arXiv 2512.003242026-09-29cs.ROcs.CVcs.HC

MILE：一种用于灵巧操作的指尖视觉触觉传感的机械同构外骨骼数据采集系统

MILE: A Mechanically Isomorphic Hand Exoskeleton and Visuotactile Robotic Hand for Data Collection in Dexterous Manipulation

State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China（机械系统与振动国家重点实验室，上海交通大学机械工程学院，上海200240，中国）；Shanghai Key Laboratory of Intelligent Robotics, Shanghai Jiao Tong University, Shanghai 200240, China（智能机器人上海重点实验室，上海交通大学，上海200240，中国）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室，上海，中国）；Humanoid Robot (Shanghai) Co., Ltd., Shanghai, China（上海人形机器人有限公司，上海，中国）

Jinda Du, Jieji Ren, Qiaojun Yu, Ningbin Zhang, Yu Deng, Xingyu Wei, Yufei Liu, Guoying Gu, Xiangyang Zhu

备注：: 18 pages including supplementary material

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有灵巧操作数据采集系统运动重定向不准确、效率低、缺乏高分辨率指尖触觉传感的问题，提出MILE系统，通过从人手到外骨骼再到机械手的机械同构设计，实现无重定向精确控制，并集成指尖视觉触觉模块，采集多模态数据集，显著提升遥操作成功率。

摘要：

模仿学习为灵巧手操作提供了一种有前景的方法，但其有效性受限于缺乏大规模、高保真度的数据。现有的数据采集流程存在运动重定向不准确、数据采集效率低以及缺乏高分辨率指尖触觉传感等问题。我们通过MILE系统解决了这一差距，该系统是一种从人手到外骨骼再到机械手协同设计的机械同构遥操作和数据采集系统。外骨骼基于人体手部人体测量学推导而来，机械手保持一对一的关节位置同构性，消除了非线性重定向，实现了精确、自然的控制。外骨骼的多关节平均绝对角度误差低于1度，而机械手集成了紧凑的指尖视觉触觉模块，提供高分辨率的触觉观测。基于这种无需重定向的接口，我们遥操作复杂的、接触密集的掌内操作，并高效地采集了一个多模态数据集，包含高分辨率指尖视觉触觉信号、RGB-D图像和关节位置。该遥操作管道的平均成功率提升了64%。与仅基于视觉的基线相比，加入指尖触觉观测后，成功率平均额外提高了25%，验证了数据集的保真度和实用性。更多详情请访问：this https URL。

英文摘要：

Dexterous robotic hands perform complex, contact-rich manipulation. Imitation learning provides a route to such skills, but collecting human demonstrations with accurate hand actions and rich tactile information remains a key bottleneck. We present MILE, a teleoperation-based data-collection system comprising the wearable MILE exoskeleton and the mechanically corresponding MILE-Tac robotic hand. Because human-hand anatomy and wearability place tighter constraints on the high-DoF wearable, our human-first design begins with the MILE exoskeleton, equipped with custom modular joint encoders for accurate joint-angle acquisition. We then design the MILE-Tac robotic hand to share the exoskeleton's selected kinematic topology and joint-axis arrangement while satisfying robot-side implementation constraints, and equip its fingertips with compact visuotactile sensor modules. This correspondence enables direct exoskeleton-to-robot joint-space command transfer without online task-space inverse-kinematics retargeting. During teleoperation, the system synchronously records task-specific visual observations, four fingertip visuotactile streams, robot-hand proprioception, and exoskeleton-derived action commands. In a four-task teleoperation benchmark, MILE achieved a mean success rate of 76%, compared with 28% and 8% for glove-based and vision-based baselines, respectively. For downstream imitation learning, we trained paired ACT and DP policies with and without tactile input on MILE-collected demonstrations. The tactile-input variants achieved higher success rates in all paired evaluations.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。