Mobile UMI: 用于移动操作的跨视角扩散策略与解耦动力学
Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulation
AI总结：
本文提出了一种无需硬件的演示框架Mobile UMI，通过三个组件解决移动模仿学习中的两个瓶颈问题：运动污染的动作标签和推理导致的执行延迟。核心方法是通过双摄像头捕捉全局和局部上下文，结合空间锚点统一视觉-惯性框架，并利用异步递推地执行器进行在线状态匹配，从而实现解耦的动力学和基座轨迹。
摘要：
在便携式演示接口上进行移动模仿学习面临两个耦合的瓶颈：由运动污染导致的动作标签和由于连续移动基座引起的推理诱导的执行延迟。最近的腕部安装接口降低了桌面数据收集的成本，但单个腕部视角无法捕捉基座导航所需的全局上下文。添加身体安装的摄像头会将人类行走与手部运动纠缠在一起。同时，生成策略引入了数百毫秒的推理延迟，在此期间，基座会经过预测的路径点，迫使在动作拼接处进行回退修正。本文提出了Mobile UMI，一种无需硬件的演示框架，通过三个组件解决这两个缺口。首先，双摄像头捕获系统记录以胸部为中心的全局上下文和以腕部为中心的局部交互，无需任何机器人存在。其次，基于ChArUco的一次性空间锚点统一了胸部和手部的视觉-惯性框架；手部姿态随后相对于胸部重新表达，以提取解耦的SE(3)操作和SE(2)基座轨迹。第三，异步递推地执行器执行在线状态匹配：每个生成的动作块都与当前物理姿态对齐，使过期的路径点在执行前被丢弃。整个系统在四个长周期家庭任务上进行了评估，在100次试验中平均成功率为83.8%。受控比较ACT和Diffusion Policy显示，仅胸部相对标签就缩小了大部分差距；在线状态匹配缩小了剩余差距。这些结果表明，在测试条件下，移动模仿学习中显式动力学分解与状态级延迟对齐相结合，提供了一种有效的解决方案，而无需对底层策略类别进行架构更改。
英文摘要：
Mobile imitation learning on portable demonstration interfaces faces two coupled bottlenecks: locomotion-contaminated action labels and inference-induced execution latency on a continuously moving base. Recent wrist-mounted interfaces lower the cost of tabletop data collection, yet a single wrist view does not capture the global context required for base navigation. Adding a body-mounted camera entangles human walking with hand motion. Meanwhile, generative policies introduce hundreds of milliseconds of inference latency, during which the base advances past predicted waypoints, forcing backward corrections at action splices. This paper presents Mobile UMI, a hardware-free demonstration framework that addresses both gaps through three components. First, a dual-camera capture system records chest-centric global context and wrist-centric local interaction without any robot present. Second, a one-shot ChArUco-based spatial anchor unifies the chest and hand visual-inertial frames; the hand pose is then re-expressed relative to the chest to extract decoupled SE(3) manipulation and SE(2) base trajectories. Third, an asynchronous receding-horizon executor performs online state matching: each generated action chunk is realigned with the current physical pose so that expired waypoints are discarded before execution. The full system is evaluated on four long-horizon household tasks, achieving an average success rate of 83.8% over 100 trials per task. Controlled comparisons against ACT and Diffusion Policy show that the chest-relative label alone closes much of the gap; online state matching closes the remainder. These results indicate that, for mobile imitation learning under the tested conditions, explicit kinematic factorization combined with state-level latency alignment provides an effective solution without requiring architectural changes to the underlying policy class.
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。
