外观
论文arXiv 2609.3755229 天前
Wrench-ACT：使用直接力/力矩控制增强机器人策略的接触丰富行为
原文链接：Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control（arXiv 2609.37552 · 发布日期：2026-09-29）
Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control
提出仅输出力/力矩并由纯力控制器执行的模仿学习策略，在五个接触丰富操作任务上验证并匹配或超过位置基线。
核心要点
- 接触丰富操作需要主动调节交互力，而现有学习策略多以目标位置或位姿表示动作。
- 方法以 ACT 为基础，训练单任务模型，从双边力/力矩示范中预测唯一动作输出。
- 五个任务评估显示，wrench 策略在所有任务上匹配或超过位置基线。
- 消融表明双边采集界面与 wrench 动作空间各自独立提升性能，并计划发布千余示范。
验证范围与局限：验证范围为五个接触丰富操作任务上的单任务模型。
英文摘要 (Abstract)
While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly represent actions as target positions or poses. Even methods that incorporate force sensing either use it solely as an observation or, when predicting forces as part of the output, rely on a hybrid force controller. In this paper, we propose an imitation learning policy that predicts wrenches as its sole action output for direct use by a pure force controller. Our studies suggest that force-domain imitation learning depends critically on data collection, with force-feedback teleoperation improving policy performance by capturing the operator's deliberate force regulation. Using Action Chunking with Transformers (ACT) as the base architecture, we train single-task models on bilateral wrench demonstrations and evaluate them on five contact-rich manipulation tasks. The wrench policy matches or outperforms position-based baselines across all tasks, with gains varying according to the degree of deliberate force regulation each task requires. Cross-condition ablations show that the bilateral data collection interface and the wrench action space each contribute independently to performance. To support further research, we will release over 1000 wrench-action demonstrations spanning these tasks on a companion website upon publication.
作者：Johannes Hechtl, Yannik Blei, Simon Ball, Reihaneh Mirjalili, Michael Krawez, Seongjin Bien, Philipp Schmitt, Wolfram Burgard
来源
本页事实对应的公开页面，以原文为准。