertiesLink: https://arxiv.org/abs/2508.09836

Authors: utta, Alexis WM Devillard, Zhihuan Zhang, Xiaoxiao Cheng, Etienne BurdetAbstract: To enable robots to develop human-like fine manipulation, it is essential to understand how mechanical compliance, multi-modal sensing, and purposeful interaction jointly shape tactile perception. In this study, we use a dedicated modular e-Skin with tunable mechanical compliance and multi-modal sensing (normal, shear forces and vibrations) to systematically investigate how sensing embodiment and interaction strategies influence robotic perception of objects. Leveraging a curated set of soft wave objects with controlled viscoelastic and surface properties, we explore a rich set of palpation primitives-pressing, precession, sliding that vary indentation depth, frequency, and directionality. In addition, we propose the latent filter, an unsupervised, action-conditioned deep state-space model of the sophisticated interaction dynamics and infer causal mechanical properties into a structured latent space. This provides generalizable and in-depth interpretable representation of how embodiment and interaction determine and influence perception. Our investigation demonstrates that multi-modal sensing outperforms single-modal sensing. It highlights a nuanced interaction between the environment and mechanical properties of e-Skin, which should be examined alongside the interaction by incorporating temporal dynamics.

【11】RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or GaussiansTitle: RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or GaussiansLink: https://arxiv.org/abs/2508.09830

Authors: Wei, Jinxi Li, Yafei Yang, Siyuan Zhou, Bo YangNote: ICCV 2025 Highlight. Shenxing and Jinxi are co-first authors. Code and data are available at: this https URLAbstract: In this paper, we present a generalizable method for 3D surface reconstruction from raw point clouds or pre-estimated 3D Gaussians by 3DGS from RGB images. Unlike existing coordinate-based methods which are often computationally intensive when rendering explicit surfaces, our proposed method, named RayletDF, introduces a new technique called raylet distance field, which aims to directly predict surface points from query rays. Our pipeline consists of three key modules: a raylet feature extractor, a raylet distance field predictor, and a multi-raylet blender. These components work together to extract fine-grained local geometric features, predict raylet distances, and aggregate multiple predictions to reconstruct precise surface points. We extensively evaluate our method on multiple public real-world datasets, demonstrating superior performance in surface reconstruction from point clouds or 3D Gaussians. Most notably, our method achieves exceptional generalization ability, successfully recovering 3D surfaces in a single-forward pass across unseen datasets in testing.

【12】TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view VideosTitle: TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view VideosLink: https://arxiv.org/abs/2508.09811

Authors: Ziyang Song, Bo YangNote: ICCV 2025. Code and data are available at: this https URLAbstract: In this paper, we aim to model 3D scene geometry, appearance, and physical information just from dynamic multi-view videos in the absence of any human labels. By leveraging physics-informed losses as soft constraints or integrating simple physics models into neural networks, existing works often fail to learn complex motion physics, or doing so requires additional labels such as object types or masks. We propose a new framework named TRACE to model the motion physics of complex dynamic 3D scenes. The key novelty of our method is that, by formulating each 3D point as a rigid particle with size and orientation in space, we directly learn a translation rotation dynamics system for each particle, explicitly estimating a complete set of physical parameters to govern the particle’s motion over time. Extensive experiments on three existing dynamic datasets and one newly created challenging synthetic datasets demonstrate the extraordinary performance of our method over baselines in the task of future frame extrapolation. A nice property of our framework is that multiple objects or parts can be easily segmented just by clustering the learned physical parameters.

【13】FLARE: Agile Flights for Quadrotor Cable-Suspended Payload System via Reinforcement LearningTitle: FLARE: Agile Flights for Quadrotor Cable-Suspended Payload System via Reinforcement LearningLink: https://arxiv.org/abs/2508.09797

Authors: Cao, Jin Zhou, Xian Wang, Shuo LiAbstract: Agile flight for the quadrotor cable-suspended payload system is a formidable challenge due to its underactuated, highly nonlinear, and hybrid dynamics. Traditional optimization-based methods often struggle with high computational costs and the complexities of cable mode transitions, limiting their real-time applicability and maneuverability exploitation. In this letter, we present FLARE, a reinforcement learning (RL) framework that directly learns agile navigation policy from high-fidelity simulation. Our method is validated across three designed challenging scenarios, notably outperforming a state-of-the-art optimization-based approach by a 3x speedup during gate traversal maneuvers. Furthermore, the learned policies achieve successful zero-shot sim-to-real transfer, demonstrating remarkable agility and safety in real-world experiments, running in real time on an onboard computer.

