arXiv_RO
-
De-Risking Robotic Welding for In-Space Metal Joining Through Physics-Grounded Digital Twins
2026-10-15 14:14:10Zhou Daniel Hao, Umer Masood Chaudry, Robert Shaw, Andrew Cheney, Nick Ludford, Mark Sims, Hongbiao DongAbstract
Growing interest in in-space servicing, manufacturing, and assembly has renewed attention on reliable metal joining for modular construction and on-orbit repair. Robotic welding is promising, but reduced-gravity and low-pressure operation remains poorly characterised and flight-like tests are limited. The UK Space Agency-supported ISPARK project is developing a physics-grounded digital twin for structured process de-risking. This paper evaluates a model-based prototype combining a finite-volume thermal weld-pool model, Gaussian-process (GP) and neural-network surrogates, and a simulated six-axis manipulator. The reduced model includes solid-liquid phase change, effective thermocapillary transport, and a local-pressure parameter. Gravity is assessed separately through a hydrostatic-to-capillary pressure ratio and does not enter the thermal energy equation. Across repeated five-fold cross-validation, the GP has lower normalised mean absolute error than the neural network for all eight outputs. In 10 held-out boundary cases, 74 of 80 solver responses fall within nominal 90% GP predictive intervals. A three-output GP query takes 249 microseconds, including scaling and predictive variance. In a simulated UR5 L-shaped-seam study, a proportional controller adjusts the synergic power-source setting as travel speed falls near the corner. Finite-volume re-evaluation finds all 12 closed-loop operating points and 9 of 12 open-loop points within an illustrative 1.0-3.0 mm root-side-width band. These simulation results support using the framework to screen welding conditions and control strategies before experimental tests. Thermal-vacuum, targeted reduced-gravity, and robotic hardware-in-the-loop studies are needed to assess the model and controller.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21939
PDF
-
TS-WAM: Temporal Latent Actions and World-Action Coupling for Vision-Language Robot Control
2026-10-15 14:05:28Menghao Yin, Jiaju Yin, Xiyue Dong, Lixin Xu, Zhenhui Zhang, Ke Zhang, Yating Feng, Renjing XuAbstract
Many vision-language-action policies rely on action-labeled robot demonstrations and lack an explicit mechanism for predicting future visual states. These limitations hinder learning from action-free videos and can encourage overfitting to demonstration conditions, weakening generalization and robustness. We present TS-WAM, a lightweight Teacher-Student World-Action Model that addresses these challenges through self-supervised temporal learning and explicit future prediction. Its vlm-jepa framework learns from heterogeneous data, including robot demonstrations and action-free human videos, using an EMA target branch without requiring a separately trained external teacher. By coupling vlm-jepa with delta-lwm, TS-WAM learns to predict latent actions from the current observation and instruction and uses them to predict future visual features that guide action generation at inference. A unified end-to-end training architecture jointly optimizes temporal representation learning, visual dynamics, and robot control without a separate latent-action or world-model pretraining stage. The EMA target branch is removed at inference, keeping the deployed policy lightweight. Experiments on LIBERO, LIBERO-Plus, and SimplerEnv, together with real-world manipulation experiments on Franka Research 3 and RevoTron, demonstrate that TS-WAM achieves strong manipulation performance, generalization, and robustness.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21922
PDF
-
What Should Robot Policies Learn to Predict? Rethinking Supervision Targets in Vision-Language-Action Learning
2026-10-15 14:01:06Haitao Shen, Hanyu Liu, Yihan Lin, Huiping Liu, Junbo Cui, Daoheng Li, Yang Li, Jing Zhang, Wenxin Li, Yuan YaoAbstract
