ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation

在大多数接触丰富的操作任务中，人类会施加随时间变化的力，以补偿视觉引导手轨迹中的误差。然而，现有机器人学习算法主要关注轨迹策略，对力相关技能的学习关注有限。为此，本文提出 ForceMimic：一个以力为中心的机器人学习系统，包括自然、具备力觉感知且无需机器人的示范采集系统，以及用于鲁棒接触操作的混合力—运动模仿学习算法。借助 ForceCapture，操作者可在 5 分钟内削完一根西葫芦，而力反馈遥操作需要超过 13 分钟且难以完成任务。基于采集数据，作者提出 HybridIL 训练以力为中心的模仿模型，并在机器人执行时用混合力—位控制原语拟合预测的 wrench—位姿参数。在西葫芦削皮任务中，该方法相较先进的纯视觉模仿学习方法取得了更鲁棒的策略，成功率相对提升 54.5%。

In most contact-rich manipulation tasks, humans apply time-varying forces to the target object, compensating for inaccuracies in the vision-guided hand trajectory. However, current robot learning algorithms primarily focus on trajectory-based policy, with limited attention given to learning force-related skills. To address this limitation, we introduce ForceMimic, a force-centric robot learning system, providing a natural, force-aware and robot-free robotic demonstration collection system, along with a hybrid force-motion imitation learning algorithm for robust contact-rich manipulation. Using the proposed ForceCapture system, an operator can peel a zucchini in 5 minutes, while force-feedback teleoperation takes over 13 minutes and struggles with task completion. With the collected data, we propose HybridIL to train a force-centric imitation learning model, equipped with hybrid force-position control primitive to fit the predicted wrench-position parameters during robot execution. Experiments demonstrate that our approach enables the model to learn a more robust policy under the contact-rich task of vegetable peeling, increasing the success rates by 54.5% relatively compared to state-of-the-art pure-vision-based imitation learning.