【14】Predictive Uncertainty for Runtime Assurance of a Real-Time Computer Vision-Based Landing SystemTitle: Predictive Uncertainty for Runtime Assurance of a Real-Time Computer Vision-Based Landing SystemLink: https://arxiv.org/abs/2508.09732

Authors: entin, Sydney M. Katz, Artur B. Carneiro, Don Walker, Mykel J. KochenderferNote: 8 pages, 5 figures, accepted at DASC 2025Abstract: Recent advances in data-driven computer vision have enabled robust autonomous navigation capabilities for civil aviation, including automated landing and runway detection. However, ensuring that these systems meet the robustness and safety requirements for aviation applications remains a major challenge. In this work, we present a practical vision-based pipeline for aircraft pose estimation from runway images that represents a step toward the ability to certify these systems for use in safety-critical aviation applications. Our approach features three key innovations: (i) an efficient, flexible neural architecture based on a spatial Soft Argmax operator for probabilistic keypoint regression, supporting diverse vision backbones with real-time inference; (ii) a principled loss function producing calibrated predictive uncertainties, which are evaluated via sharpness and calibration metrics; and (iii) an adaptation of Residual-based Receiver Autonomous Integrity Monitoring (RAIM), enabling runtime detection and rejection of faulty model outputs. We implement and evaluate our pose estimation pipeline on a dataset of runway images. We show that our model outperforms baseline architectures in terms of accuracy while also producing well-calibrated uncertainty estimates with sub-pixel precision that can be used downstream for fault detection.

【15】Immersive Teleoperation of Beyond-Human-Scale Robotic Manipulators: Challenges and Future DirectionsTitle: Immersive Teleoperation of Beyond-Human-Scale Robotic Manipulators: Challenges and Future DirectionsLink: https://arxiv.org/abs/2508.09700

Authors: rati, Jouni MattilaNote: This work has been accepted for presentation at the 2025 IEEE Conference on Telepresence, to be held in Leiden, NetherlandsAbstract: Teleoperation of beyond-human-scale robotic manipulators (BHSRMs) presents unique challenges that differ fundamentally from conventional human-scale systems. As these platforms gain relevance in industrial domains such as construction, mining, and disaster response, immersive interfaces must be rethought to support scalable, safe, and effective human-robot collaboration. This paper investigates the control, cognitive, and interface-level challenges of immersive teleoperation in BHSRMs, with a focus on ensuring operator safety, minimizing sensorimotor mismatch, and enhancing the sense of embodiment. We analyze design trade-offs in haptic and visual feedback systems, supported by early experimental comparisons of exoskeleton- and joystick-based control setups. Finally, we outline key research directions for developing new evaluation tools, scaling strategies, and human-centered safety models tailored to large-scale robotic telepresence.

【16】Surg-InvNeRF: Invertible NeRF for 3D tracking and reconstruction in surgical visionTitle: Surg-InvNeRF: Invertible NeRF for 3D tracking and reconstruction in surgical visionLink: https://arxiv.org/abs/2508.09681