Vision-language-action (VLA) policies are typically trained with action prediction as the primary supervision signal, since robots ultimately execute actions. Auxiliary objectives such as latent-action (LA) and future-vision (FV) prediction are often added to improve policy learning, yet they compete with action prediction for the same training budget. We ask whether, under a fixed budget, allocating a substantial share of training samples to such objectives, rather than to further action prediction, can improve policy learning. We build a unified VLA framework that couples a two-stream multimodal diffusion transformer (MMDiT) with a sample-level router, which assigns each training sample to either action prediction or an auxiliary objective and thus makes supervision allocation explicit. Within this framework, we instantiate three LA targets based on LAPA and its DINO-feature variants, and three FV targets based on DINOv3, V-JEPA 2, and Wan2.2 representations. Across LIBERO, CALVIN, and four real-robot tasks, suitable LA and FV supervision outperforms action-only training under the same budget, even when action prediction receives no more than half of the training samples. FV generally outperforms LA, although the strongest LA target remains competitive on CALVIN. Diagnostic analyses suggest that DINO-based LA targets emphasize relative motion, whereas FV targets emphasize absolute position and task identity. We therefore argue that what robot policies learn to predict, and how training is allocated among these targets, should be treated as explicit design choices rather than defaulting to action-dominant training.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21915
PDF
-
Sub-Millisecond Reflexes for Continuous Physical Human-Robot Interaction
Abstract
Continuous physical human-robot interaction requires robots to rapidly adapt their control behaviour without interrupting task execution. However, existing ROS 2 control architectures rely on stop-to-switch mechanisms that introduce substantial delays and interrupt execution. We present an open-source, sub-millisecond reflex engine based on an enhanced ROS 2-compatible multimode controller that enables deterministic switching between control modalities and integrates reflex behaviours for mitigating contact hazards and kinematic limit violations. Experiments on a Franka Robotics manipulator demonstrate switching delays below 0.1 ms, more than four orders of magnitude faster than conventional ros2_control, while maintaining continuous operation during safety-critical events. In a multi-stage manipulation task, the proposed framework reduced execution time by 3.5% and peak trajectory jerk by more than threefold. By eliminating runtime middleware overhead, controller transitions are implemented as lock-free pointer operations, enabling reflex-level responsiveness within an open-source robotics framework.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21913
PDF
-
MAGMA: Multiplier-Augmented Geometric Motion Algorithm
2026-10-15 13:30:13C\'esar E. Ramos Chuquiure, Vansh Thakur, Challen Enninful Adu, Ram VasudevanAbstract
Solving optimal control problems for high-dimensional mechanical systems subject to constraints remains challenging due to nonlinear dynamics and non-convex feasible sets. This paper introduces MAGMA(Multiplier-Augmented Geometric Motion Algorithm), an Affine Geometric Heat Flow (AGHF)-based trajectory optimizer that incorporates an augmented Lagrangian framework solved via a primal-dual flow. A theoretical characterization of the primal-dual AGHF is provided, establishing that MAGMA is a gradient flow on an appropriately defined energy. MAGMA is validated across a variety of challenging trajectory generation problems with obstacles, state limits, and actuation limits. Comparative evaluations against state-of-the-art solvers demonstrate that MAGMA achieves high quality solutions with significantly reduced tuning effort on the hardest problems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21852
PDF
-
Time-Optimal Ergodic Retrieval
2026-10-15 13:08:23Christian Sulana, Christian Hughes, Ian AbrahamAbstract
Retrieval tasks are a form of search task where a robot must explore, find an object, and return with it as quickly as possible. Recent work in ergodic control has demonstrated time-optimal path planning for search tasks where visitation is proportionally matched, within some tolerance, to a given target distribution. However, these planners minimize the duration of a full deterministic search, while retrieval missions end their search at an unknown point in the trajectory and must return to a given base. In this work, we propose a new formulation of the time-optimal ergodic search problem that models detection as a Poisson process and minimizes total mission time by including the return phase in the objective. Experimental results show that time-optimal ergodic retrieval (TOER) achieves up to $19\%$ shorter mission durations relative to ergodic baselines and that this advantage grows as the return phase becomes more costly. Simulation and hardware implementations validate TOER's compatibility with environments of non-convex geometry as well as both 2D and 3D search domains.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21823
PDF
-
