外观
论文arXiv 2402.167962024-02-26
Exbody框架实现人形机器人全身表达控制与Sim2Real迁移
本文由 AI 根据公开内容整理，可能有误，请以原文为准：Expressive Whole-Body Control for Humanoid Robots（arXiv 2402.16796）
核心内容
针对人形机器人真实世界运动表达匮乏问题，研究团队提出Expressive Whole-Body Control（Exbody）框架。该方法利用图形学社区大规模人体动捕数据，在强化学习框架下训练全身控制策略。核心创新在于解耦控制目标：鼓励上半身高保真模仿参考动作，同时放松下肢模仿约束，仅要求其鲁棒跟踪给定速度指令，从而克服人形机器人与人类在自由度及物理能力上的巨大差异。
Exbody采用仿真训练结合Sim2Real迁移的技术路线，成功将策略部署至实体人形机器人。实验表明，该系统不仅支持多种步态风格切换，还能在真实物理环境中稳定执行握手、与人共舞等高动态交互任务。 extensive studies证实，相比直接模仿学习，这种分层约束机制有效弥合了仿真与现实的动力学鸿沟，显著提升了复杂动作生成的成功率与自然度。
关键看点
- 分层控制策略：上肢严格模仿参考动捕轨迹，下肢仅跟踪速度指令，解耦解决DoF与物理能力失配问题
- 数据迁移范式：复用图形学大规模人体动捕数据集，通过RL框架实现从数字人到实体机器人的跨域动作迁移
- Sim2Real验证：策略经仿真训练后零样本迁移至真机，实测支持多风格行走、握手及人机共舞等复杂交互
- 鲁棒性提升：放宽下肢运动学约束换取动态平衡裕度，确保在非结构化真实环境中执行 expressive motions 的稳定性
工程与产业观察
Exbody为具身智能提供了低成本获取高质量运动先验的工程范式。通过解耦上下肢控制目标，有效利用了海量非机器人专用动捕数据，降低了真机数据采集门槛。这对解决人形机器人‘小脑’运动中自然度与稳定性兼顾的难题具有重要参考价值，加速了生成式动作模型在实体硬件上的落地进程。
英文摘要 (Abstract)
Can we enable humanoid robots to generate rich, diverse, and expressive motions in the real world? We propose to learn a whole-body control policy on a human-sized robot to mimic human motions as realistic as possible. To train such a policy, we leverage the large-scale human motion capture data from the graphics community in a Reinforcement Learning framework. However, directly performing imitation learning with the motion capture dataset would not work on the real humanoid robot, given the large gap in degrees of freedom and physical capabilities. Our method Expressive Whole-Body Control (Exbody) tackles this problem by encouraging the upper humanoid body to imitate a reference motion, while relaxing the imitation constraint on its two legs and only requiring them to follow a given velocity robustly. With training in simulation and Sim2Real transfer, our policy can control a humanoid robot to walk in different styles, shake hands with humans, and even dance with a human in the real world. We conduct extensive studies and comparisons on diverse motions in both simulation and the real world to show the effectiveness of our approach.
作者：Xuxin Cheng, Yandong Ji, Junming Chen, Ruihan Yang, Ge Yang, Xiaolong Wang
来源
本页事实对应的公开页面，以原文为准。