Authors: oza, Junlei Hu, Dominic Jones, Sharib Ali, Pietro ValdastriNote: 10 pagesAbstract: We proposed a novel test-time optimization (TTO) approach framed by a NeRF-based architecture for long-term 3D point tracking. Most current methods in point tracking struggle to obtain consistent motion or are limited to 2D motion. TTO methods frame the solution for long-term tracking as optimizing a function that aggregates correspondences from other specialized state-of-the-art methods. Unlike the state-of-the-art on TTO, we propose parametrizing such a function with our new invertible Neural Radiance Field (InvNeRF) architecture to perform both 2D and 3D tracking in surgical scenarios. Our approach allows us to exploit the advantages of a rendering-based approach by supervising the reprojection of pixel correspondences. It adapts strategies from recent rendering-based methods to obtain a bidirectional deformable-canonical mapping, to efficiently handle a defined workspace, and to guide the rays’ density. It also presents our multi-scale HexPlanes for fast inference and a new algorithm for efficient pixel sampling and convergence criteria. We present results in the STIR and SCARE datasets, for evaluating point tracking and testing the integration of kinematic data in our pipeline, respectively. In 2D point tracking, our approach surpasses the precision and accuracy of the TTO state-of-the-art methods by nearly 50% on average precision, while competing with other approaches. In 3D point tracking, this is the first TTO approach, surpassing feed-forward methods while incorporating the benefits of a deformable NeRF-based reconstruction.

【17】Plane Detection and Ranking via Model Information OptimizationTitle: Plane Detection and Ranking via Model Information OptimizationLink: https://arxiv.org/abs/2508.09625

Authors: ong, Jun Li, Meng Yee Michael ChuahNote: Accepted as contributed paper in the 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)Abstract: Plane detection from depth images is a crucial subtask with broad robotic applications, often accomplished by iterative methods such as Random Sample Consensus (RANSAC). While RANSAC is a robust strategy with strong probabilistic guarantees, the ambiguity of its inlier threshold criterion makes it susceptible to false positive plane detections. This issue is particularly prevalent in complex real-world scenes, where the true number of planes is unknown and multiple planes coexist. In this paper, we aim to address this limitation by proposing a generalised framework for plane detection based on model information optimization. Building on previous works, we treat the observed depth readings as discrete random variables, with their probability distributions constrained by the ground truth planes. Various models containing different candidate plane constraints are then generated through repeated random sub-sampling to explain our observations. By incorporating the physics and noise model of the depth sensor, we can calculate the information for each model, and the model with the least information is accepted as the most likely ground truth. This information optimization process serves as an objective mechanism for determining the true number of planes and preventing false positive detections. Additionally, the quality of each detected plane can be ranked by summing the information reduction of inlier points for each plane. We validate these properties through experiments with synthetic data and find that our algorithm estimates plane parameters more accurately compared to the default Open3D RANSAC plane segmentation. Furthermore, we accelerate our algorithm by partitioning the depth map using neural network segmentation, which enhances its ability to generate more realistic plane parameters in real-world data.

【18】Interpretable Robot Control via Structured Behavior Trees and Large Language ModelsTitle: Interpretable Robot Control via Structured Behavior Trees and Large Language ModelsLink: https://arxiv.org/abs/2508.09621

Authors: éva Chekam, Ines Pastor-Martinez, Ali Tourani, Jose Andres Millan-Romera, Laura Ribeiro, Pedro Miguel Bastos Soares, Holger Voos, Jose Luis Sanchez-LopezNote: 15 pages, 5 figures, 3 tablesAbstract: As intelligent robots become more integrated into human environments, there is a growing need for intuitive and reliable Human-Robot Interaction (HRI) interfaces that are adaptable and more natural to interact with. Traditional robot control methods often require users to adapt to interfaces or memorize predefined commands, limiting usability in dynamic, unstructured environments. This paper presents a novel framework that bridges natural language understanding and robotic execution by combining Large Language Models (LLMs) with Behavior Trees. This integration enables robots to interpret natural language instructions given by users and translate them into executable actions by activating domain-specific plugins. The system supports scalable and modular integration, with a primary focus on perception-based functionalities, such as person tracking and hand gesture recognition. To evaluate the system, a series of real-world experiments were conducted across diverse environments. Experimental results demonstrate that the proposed approach is practical in real-world scenarios, with an average cognition-to-execution accuracy of approximately 94%, making a significant contribution to HRI systems and robots. The complete source code of the framework is publicly available at https://github.com/snt-arg/robot_suite.

