发表机构
Siemens Research and Predevelopment; University of Technology Nuremberg（西门子研究与预开发; 纽伦堡工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Wrench-ACT，一种直接预测力/力矩作为动作输出的模仿学习策略，利用双边遥操作数据，在五个接触丰富任务上匹配或超越基于位置的方法，并发布超1000个演示。
AI 中文摘要
虽然接触丰富的操作需要对相互作用力进行精细调节，但近期机器人操作学习方法主要将动作表示为目标位置或姿态。即使结合力传感的方法，要么仅将其用作观测，要么在预测力作为输出的一部分时依赖混合力控制器。在本文中，我们提出一种模仿学习策略，该策略预测力/力矩作为其唯一动作输出，供纯力控制器直接使用。我们的研究表明，力域模仿学习关键依赖于数据收集，力反馈遥操作通过捕捉操作者的精细力调节来提高策略性能。以动作分块变换器（ACT）作为基础架构，我们在双边力/力矩演示上训练单任务模型，并在五个接触丰富操作任务上评估它们。力/力矩策略在所有任务上匹配或优于基于位置的方法，其增益因每个任务所需的精细力调节程度而异。跨条件消融实验表明，双边数据收集接口和力/力矩动作空间各自独立地贡献于性能。为了支持进一步研究，我们将在发表时在配套网站上发布涵盖这些任务的超过1000个力/力矩动作演示。
英文摘要
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.