Trajectory-based Diffusion from One-shot Human Video for Generalizable Manipulation
2026-10-15 12:45:26Guoping Pan, Xinmiao Yu, Wannan Cao, Jincheng Li, Baolin Jiang, Yizhe Li, Yi Cheng, Houde LiuAbstract
Imitation learning enables robots to perform complex tasks by leveraging human-collected demonstrations. However, most existing approaches require labor-intensive data collection with additional teleoperation systems, which hinders scalability. Human videos represent a natural source of data that implicitly contain knowledge of manipulation behaviors. However, transferring them to robots remains challenging due to the visual domain gap and the absence of explicit action labels. In this work, we introduce TDV, a trajectory-based framework that leverages data generation to enable generalizable manipulation. TDV focuses on task-relevant objects by leveraging plug-and-play 6D pose estimation techniques to extract object trajectories from human videos, thereby mitigating the impact of irrelevant backgrounds and varying viewpoints. As a modality-agnostic intermediate representation, trajectories are inherently independent of the visual domains and different embodiments, enabling efficient data generation. Our method outperforms previous approaches on RLBench simulation tasks, achieving near 100\% success rates across seven tasks. In real-world experiments, TDV enables cross-embodiment generalization manipulation from one-shot human demonstrations by leveraging efficient trajectory generation techniques.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21792
PDF
-
Comfortably Stuck: Evaluation Pitfalls in Bench2Drive's Closed-Loop Protocol
2026-10-15 11:59:04Thomas Schwarzfischer, Emad Aghajanzadeh, Moritz Thoma, Nael Fasfous, Manoj Rohit Vemparala, Pierpaolo Mori, Daniel Mueller-Gritschneder, Ulf SchlichtmannAbstract
Closed-loop evaluation is widely regarded as a more faithful way to assess end-to-end (E2E) driving models than open-loop evaluation, and Bench2Drive, built on the CARLA simulator, has become the dominant benchmark for it. We show that its evaluation protocol itself contains pitfalls that can misrepresent the models scored on it. Bench2Drive's comfort metric, adapted from nuPlan, has several implementation errors and a segmentation scheme that rewards standing still, so it mostly measures how long a vehicle stays stationary, correlating with stationary time at r = 0.97 across eight models. We propose a corrected, distance-based metric that cuts that correlation to r = 0.06. Under it, the strong driving-score/comfort tradeoff the original metric reports is no longer detectable once models are compared at matched driving speed, which suggests that comfort trades against how fast a model drives rather than against how well it drives. We also uncover two pitfalls in how the harness supplies navigation signals: the default controller can replace a model's own steering with an angle toward the route target point, and the target point supplied at evaluation time can differ substantially from what a model saw in training. We demonstrate both on UniAD and VAD, where their effects differ sharply, and argue that future closed-loop evaluations should check for them. We will release all fixes as standalone code, so corrected comfort scores can be obtained from logged trajectories without re-running closed-loop simulation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21741
PDF
-
Uni-PNP: Unified Prehensile and Non-prehensile Policy Learning for Generalizable Object Pose Reaching
2026-10-15 11:53:10Wenxuan Zhu, Yuze Wang, Jiangran Lyu, Jiayi Chen, Yixin Zheng, Mi Yan, Li Yi, Zhizheng Zhang, He WangAbstract
Object manipulation often requires combining non-prehensile actions with grasping. However, existing approaches typically develop these capabilities separately and integrate them by sequencing distinct primitives through prescribed intermediate objectives, limiting the coordination of contact motions and grasping. Their integration also remains sensitive to object and gripper geometry and depends on particular environmental supports, complicating real-world deployment. We present Uni-PNP, a unified policy that jointly learns prehensile and non-prehensile manipulation for object pose reaching across diverse objects and grippers. To achieve this, we first pretrain a geometry encoder to predict contact-induced object motion using a contact-dynamics dataset constructed from simulated interactions between diverse objects and grippers. We then train the policy in a two-stage reinforcement learning curriculum from graspable objects to ungraspable peers, encouraging the discovery of non-prehensile interactions and their integration with grasping. Experiments show 76.39% success on hundreds of seen objects with grippers, and 57.91% on unseen peers, outperforming the strongest pose-reaching baseline by 20.52 and 17.79 percentage points, respectively. We also analyze emergent behaviors, including nonprehensile and prehensile repositioning, grasp acquisition that requires grasping after tipping, and table-assisted reorientation while grasping, and transfer to the real-world scenario. Project page available at this http URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21735