【19】BEAVR: Bimanual, multi-Embodiment, Accessible, Virtual Reality Teleoperation System for RobotsTitle: BEAVR: Bimanual, multi-Embodiment, Accessible, Virtual Reality Teleoperation System for RobotsLink: https://arxiv.org/abs/2508.09606

Authors: Posadas-Nava, Alejandro Carrasco, Richard LinaresNote: Accepted for presentation on ICCR Kyoto 2025Abstract: BEAVR is an open-source, bimanual, multi-embodiment Virtual Reality (VR) teleoperation system for robots, designed to unify real-time control, data recording, and policy learning across heterogeneous robotic platforms. BEAVR enables real-time, dexterous teleoperation using commodity VR hardware, supports modular integration with robots ranging from 7-DoF manipulators to full-body humanoids, and records synchronized multi-modal demonstrations directly in the LeRobot dataset schema. Our system features a zero-copy streaming architecture achieving ≤35 ms latency, an asynchronous “think–act” control loop for scalable inference, and a flexible network API optimized for real-time, multi-robot operation. We benchmark BEAVR across diverse manipulation tasks and demonstrate its compatibility with leading visuomotor policies such as ACT, DiffusionPolicy, and SmolVLA. All code is publicly available, and datasets are released on Hugging Face.

【20】HapticGiant: A Novel Very Large Kinesthetic Haptic Interface with Hierarchical Force ControlTitle: HapticGiant: A Novel Very Large Kinesthetic Haptic Interface with Hierarchical Force ControlLink: https://arxiv.org/abs/2508.09595

Authors: ennell, Markus Walker, Dominik Pikos, Uwe D. HanebeckNote: Final Version – Accepted on IEEE Transactions on HapticsAbstract: Research in virtual reality and haptic technologies has consistently aimed to enhance immersion. While advanced head-mounted displays are now commercially available, kinesthetic haptic interfaces still face challenges such as limited workspaces, insufficient degrees of freedom, and kinematics not matching the human arm. In this paper, we present HapticGiant, a novel large-scale kinesthetic haptic interface designed to match the properties of the human arm as closely as possible and to facilitate natural user locomotion while providing full haptic feedback. The interface incorporates a novel admittance-type force control scheme, leveraging hierarchical optimization to render both arbitrary serial kinematic chains and Cartesian admittances. Notably, the proposed control scheme natively accounts for system limitations, including joint and Cartesian constraints, as well as singularities. Experimental results demonstrate the effectiveness of HapticGiant and its control scheme, paving the way for highly immersive virtual reality applications.

【21】ESCoT: An Enhanced Step-based Coordinate Trajectory Planning Method for Multiple Car-like RobotsTitle: ESCoT: An Enhanced Step-based Coordinate Trajectory Planning Method for Multiple Car-like RobotsLink: https://arxiv.org/abs/2508.09581

Authors: ang, Yihe Chen, Yibin Yang, Ruochen Li, Shaobing Xu, Jianqiang WangAbstract: Multi-vehicle trajectory planning is one of the key challenges in multi-robot systems and has broad applications across various fields. This paper presents ESCoT, an enhanced step-based coordinate trajectory planning method for multiple car-like robots. ESCoT incorporates two key strategies: collaborative planning for local robot groups and replanning for duplicate configurations. These strategies effectively enhance the performance of step-based MVTP methods. Through extensive experiments, we show that ESCoT 1) in sparse scenarios, significantly improves solution quality compared to baseline step-based method, achieving up to 70% improvement in typical conflict scenarios and 34% in randomly generated scenarios, while maintaining high solving efficiency; and 2) in dense scenarios, outperforms all baseline methods, maintaining a success rate of over 50% even in the most challenging configurations. The results demonstrate that ESCoT effectively solves MVTP, further extending the capabilities of step-based methods. Finally, practical robot tests validate the algorithm’s applicability in real-world scenarios.

