用人类示范指导机器人抓取，提升复杂操作成功率。
Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration
- 以物体受力空间为桥梁，匹配人机动作相似性
- 在1831个任务上达82.12%成功率，支持长时序操作
- 可从手部或第三人称示范迁移，真实世界有效
灵巧机器人操作可受益于大量人类示范，但将示范转化为机器人策略仍具挑战。本文提出基于人类示范的接触力矩引导框架（CHORD），用于刚体与关节物体的长时序灵巧操作，核心思想是物体中心的接触力矩空间引导：将人与机器人的运动表示为对物体施加的力和力矩，通过诱导的瞬时运动度量相似性。该引导机制显著提升了强化学习在高接触场景下的可扩展性。我们进一步构建了一个大规模仿真基准，包含4,739个双手灵巧操作任务，源自动作捕捉数据集并结合自建视频重建。在1,831个基准任务上，CHORD平均成功率达82.12%，展现强大可扩展性。该方法还支持从仅手部或第三人称示范泛化至全身操作，成功率达90.77%，且学习到的策略可在开环与闭环设置下成功迁移到真实世界。
原文摘要 · Abstract (English)
Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging. We present Contact Wrench Guidance from Human Demonstration in Robotic Dexterous Manipulation (CHORD), a framework for long-horizon manipulation of rigid and articulated objects with reinforcement learning. The key idea is object-centric contact wrench space guidance: we represent human and robot motions by the forces and torques they can induce on the object, enabling similarity to be measured by the induced instantaneous motions. This guidance makes reinforcement learning more scalable for contact-rich dexterous manipulation. We further introduce a large-scale simulation benchmark with 4,739 bimanual dexterous manipulation tasks, constructed from motion-capture datasets and reconstructed in-house videos. Evaluated on 1,831 benchmark tasks, CHORD achieves an average success rate of 82.12%, demonstrating strong scalability. CHORD also generalizes to whole-body manipulation from hand-only and third-person demonstrations, achieving a 90.77% success rate, and the learned policies transfer to the real world in both open-loop and closed-loop settings.
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。