ReForce：学习力感知重定向以实现灵巧操作

中文摘要 AI 辅助

人类演示为灵巧操作提供了可扩展的数据源，但由于 embodiment 差距，将其迁移至机器人动作仍具挑战性。当前的重定向多为运动学层面，然而操作由力决定，力支配手与物体的交互及物体的运动。本文提出 ReForce，一种力感知重定向方法，可将人类运动与力转化为机器人动作以复现预期接触。ReForce 利用在大规模模拟交互上训练的通用力跟踪器，对运动学重定向动作预测残差以达到期望的力。它支持在线力感知遥操作与离线数据转换。在模拟环境及真实硬件上，ReForce 在纸杯抓取、钳子操作等接触丰富的任务中，实现了更低的力跟踪误差与更强的多指接触参与度。

英文摘要

Human demonstrations offer a scalable data source for dexterous manipulation, but transferring them to robot actions remains challenging due to the embodiment gap. Today's retargeting is mostly kinematic, yet manipulation is decided by force, which governs how the hand interacts with the object and how the object moves. In this paper, we present ReForce, a Force-aware Retargeting method that turns human motion and forces into robot actions that reproduce the intended contact. ReForce predicts a residual on the kinematically retargeted action to reach the desired force, using a general force tracker trained on large-scale simulation interactions. It supports both online force-aware teleoperation and offline data translation. In simulation and on real hardware, ReForce achieves lower force-tracking error and stronger multi-finger contact engagement on contact-rich tasks such as paper-cup grasping and tongs manipulation.

发表机构

• UC San Diego（加州大学圣迭戈分校）

机构由 AI 辅助整理，请以论文原文为准。