【22】WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-LocalizationTitle: WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-LocalizationLink: https://arxiv.org/abs/2508.09560

Authors: n, Hang Yu, Zhedong ZhengNote: 13 pages, 4 figuresAbstract: Visual geo-localization for drones faces critical degradation under weather perturbations, e.g., rain and fog, where existing methods struggle with two inherent limitations: 1) Heavy reliance on limited weather categories that constrain generalization, and 2) Suboptimal disentanglement of entangled scene-weather features through pseudo weather categories. We present WeatherPrompt, a multi-modality learning paradigm that establishes weather-invariant representations through fusing the image embedding with the text context. Our framework introduces two key contributions: First, a Training-free Weather Reasoning mechanism that employs off-the-shelf large multi-modality models to synthesize multi-weather textual descriptions through human-like reasoning. It improves the scalability to unseen or complex weather, and could reflect different weather strength. Second, to better disentangle the scene and weather feature, we propose a multi-modality framework with the dynamic gating mechanism driven by the text embedding to adaptively reweight and fuse visual features across modalities. The framework is further optimized by the cross-modal objectives, including image-text contrastive learning and image-text matching, which maps the same scene with different weather conditions closer in the representation space. Extensive experiments validate that, under diverse weather conditions, our method achieves competitive recall rates compared to state-of-the-art drone geo-localization methods. Notably, it improves Recall@1 by +13.37% under night conditions and by 18.69% under fog and snow conditions.

【23】CaRoBio: 3D Cable Routing with a Bio-inspired Gripper FingernailTitle: CaRoBio: 3D Cable Routing with a Bio-inspired Gripper FingernailLink: https://arxiv.org/abs/2508.09558

Authors: o, Boyang Zhang, Fumin ZhangAbstract: The manipulation of deformable linear flexures has a wide range of applications in industry, such as cable routing in automotive manufacturing and textile production. Cable routing, as a complex multi-stage robot manipulation scenario, is a challenging task for robot automation. Common parallel two-finger grippers have the risk of over-squeezing and over-tension when grasping and guiding cables. In this paper, a novel eagle-inspired fingernail is designed and mounted on the gripper fingers, which helps with cable grasping on planar surfaces and in-hand cable guiding operations. Then we present a single-grasp end-to-end 3D cable routing framework utilizing the proposed fingernails, instead of the common pick-and-place strategy. Continuous control is achieved to efficiently manipulate cables through vision-based state estimation of task configurations and offline trajectory planning based on motion primitives. We evaluate the effectiveness of the proposed framework with a variety of cables and channel slots, significantly outperforming the pick-and-place manipulation process under equivalent perceptual conditions. Our reconfigurable task setting and the proposed framework provide a reference for future cable routing manipulations in 3D space.

【24】SMART-OC: A Real-time Time-risk Optimal Replanning Algorithm for Dynamic Obstacles and Spatio-temporally Varying CurrentsTitle: SMART-OC: A Real-time Time-risk Optimal Replanning Algorithm for Dynamic Obstacles and Spatio-temporally Varying CurrentsLink: https://arxiv.org/abs/2508.09508

Authors: al, Shalabh GuptaAbstract: Typical marine environments are highly complex with spatio-temporally varying currents and dynamic obstacles, presenting significant challenges to Unmanned Surface Vehicles (USVs) for safe and efficient navigation. Thus, the USVs need to continuously adapt their paths with real-time information to avoid collisions and follow the path of least resistance to the goal via exploiting ocean currents. In this regard, we introduce a novel algorithm, called Self-Morphing Adaptive Replanning Tree for dynamic Obstacles and Currents (SMART-OC), that facilitates real-time time-risk optimal replanning in dynamic environments. SMART-OC integrates the obstacle risks along a path with the time cost to reach the goal to find the time-risk optimal path. The effectiveness of SMART-OC is validated by simulation experiments, which demonstrate that the USV performs fast replannings to avoid dynamic obstacles and exploit ocean currents to successfully reach the goal.

