通过动态扰动关节力矩，提升仿真到现实的机器人行走控制鲁棒性。
Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection
- 训练时对关节力矩施加状态相关扰动，模拟真实世界差异。
- 在未见过的复杂现实差距下，行走策略鲁棒性显著增强。
- 适合需要高适应性的类人机器人控制任务研究者。
本文提出一种新颖的仿真实现到现实应用的控制策略训练方法，替代了以往依赖领域随机化的主流方法。传统方法仅在训练中随机化一组固定的仿真参数，而本方法在前向仿真阶段，向输入的关节力矩注入与状态相关的扰动，以更全面地模拟真实世界中的差异。实验表明，该方法使类人机器人行走策略在未见过的复杂现实偏差下表现出更强的鲁棒性。
原文摘要 · Abstract (English)
This paper proposes a novel alternative to existing sim-to-real methods for training control policies with simulated experiences. Prior sim-to-real methods for legged robots mostly rely on the domain randomization approach, where a fixed finite set of simulation parameters is randomized during training. Instead, our method adds state-dependent perturbations to the input joint torque used for forward simulation during the training phase. These state-dependent perturbations are designed to simulate a broader range of reality gaps than those captured by randomizing a fixed set of simulation parameters. Experimental results show that our method enables humanoid locomotion policies that achieve greater robustness against complex reality gaps unseen in the training domain.
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。