RealDexUMI：用于灵巧机器人学习的可穿戴通用操作接口
RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning
AI总结：
提出RealDexUMI，一种基于共享灵巧末端执行器模块的可穿戴通用操作接口，通过掌侧同构遥操作手套实现无重定向、直观精确的手部控制，在八项真实机器人任务中平均成功率达88.75%。
摘要：
学习灵巧操作需要演示，这些演示在保持精细手-物体交互的同时，在部署时仍可执行。现有流程要么通过重定向或具身转换损失可部署的灵巧性，要么依赖特定机器人的遥操作，这种遥操作成本高昂且难以扩展，并且通常缺乏用于灵巧数据收集的直观、接触感知控制。我们提出RealDexUMI，一种围绕共享灵巧末端执行器模块构建的可穿戴通用操作接口，该模块集成了轻量级灵巧手、手内视觉和指尖触觉传感。掌侧同构遥操作手套将人类手指输入映射到机器人手关节命令，实现实时、无重定向、直观且精确的手部控制。共享的手和传感模块产生零间隙的末端执行器数据，在收集和部署之间具有匹配的手内观察、触觉信号、接触和手部动作。在涵盖精细、接触丰富、长时域和双臂操作的八项真实机器人任务中，基于RealDexUMI数据训练的策略平均成功率达到88.75%，能够泛化到未见过的初始姿态，并在三种具身之间迁移。网站：https://research.beingbeyond.com/realdexumi
英文摘要：
Learning dexterous manipulation requires demonstrations that preserve fine hand-object interactions while remaining executable at deployment. Existing pipelines either lose deployable dexterity through retargeting or embodiment conversion, or rely on robot-specific teleoperation that is costly to scale and often lacks intuitive, contact-aware control for dexterous data collection. We present RealDexUMI, a wearable universal manipulation interface built around a shared dexterous end-effector module that integrates a lightweight dexterous hand, in-hand vision, and fingertip tactile sensing. A palm-side isomorphic teleoperation glove maps human finger inputs to robot-hand joint commands, enabling real-time, retargeting-free, intuitive, and precise hand control. The shared hand and sensing modules yield zero-gap end-effector data, with matched in-hand observations, tactile signals, contacts, and hand actions between collection and deployment. Across eight real-robot tasks spanning fine-grained, contact-rich, long-horizon, and bimanual manipulation, policies trained on RealDexUMI data achieve an average success rate of 88.75%, generalize to unseen initial poses, and transfer across three embodiments. Website: https://research.beingbeyond.com/realdexumi
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。