【25】Reactive Model Predictive Contouring Control for Robot ManipulatorsTitle: Reactive Model Predictive Contouring Control for Robot ManipulatorsLink: https://arxiv.org/abs/2508.09502

Authors: oon, Woo-Jeong Baek, Jaeheung ParkNote: 8 pages, 7 figures, 3 tables, conference paper, Accepted for publication at IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS) 2025Abstract: This contribution presents a robot path-following framework via Reactive Model Predictive Contouring Control (RMPCC) that successfully avoids obstacles, singularities and self-collisions in dynamic environments at 100 Hz. Many path-following methods rely on the time parametrization, but struggle to handle collision and singularity avoidance while adhering kinematic limits or other constraints. Specifically, the error between the desired path and the actual position can become large when executing evasive maneuvers. Thus, this paper derives a method that parametrizes the reference path by a path parameter and performs the optimization via RMPCC. In particular, Control Barrier Functions (CBFs) are introduced to avoid collisions and singularities in dynamic environments. A Jacobian-based linearization and Gauss-Newton Hessian approximation enable solving the nonlinear RMPCC problem at 100 Hz, outperforming state-of-the-art methods by a factor of 10. Experiments confirm that the framework handles dynamic obstacles in real-world settings with low contouring error and low robot acceleration.

【26】DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language NavigationTitle: DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language NavigationLink: https://arxiv.org/abs/2508.09444

Authors: Shi, Xiang Deng, Zaijing Li, Gongwei Chen, Yaowei Wang, Liqiang NieAbstract: Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typically use a two-stage waypoint planning framework, where a high-level waypoint predictor generates the navigable waypoints, and then a navigation planner suggests the intermediate goals in the high-level action space. However, this two-stage decomposition framework suffers from: (1) global sub-optimization due to the proxy objective in each stage, and (2) a performance bottleneck caused by the strong reliance on the quality of the first-stage predicted waypoints. To address these limitations, we propose DAgger Diffusion Navigation (DifNav), an end-to-end optimized VLN-CE policy that unifies the traditional two stages, i.e. waypoint generation and planning, into a single diffusion policy. Notably, DifNav employs a conditional diffusion policy to directly model multi-modal action distributions over future actions in continuous navigation space, eliminating the need for a waypoint predictor while enabling the agent to capture multiple possible instruction-following behaviors. To address the issues of compounding error in imitation learning and enhance spatial reasoning in long-horizon navigation tasks, we employ DAgger for online policy training and expert trajectory augmentation, and use the aggregated data to further fine-tune the policy. This approach significantly improves the policy’s robustness and its ability to recover from error states. Extensive experiments on benchmark datasets demonstrate that, even without a waypoint predictor, the proposed method substantially outperforms previous state-of-the-art two-stage waypoint-based models in terms of navigation performance. Our code is available at: https://github.com/Tokishx/DifNav.

【27】Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal NavigationTitle: Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal NavigationLink: https://arxiv.org/abs/2508.09423

Authors: Ren-jie Lu, Yu Zhou, Jingke Meng, Wei-shi ZhengAbstract: The Object Goal Navigation (ObjectNav) task challenges agents to locate a specified object in an unseen environment by imagining unobserved regions of the scene. Prior approaches rely on deterministic and discriminative models to complete semantic maps, overlooking the inherent uncertainty in indoor layouts and limiting their ability to generalize to unseen environments. In this work, we propose GOAL, a generative flow-based framework that models the semantic distribution of indoor environments by bridging observed regions with LLM-enriched full-scene semantic maps. During training, spatial priors inferred from large language models (LLMs) are encoded as two-dimensional Gaussian fields and injected into target maps, distilling rich contextual knowledge into the flow model and enabling more generalizable completions. Extensive experiments demonstrate that GOAL achieves state-of-the-art performance on MP3D and Gibson, and shows strong generalization in transfer settings to HM3D. Codes and pretrained models are available at https://github.com/Badi-Li/GOAL.

