外观
论文arXiv 2610.1959413 天前
RoboSpan发布29自由度全身遥操作平台与分层模块化协调策略
本文由 AI 根据公开内容整理，可能有误，请以原文为准：RoboSpan: Learning Modular Coordination Policies for High-DoF Whole-Body Mobile Manipulation with Teleoperation（arXiv 2610.19594）
核心内容
针对全身移动操作中运动异构性与长时序误差累积痛点，论文提出RoboSpan高自由度遥操作演示平台及分层模块化框架HMF。该平台支持29-DoF机器人系统，通过功能解耦与多模态感知融合，解决了现有遥操作系统缺乏灵巧触觉反馈及跨模块协同决策能力的问题，为复杂具身任务提供标准化数据采集与策略学习基础设施。
HMF将29-DoF动作空间解耦为手部精细操作、臂部姿态调整与底盘空间配置三分支，采用带跨模块交叉注意力的COMET Transformer实现动态信息交互。系统利用视觉语言模型进行层级任务分解以抑制时序误差传播，并引入全掌2D触觉表征编码分布式接触信号。物理实验表明，该方法在多项长时序全身任务中成功率比主流基线提高20%以上，验证了模块化协调策略在接触密集操作中的稳定性优势。
关键看点
- 动作空间解耦：HMF框架将29-DoF动作空间拆分为手、臂、底盘三独立分支，降低高维控制复杂度
- 跨模块协调模型：COMET Transformer引入模块间交叉注意力机制，实现全身动态信息交换与动作协同
- 触觉感知增强：采用全掌2D触觉表征编码分布式接触信号，弥补传统遥操作平台触觉反馈缺失短板
- 长时序性能验证：在29-DoF物理机器人上实测，长时序全身任务成功率较主流基线提升超20%
工程与产业观察
该工作证明了在高维全身移动操作中，通过架构层面的模块化解耦与跨模态注意力机制，可有效缓解长时序误差累积问题。其集成的全掌触觉表征与VLM驱动的任务分解范式，为构建高质量具身智能遥操作数据集及训练泛化性强的基础模型提供了可复现的工程路径，对解决非结构化环境下的精密操作具有参考价值。
英文摘要 (Abstract)
Whole-body mobile manipulation suffers from two fundamental challenges: inherent motion heterogeneity across locomotion, arm, and hand modules, and progressive error accumulation over long-horizon multi-stage tasks. Existing teleoperation platforms also lack integrated dexterous tactile sensing to support coordinated whole-body decision-making. This paper presents RoboSpan, a high-DoF whole-body teleoperation and demonstration platform, and the Hierarchical Modular Framework (HMF) for learning modular coordination policies. HMF functionally decouples the 29-DoF action space into fine hand manipulation, arm pose adjustment, and mobile-base spatial configuration branches, and introduces the Coordinated Modular Embodied Transformer (COMET) with inter-modular cross-attention to enable dynamic information exchange and action coordination. Vision-language model driven hierarchical task decomposition structurally suppresses temporal error propagation, while a full-palm 2D tactile representation encodes distributed contact signals for cross-module tactile empowerment. Experiments on a physical 29-DoF robot demonstrate that the proposed method achieves over 20% higher task success rate than mainstream baselines across a range of long-horizon whole-body tasks, markedly improving stability and robustness in contact-rich manipulation.
作者：Keqiang Ren, Xuecheng Ye, Hanyu Liu, Zhihua Wang, Tao Jian, Yunsheng Ma, Jiayi Wen, Xinran Li, Zhigong Song
来源
本页事实对应的公开页面，以原文为准。