用强化学习让机器人动作更真实，避免滑倒和碰撞。
ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
- 双层优化+强化学习，自动调整动作适配机器人形态
- 在仿真和真实机器人上成功实现四足动物动作重定向
- 只需少量对应点，无需人工调参，适合非人形机器人
将人类运动数据重定向到机器人形态仍面临巨大挑战。现有方法常产生物理不一致现象，如脚部滑动、自碰撞或动力学不可行的动作，阻碍后续模仿学习。本文提出一种双层优化框架，联合调整参考动作以适应机器人形态，并使用强化学习训练跟踪策略。为使优化可行，我们推导了上层损失的近似梯度。该框架仅需稀疏的语义刚体对应关系，无需手动调参即可自动确定足够表达性的参数值，以保留不同形态下的特征动作。通过直接集成重定向与物理仿真，生成物理合理动作，促进鲁棒模仿学习。我们在仿真和硬件上验证方法，成功实现显著区别于人类形态的复杂动作重定向，包括向四足机器人重定向。
原文摘要 · Abstract (English)
Retargeting human kinematic reference motion onto a robot's morphology remains a formidable challenge. Existing methods often produce physical inconsistencies, such as foot sliding, self-collisions, or dynamically infeasible motions, which hinder downstream imitation learning. We propose a bilevel optimization framework that jointly adapts reference motions to a robot's morphology while training a tracking policy using reinforcement learning. To make the optimization tractable, we derive an approximate gradient for the upper-level loss. Our framework requires only a sparse set of semantic rigid-body correspondences and eliminates the need for manual tuning by identifying optimal values for a parameterization expressive enough to preserve characteristic motion across different embodiments. Moreover, by integrating retargeting directly with physics simulation, we produce physically plausible motions that facilitate robust imitation learning. We validate our method in simulation and on hardware, demonstrating challenging motions for morphologies that differ significantly from a human, including retargeting onto a quadruped.
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。