外观
论文arXiv 2609.228291 个月前
Whole-Body UMI：通过实时运动生成将 UMI 操作技能迁移到类人机器人全身操作
原文链接：Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation（arXiv 2609.22829 · 发布日期：2026-09-19）
Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation
提出 WB-UMI，以端执行器条件实时运动生成，将 UMI 技能迁移到 G1 全身操作并在四项真机任务验证。
核心要点
- 类人操作全身示教依赖遥操作，成本高且难扩展。
- WB-UMI 用共享端执行器接口，解耦全身协调与任务语义学习。
- 扩散策略学原生 UMI 示教，运动生成器独立学重定向动捕。
- G1 真机四任务闭环迁移，成功率分别为 90%、80%、30%、40%。
验证范围与局限：验证限于 G1 真机上的抽屉关闭、货架取放、抛球和 Loco-PnP 四项任务。
英文摘要 (Abstract)
Collecting whole-body demonstrations for humanoid manipulation mostly relies on teleoperation, which is costly and hard to scale up. The Universal Manipulation Interface (UMI) provides a scalable data collection paradigm, but end-effector trajectories alone underdetermine humanoid whole-body coordination, which is insufficient for whole-body demonstration collection. Therefore, we introduce Whole-Body UMI (WB-UMI), a task-agnostic, real-time and end-effector conditioned motion generator that decouples whole-body coordination learning from task semantics learning through a shared end-effector interface. A diffusion policy learns from native UMI demonstrations, while WB-UMI learns independently from retargeted motion capture, requiring no body trackers or paired image--whole-body demonstrations during task-specific data collection. In real deployment, an asynchronous hierarchy integrates the diffusion policy, motion generator, and a whole-body controller with latency compensation and measured-state feedback. Real-robot experiments on G1 support real-time closed-loop transfer across four tasks, achieving 90% success in drawer closing, 80% in shelf pick-and-place, 30% in ball toss, and 40% in Loco-PnP, which shows the effectiveness of this hierarchy in transferring native UMI skills to humanoid whole-body manipulation.
作者：Yuxuan Nai, Leixin Chang, Liangjing Yang, Shuo Yang, Zhongyu Li
来源
本页事实对应的公开页面，以原文为准。