PDF
-
MAIA: Anticipating Interaction Anomalies in Contact-Rich Manipulation via Multimodal World Models
2026-10-15 11:11:27Yi Qiao, Maolin Zheng, Haoran Sun, Lujia Dong, Wenzhao LianAbstract
Reliable contact-rich manipulation requires detecting execution deviations early enough for corrective action. Yet most monitoring methods are reactive, identifying anomalies only after they become observable. Anticipating such anomalies is challenging because visual observations only partially reveal physical interaction, while planned actions describe intended motion rather than their actual physical consequences. We address this problem with MAIA, a multimodal framework for anomaly anticipation. Its vision-action-force world model learns nominal interaction dynamics and predicts the visual and force responses of planned actions, while a lightweight anomaly head predicts impending interaction anomalies. To enable systematic evaluation, we introduce CRIA, a real-world multimodal dataset of 2,852 trajectories spanning 18 contact-rich manipulation tasks, with frame-level annotations of anomaly onset and evolution. Experiments on both seen and novel tasks show that MAIA achieves more accurate anomaly discrimination than representative baselines while providing earlier warnings, with bACC scores of 0.765 and 0.710 and median anticipation lead times of 28.0 and 25.1 steps, respectively. Moreover, using these predictions for anomaly-aware action selection improves end-to-end task success from 52.6% to 61.5% without retraining the underlying manipulation policy. These results highlight the value of modeling future physical consequences for proactive anomaly anticipation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21686
PDF
-
Diffeomorphic Hidden-State Steering: Improving Imitation Learning Policy Robustness through Expert Hidden-State Geometry
Abstract
Small observation or action errors can compound during closed-loop execution and disrupt a trained imitation learning policy. We study whether the original expert demonstrations can improve robustness through test-time hidden-state steering without additional demonstrations or policy retraining. Our analysis of a trained policy finds that expert hidden-state variation is concentrated in relatively few dimensions, while the directions capturing this variation differ across regions. Motivated by this geometry, we propose Diffeomorphic Hidden-State Steering (DHS), which learns an invertible nonlinear coordinate map from expert hidden states obtained by replaying the demonstrations through the frozen policy. DHS attenuates coordinates with low expert variance more strongly than those with high variance, then maps the modified coordinates back to hidden-state space. This allows steering directions to vary with the current hidden state while retaining every coordinate. Across four simulated manipulation tasks, DHS improves mean success under observation noise over the unmodified Transformer policies. Controlled comparisons yield higher mean success with learned nonlinear coordinates than with linear coordinates under both hard projection and full-rank rescaling. Combining DHS with action smoothing improves mean success rate under observation noise in certain tasks compared with action smoothing alone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21666
PDF
-
SPEAR: Selective Preference Elicitation with Adaptive Rewards for VLM-Guided Robotic Manipulation
2026-10-15 10:02:57Zewen Wu, Ruizhe Liu, Pei Zhou, Feng Chen, Yanchao YangAbstract
