让机器人更灵活地完成推拉擦等力气活。
CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation
- 事后扰动法动态调节末端执行器硬度
- 无需额外训练即可完成多种用力任务
- 适合想提升机器人操作能力的研究者
近期人形机器人在敏捷运动方面取得进展，如后空翻、跑步和爬行。然而，要完成推物、擦除、推车等用力操作仍具挑战。本文提出一种即插即用的自适应柔顺控制模块 CHIP（通过事后扰动实现人形机器人自适应柔顺控制），可在保持动态参考轨迹精准跟踪的同时，实现末端执行器刚度的可控调节。CHIP 实现简单，无需数据增强或额外奖励调参。实验表明，使用 CHIP 训练的通用运动追踪控制器，可完成多种需不同末端执行器柔顺性的用力操作，包括多机器人协作、擦拭、箱体递送和开门。
原文摘要 · Abstract (English)
Recent progress in humanoid robots has unlocked agile locomotion skills, including backflipping, running, and crawling. Yet it remains challenging for a humanoid robot to perform forceful manipulation tasks such as moving objects, wiping, and pushing a cart. We propose adaptive Compliance Humanoid control through hIsight Perturbation (CHIP), a plug-and-play module that enables controllable end-effector stiffness while preserving agile tracking of dynamic reference motions. CHIP is easy to implement and requires neither data augmentation nor additional reward tuning. We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks that require different end-effector compliance, such as multi-robot collaboration, wiping, box delivery, and door opening.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。