【28】CLF-RL: Control Lyapunov Function Guided Reinforcement LearningTitle: CLF-RL: Control Lyapunov Function Guided Reinforcement LearningLink: https://arxiv.org/abs/2508.09354

Authors: Zachary Olkin, Yisong Yue, Aaron D. AmesNote: 8 pages; 8 figuresAbstract: Reinforcement learning (RL) has shown promise in generating robust locomotion policies for bipedal robots, but often suffers from tedious reward design and sensitivity to poorly shaped objectives. In this work, we propose a structured reward shaping framework that leverages model-based trajectory generation and control Lyapunov functions (CLFs) to guide policy learning. We explore two model-based planners for generating reference trajectories: a reduced-order linear inverted pendulum (LIP) model for velocity-conditioned motion planning, and a precomputed gait library based on hybrid zero dynamics (HZD) using full-order dynamics. These planners define desired end-effector and joint trajectories, which are used to construct CLF-based rewards that penalize tracking error and encourage rapid convergence. This formulation provides meaningful intermediate rewards, and is straightforward to implement once a reference is available. Both the reference trajectories and CLF shaping are used only during training, resulting in a lightweight policy at deployment. We validate our method both in simulation and through extensive real-world experiments on a Unitree G1 robot. CLF-RL demonstrates significantly improved robustness relative to the baseline RL policy and better performance than a classic tracking reward RL formulation.

【29】How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled AutonomyTitle: How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled AutonomyLink: https://arxiv.org/abs/2508.09346

Authors: Mao, Mrinall Eashaan Umasudhan, Ivan RuchkinAbstract: Autonomous robots that rely on deep neural network controllers pose critical challenges for safety prediction, especially under partial observability and distribution shift. Traditional model-based verification techniques are limited in scalability and require access to low-dimensional state models, while model-free methods often lack reliability guarantees. This paper addresses these limitations by introducing a framework for calibrated safety prediction in end-to-end vision-controlled systems, where neither the state-transition model nor the observation model is accessible. Building on the foundation of world models, we leverage variational autoencoders and recurrent predictors to forecast future latent trajectories from raw image sequences and estimate the probability of satisfying safety properties. We distinguish between monolithic and composite prediction pipelines and introduce a calibration mechanism to quantify prediction confidence. In long-horizon predictions from high-dimensional observations, the forecasted inputs to the safety evaluator can deviate significantly from the training distribution due to compounding prediction errors and changing environmental conditions, leading to miscalibrated risk estimates. To address this, we incorporate unsupervised domain adaptation to ensure robustness of safety evaluation under distribution shift in predictions without requiring manual labels. Our formulation provides theoretical calibration guarantees and supports practical evaluation across long prediction horizons. Experimental results on three benchmarks show that our UDA-equipped evaluators maintain high accuracy and substantially lower false positive rates under distribution shift. Similarly, world model-based composite predictors outperform their monolithic counterparts on long-horizon tasks, and our conformal calibration provides reliable statistical bounds.

【30】SegDAC: Segmentation-Driven Actor-Critic for Visual Reinforcement LearningTitle: SegDAC: Segmentation-Driven Actor-Critic for Visual Reinforcement LearningLink: https://arxiv.org/abs/2508.09325

Authors: Brown, Glen BersethAbstract: Visual reinforcement learning (RL) is challenging due to the need to learn both perception and actions from high-dimensional inputs and noisy rewards. Although large perception models exist, integrating them effectively into RL for visual generalization and improved sample efficiency remains unclear. We propose SegDAC, a Segmentation-Driven Actor-Critic method. SegDAC uses Segment Anything (SAM) for object-centric decomposition and YOLO-World to ground segments semantically via text prompts. It includes a novel transformer-based architecture that supports a dynamic number of segments at each time step and effectively learns which segments to focus on using online RL, without using human labels. By evaluating SegDAC over a challenging visual generalization benchmark using Maniskill3, which covers diverse manipulation tasks under strong visual perturbations, we demonstrate that SegDAC achieves significantly better visual generalization, doubling prior performance on the hardest setting and matching or surpassing prior methods in sample efficiency across all evaluated tasks.

