We address key challenges in Dataset Aggregation (DAgger) for real-world contact-rich manipulation: how to collect informative human correction data and how to effectively update policies with this new data. We introduce Compliant Residual DAgger (CR-DAgger), which contains two novel components: 1) a Compliant Intervention Interface that leverages compliance control, allowing humans to provide gentle, accurate delta action corrections without interrupting the ongoing robot policy execution; and 2) a Compliant Residual Policy formulation that learns from human corrections while incorporating force feedback and force control. Our system significantly enhances performance on precise contact-rich manipulation tasks using minimal correction data, improving base policy success rates by 64% on four challenging tasks (book flipping, belt assembly, cable routing, and gear insertion) while outperforming both retraining-from-scratch and finetuning approaches. Through extensive real-world experiments, we provide practical guidance for implementing effective DAgger in real-world robot learning tasks. Result videos are available at: https://compliant-residual-dagger.github.io

翻译：我们解决了现实世界中接触丰富操作任务中数据集聚合（DAgger）面临的关键挑战：如何收集信息丰富的人工校正数据，以及如何利用这些新数据有效更新策略。我们提出了顺从残差DAgger（CR-DAgger），该系统包含两个新颖组件：1）顺从干预接口——利用顺从控制技术，允许人类在不中断机器人策略持续执行的情况下提供轻柔而精确的增量动作校正；2）顺从残差策略框架——在整合力反馈与力控制的同时学习人类校正动作。我们的系统仅需少量校正数据即可显著提升精确接触操作任务的性能，在四项挑战性任务（书本翻页、皮带装配、线缆布线与齿轮插入）中将基础策略成功率提升64%，其表现同时优于从头训练与微调方法。通过大量现实世界实验，我们为在实际机器人学习任务中实施高效DAgger提供了实用指导。实验视频详见：https://compliant-residual-dagger.github.io