Recent Vision-Language Models (VLMs) enable automated preference labeling for robotic manipulation, yet their deployment remains impractical since each query incurs substantial inference cost, while VLMs frequently abstain on visually challenging comparisons. We propose SPEAR, a framework that transforms VLMs into efficient preference oracles via two synergistic mechanisms. First, we design distinguishability-aware query selection to reduce abstention rates by targeting only informative and distinguishable comparisons. Second, we deploy an adaptive reward transition that bootstraps exploration with VLM-synthesized guidance before preference-based refinement. Experiments on the manipulation benchmarks demonstrate that SPEAR achieves 88.9% average success, outperforming baselines by 23.3 percentage points, while significantly reducing abstention and wall-clock training time on contact-rich tasks. SPEAR learns three Mobile ALOHA manipulation tasks fully online on real hardware, demonstrating end-to-end real-world applicability. By addressing query efficiency and exploration challenges, SPEAR establishes VLMs as practical preference oracles for scalable robot learning without manual reward engineering.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21621
PDF
-
A Flow-Theoretic Multimodal Control Framework Fusing Mental and Physical Engagement for Upper-Limb Rehabilitation
2026-10-15 09:36:19Jun Leng, Pengcheng Li, Hanze Wang, Shuxiang Guo, Junlin JiangAbstract
While Assist-as-Needed (AAN) control aims to maximize user participation in robot-assisted training, existing methods relying solely on physical metrics cannot distinguish muscular inability from mental disengagement, leading to suboptimal interventions. To address this ambiguity, a Flow-theoretic multimodal AAN framework is proposed, fusing EEG-based mental engagement and sEMG-based physical engagement into an adaptive impedance control strategy. A four-quadrant fuzzy decision engine translates these dual physiological metrics into continuous control policies. This enables the upper-limb exoskeleton to inject feedforward assistance during intent-execution mismatch (e.g., motor output attenuation despite mental focus) and escalate guiding stiffness to penalize mental distraction. The framework was validated with healthy participants against a state-of-practice sEMG-only AAN baseline. Kinematically and mechanically, the proposed framework reduced robotic energy expenditure by 71.9\% while maintaining precise trajectory tracking, confirming it elicited greater voluntary human effort. Physiologically, the system increased the time spent in the neuroplasticity zone (Flow State Ratio) from 4.6% to 42.8%. These results validate that decoupling and jointly regulating mental and physical states enhances the selectivity of robotic assistance, mitigating user passivity and sustaining the engagement crucial for motor learning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21590
PDF
-
Attribution-Gated Joint Estimation of Intention and Capability for Assist-as-Needed Upper-Limb Robots
2026-10-15 09:02:02Pengcheng Li, Shuxiang Guo, Hanze Wang, Jun Leng, Bin Wang, Mingchao DingAbstract
Assist-as-needed (AAN) control must distinguish between changes in intended motion and changes in effective voluntary torque capability, even though both can produce similar kinematic and interaction responses. A dual-measurand multimodal MHE-MPC architecture is developed as the base framework, in which the intended trajectory and the task-dependent effective voluntary torque capability are estimated online as distinct quantities, and both estimates are used to adapt robotic assistance. Building on this architecture, the ambiguity between the two update channels is formulated as a continuous credit-assignment problem and resolved by an attribution gate. A trajectory-change indicator is obtained from persistent corrective interaction, whereas a capability-change indicator is derived from the residual between normalized muscle activation and dynamics-reconstructed voluntary torque. Nine healthy participants completed factorial target-height-load trials and a pre-post fatigue cup-transport task. Without target-height input, the gated method generated correctly ordered Low-Middle-High references under every load: target changes were preferentially assigned to trajectory adaptation, whereas added load shifted adaptation toward the capability channel. It achieved the lowest RMSE in all nine conditions (0.017 rad versus 0.041 rad for ungated dual estimation and 0.127 rad for fixed-reference error-based AAN). Post-fatigue capability estimates decreased and assistance increased at all heights, supporting functional feasibility.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21534
PDF
-
Multi-Teacher On-Policy Distillation for Flow-Based Vision-Language-Action Models
2026-10-15 08:55:07Lichao Ni, Yuhan Liu, Pengfei Li, Guanghuan FangAbstract