【31】Decision-Making-Based Path Planning for Autonomous UAVs: A SurveyTitle: Decision-Making-Based Path Planning for Autonomous UAVs: A SurveyLink: https://arxiv.org/abs/2508.09304

Authors: Teixeira Vivaldini, Robert Pěnička, Martin SaskaAbstract: One of the most critical features for the successful operation of autonomous UAVs is the ability to make decisions based on the information acquired from their surroundings. Each UAV must be able to make decisions during the flight in order to deal with uncertainties in its system and the environment, and to further act upon the information being received. Such decisions influence the future behavior of the UAV, which is expressed as the path plan. Thus, decision-making in path planning is an enabling technique for deploying autonomous UAVs in real-world applications. This survey provides an overview of existing studies that use aspects of decision-making in path planning, presenting the research strands for Exploration Path Planning and Informative Path Planning, and focusing on characteristics of how data have been modeled and understood. Finally, we highlight the existing challenges for relevant topics in this field.

【32】QuickGrasp: Lightweight Antipodal Grasp Planning with Point CloudsTitle: QuickGrasp: Lightweight Antipodal Grasp Planning with Point CloudsLink: https://arxiv.org/abs/2504.19716

Authors: ram Ravie, Keerthi Vasan M, Asokan Thondiyath, Bijo SebastianAbstract: Grasping has been a long-standing challenge in facilitating the final interface between a robot and the environment. As environments and tasks become complicated, the need to embed higher intelligence to infer from the surroundings and act on them has become necessary. Although most methods utilize techniques to estimate grasp pose by treating the problem via pure sampling-based approaches in the six-degree-of-freedom space or as a learning problem, they usually fail in real-life settings owing to poor generalization across domains. In addition, the time taken to generate the grasp plan and the lack of repeatability, owing to sampling inefficiency and the probabilistic nature of existing grasp planning approaches, severely limits their application in real-world tasks. This paper presents a lightweight analytical approach towards robotic grasp planning, particularly antipodal grasps, with little to no sampling in the six-degree-of-freedom space. The proposed grasp planning algorithm is formulated as an optimization problem towards estimating grasp points on the object surface instead of directly estimating the end-effector pose. To this extent, a soft-region-growing algorithm is presented for effective plane segmentation, even in the case of curved surfaces. An optimization-based quality metric is then used for the evaluation of grasp points to ensure indirect force closure. The proposed grasp framework is compared with the existing state-of-the-art grasp planning approach, Grasp pose detection (GPD), as a baseline over multiple simulated objects. The effectiveness of the proposed approach in comparison to GPD is also evaluated in a real-world setting using image and point-cloud data, with the planned grasps being executed using a ROBOTIQ gripper and UR5 manipulator.

【33】Safety Perspective on Assisted Lane Changes: Insights from Open-Road, Live-Traffic ExperimentsTitle: Safety Perspective on Assisted Lane Changes: Insights from Open-Road, Live-Traffic ExperimentsLink: https://arxiv.org/abs/2508.09233

Authors: nos Mattas, Sandor Vass, Gergely Zachar, Junyi Ji, Derek Gloudemans, Davide Maggi, Akos Kriston, Mohamed Brahmi, Maria Christina Galassi, Daniel B Work, Biagio CiuffoNote: 21 pages, 8 FiguresAbstract: This study investigates the assisted lane change functionality of five different vehicles equipped with advanced driver assistance systems (ADAS). The goal is to examine novel, under-researched features of commercially available ADAS technologies. The experimental campaign, conducted in the I-24 highway near Nashville, TN, US, collected data on the kinematics and safety margins of assisted lane changes in real-world conditions. The results show that the kinematics of assisted lane changes are consistent for each system, with four out of five vehicles using slower speeds and decelerations than human drivers. However, one system consistently performed more assertive lane changes, completing the maneuver in around 5 seconds. Regarding safety margins, only three vehicles are investigated. Those operated in the US are not restricted by relevant UN regulations, and their designs were found not to adhere to these regulatory requirements. A simulation method used to classify the challenge level for the vehicle receiving the lane change, showing that these systems can force trailing vehicles to decelerate to keep a safe gap. One assisted system was found to have performed a maneuver that posed a hard challenge level for the other vehicle, raising concerns about the safety of these systems in real-world operation. All three vehicles were found to carry out lane changes that induced decelerations to the vehicle in the target lane. Those decelerations could affect traffic flow, inducing traffic shockwaves.

Machine translation provided by Tencent Interactive Translation, for reference only

Click“Read the original text” to get the academic dispatch with summaries