让机器人站稳时模仿人上半身动作，避免失控。
EMP: Executable Motion Prior for Humanoid Robot Standing Upper-body Motion Imitation
- 用强化学习+动作重定向生成海量动作数据训练策略。
- 实测在仿真和真实机器人上都能稳定模仿人类动作。
- 新增可执行动作先验模块，自动调校动作保安全。
为支持类人机器人执行操作任务，需研究站立状态下上半身动作的稳定性。然而，类人机器人在站立姿态下的可控范围有限，影响整体稳定性。为此，我们提出一种基于强化学习的框架，使机器人在保持整体稳定的同时模仿人类上半身动作。方法首先设计一个动作重定向网络，生成大规模上半身动作数据集用于训练强化学习（RL）策略，从而实现对上半身动作目标的跟踪，并采用领域随机化提升鲁棒性。为避免超出机器人执行能力、确保安全与稳定，我们引入可执行动作先验（EMP）模块，根据机器人当前状态动态调整输入目标动作。该调整在保障站立稳定性的同时，最小化动作幅度变化。我们在仿真和真实世界中评估了该框架，验证了其实际可用性。
原文摘要 · Abstract (English)
To support humanoid robots in performing manipulation tasks, it is essential to study stable standing while accommodating upper-body motions. However, the limited controllable range of humanoid robots in a standing position affects the stability of the entire body. Thus we introduce a reinforcement learning based framework for humanoid robots to imitate human upper-body motions while maintaining overall stability. Our approach begins with designing a retargeting network that generates a large-scale upper-body motion dataset for training the reinforcement learning (RL) policy, which enables the humanoid robot to track upper-body motion targets, employing domain randomization for enhanced robustness. To avoid exceeding the robot's execution capability and ensure safety and stability, we propose an Executable Motion Prior (EMP) module, which adjusts the input target movements based on the robot's current state. This adjustment improves standing stability while minimizing changes to motion amplitude. We evaluate our framework through simulation and real-world tests, demonstrating its practical applicability.
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。