Specialized vision-language-action (VLA) policies acquire strong domain-specific skills, yet consolidating these skills into one shared policy remains challenging. On-policy distillation (OPD) transfers teacher knowledge on inputs induced by the student, addressing the distribution mismatch encountered during deployment. For flow-based VLAs, this mismatch arises at two levels: environment observations and intermediate action-generation states. We propose a two-level on-policy distillation framework that couples student-driven environment interaction with teacher velocity supervision along student-generated action flow trajectories. Frozen domain specialists jointly supervise one student. After each update, the student collects new environment experience and generates fresh action-flow trajectories. Starting from a joint supervised fine-tuning (SFT) initialization, Velocity Loss OPD yields absolute success-rate gains of 22.55% on LIBERO-40, 33.4% on CALVIN five-instruction sequences, and 22.6% on Meta-World MT50. Compared with Action Loss OPD and Teacher-rollout SFT, it achieves absolute success-rate gains of 6.4-9.5% on LIBERO-40, 9.7-18.3% on CALVIN, and 3.2-4.2% on Meta-World MT50. Analysis by sequence length further shows larger success-rate gains on longer CALVIN sequences. These results demonstrate effective multi-domain capability consolidation through two-level on-policy supervision, with a single student deployed across domains.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21522
PDF
-
TRACE: Typed Reference-Aware Conversational Editing for Humanoid Motion Diffusion
2026-10-15 08:49:53Zejian Kang, Yifu Luo, Boyang Shen, Jingxuan Li, Zekai Chen, Zekun Shi, Yongxue Xu, Zhenyu Hou, Bingqian Wu, Shaolei Zhang, Wentao Yang, Xiangru HuangAbstract
Language-conditioned humanoid motion generation enables users to create and refine robot movements through natural language. The central challenge is to connect an underspecified request to concrete motion structure that can subsequently be revised relative to an accepted reference. We present TRACE, a generation and editing framework for the Unitree G1 humanoid robot built around typed, measurable kinematic quantities. Our insight is to ground generation conditions in paired training motions and editing goals in the current motion. A language model learns to predict support, root, and hand events from motion-derived supervision; their time-aligned encodings complement the original text in a diffusion generator. Gravity-referenced states and trajectory--contact objectives improve kinematic consistency. For editing, typed requests define body--time scopes and source-relative goals. A separate reference-conditioned diffusion editor uses these goals and revised events to realize changes, while sampling-time projection preserves protected state coordinates. Quantitative evaluation and human assessment show improved semantic alignment and motion quality over the compared methods. Controlled ablations support the value of motion-grounded conditioning and kinematic consistency, while multi-turn editing evaluations demonstrate more reliable execution of successive relative requests under shared preservation constraints. Together, these results support typed kinematic structure as a common basis for motion generation and reference-aware revision.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21515
PDF
-
Location-Based Safety Management with Wearable Seamless Indoor-Outdoor Positioning
2026-10-15 08:40:15Anh-Van Vu, Seungwoo Chae, Changmin Sung, Van-Tuan Nguyen, Dongsoo HanAbstract
Reliable worker localization is essential for real-time industrial safety management, but seamless outdoor-indoor positioning remains challenging. GNSS performs well outdoors yet degrades near buildings and fails indoors, while many indoor systems require costly infrastructure or extensive calibration. This paper presents a practical safety-oriented positioning system that uses resource-constrained wearable tags and a device-cloud split architecture for continuous outdoor-indoor worker tracking. The tag integrates GNSS, IMU, barometric sensing, LTE Cat-M communication, and performs lightweight sensor fusion, while the cloud server executes map-aware fusion for continuous tracking. Developed as an operational platform, the system also includes a database, a map tool, and a dashboard that provide real-time monitoring, geofencing-based access alerts, and safety and productivity analysis. Experiments with multiple participants, each walking an approximately 1400 m outdoor-indoor route, using LTE Cat-M communication, achieve mean errors of 1.32 m indoors and 3.30 m outdoors, while maintaining low positioning latency and efficient power consumption. These results demonstrate the feasibility of wearable-based seamless positioning for scalable real-time safety management.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21503
PDF
-
