从可穿戴接口到灵巧策略：接触转移与触觉表征
From Wearable Interfaces to Dexterous Policies: Contact Shifts and Tactile Representations
- University of Florida（佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究探讨可穿戴接口几何形状对灵巧操作演示数据的影响，发现改进接口改变接触模式并提升触觉记录能力，基于其演示训练的策略成功率更高，证明采集硬件是数据生成过程的关键部分。
AI中文摘要：
与传统遥操作不同，可穿戴接口允许操作者通过自身手部运动直接与任务对象交互，从而收集灵巧演示。这种直接交互减少了对目标机器人的依赖，但也使采集硬件成为生成每个演示的物理过程的一部分。接口几何形状既影响任务执行方式，也影响为学习而记录的触觉观测。我们研究了DexUMI家族外骨骼的两个版本，它们共享相同的机器人命令定义、映射程序和触觉模块类型，但手侧几何形状不同。改进后的接口降低了报告的身体需求，提升了选定的设备评分，实现了在基线接口中因机械阻挡而无法进行的精确抓握中的触觉访问，并导致记录的接触产生任务相关变化。盖子扭转主要表现出接触位置的变化，而蛋盒打开主要表现出接触发生的变化。然后，我们使用二元聚合输入或空间加力输入训练匹配的策略。在盖子扭转和蛋盒打开任务上，使用改进接口演示训练的策略比使用基线演示训练的策略成功率更高，且存在显著的合并接口效应。在这两个任务以及另外两个任务（USB插入和烙铁拾取与放置）中，空间加力输入同样优于二元聚合。这些结果表明，可穿戴采集硬件是机器人学习数据生成过程的一部分。因此，此类接口不仅应通过操作者体验进行评估，还应通过它们可记录的触觉交互及其演示所支持的策略性能进行评估。
英文摘要：
Unlike conventional teleoperation, wearable interfaces allow operators to collect dexterous demonstrations through their own hand motions while directly interacting with task objects. This direct interaction reduces dependence on the target robot during collection, but it also makes the collection hardware part of the physical process that generates each demonstration. Interface geometry can influence both how a task is performed and what tactile observations are recorded for learning. We study two versions of a DexUMI-family exoskeleton that share the same robot command definition, mapping procedure, and tactile module type but differ in hand-side geometry. The revised interface reduces reported physical demand, improves selected device ratings, enables tactile access in a precision grasp that is mechanically blocked by the baseline, and produces task-dependent changes in recorded contact. Lid twisting primarily exhibits a change in contact location, whereas egg carton opening primarily exhibits a change in contact occurrence. We then train matched policies using either a binary aggregate input or a spatial-plus-force input. On lid twisting and egg carton opening, policies trained on revised-interface demonstrations achieve higher success than those trained on baseline demonstrations, with a significant pooled interface effect. Across these and two additional tasks, USB insertion and soldering tool pick and place, the spatial-plus-force input likewise outperforms binary aggregation. These results show that wearable collection hardware is part of the data-generation process for robot learning. Such interfaces should therefore be evaluated not only through operator experience, but also through the tactile interactions they make recordable and the policy performance their demonstrations support.