A 2D Image Feedback-Based Autonomous Endovascular Navigation Method: A Perception and Control Framework
2026-10-15 08:22:01Sheng Cao, Shuxiang Guo, Yonggan Yan, Jian Guo, Chunying Li, Bin Wang, Mingchao Ding, Yongxin Zhang, Yongwei Zhang, Pengfei Yang, Jianmin LiuAbstract
In endovascular interventions, physicians rely on planar DSA and X-ray fluoroscopy to interpret vessel anatomy and device motion, yet converting these images into feedback for autonomous navigation remains difficult. A perception and control method is formulated for two-dimensional image feedback. Vessel masks are converted into a labeled centerline graph, and device-tip estimates are projected onto a planned path to obtain progress, deviation, and direction. A rule-based controller uses these quantities for delivery, branch selection, probing, rollback, and recovery. The method was evaluated on a physical dual-device robotic platform in 65 closed-loop runs using simulator-rendered planar images across three paths. All runs reached at least 0.95 maximum observed guidewire progress; two runs (3.1%) met the prespecified failure rule of three or more autonomous stop events. The results establish route-level performance on the tested platform; clinical image sequences and broader anatomy remain to be evaluated.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21481
PDF
-
Policy-Aligned Predictive Verification for Adaptive VLA Action-Chunk Execution
2026-10-15 07:45:17Minkyu Kim, Junhoo Lee, Seungyeon Kim, Suhyun Jeon, Baekseung Kim, Donghoon Han, Nojun KwakAbstract
Vision-language-action (VLA) policies generate action sequences that reduce repeated inference, but deciding how much of each sequence to execute is critical to task success. Existing adaptive methods make this decision using generation stability or prediction agreement, yet these signals do not establish whether executing a candidate prefix preserves the ability to complete the task. We introduce a policy-aligned predictive verifier (PAV) that anticipates the consequences of candidate action prefixes and evaluates their compatibility with successful continuation before execution. Rather than using future prediction to generate actions, our method evaluates existing proposals in the VLA's internal task-conditioned representation space. To learn local judgments from terminal task outcomes, we combine trajectory-level survival supervision with a localization prior that preserves useful behavior within failed rollouts. The resulting validity scores guide execution-horizon selection. Evaluations with pi_0 and pi_0.5 across LIBERO, RoboTwin 2.0, and real-world manipulation show improved success-query trade-offs. These findings point toward a different role for future prediction in robotics, using it to assess how far to trust a policy's proposed actions rather than to generate new ones.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21434
PDF
-
MuSTMM: Learning Sound-Triggered Mobile Manipulation across Multiple Scenes
2026-10-15 07:40:22Hao Ju, Feng Yan, Zhihao Zhong, Heng Yang, Shaofei Huang, Zhedong ZhengAbstract
Sound-Triggered Mobile Manipulation (STMM) requires robots to respond to sound events by navigating to the associated objects and performing appropriate physical interactions. Existing STMM evaluations primarily vary object layouts within limited architectural structures, leaving challenges to unseen scenes insufficiently explored. We introduce Multi-scene Sound-Triggered Mobile Manipulation (MuSTMM), a dataset that combines spatial audio rendering and physical interaction across 31 scenes with diverse architectures and object layouts. MuSTMM contains 14.36 million precomputed binaural Room Impulse Responses (RIRs) and a scene-disjoint split for evaluating single-event and multi-event settings in unseen scenes. We further augment the Navigation Policy Model with explicit spatial memory that complements acoustic cues with observed geometry. Specifically, we accumulate pose-aligned depth observations in a shared coordinate frame and project this memory into an egocentric Bird's-Eye View (BEV) occupancy map. Fusing map features with sound context produces a goal descriptor that provides both target-location and scene-structure priors, guiding navigation to the target region required for subsequent physical interaction. This policy achieves a 2.60% success rate boost over existing methods, while component ablations further support the effectiveness of spatial memory. MuSTMM and the navigation policy provide a testbed for the new challenge of studying sound-triggered mobile manipulation in unseen scenes. The code and dataset will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21429
PDF
