发表机构
University of Louisville（路易斯维尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究基于强化学习的四足动物运动，利用Isaac Sim和Isaac Lab训练，实现零样本模拟到现实策略，在宇树Go1硬件上验证，其速度跟踪性能佳，能从大干扰中恢复，实现特定线速度和角速度。
AI 中文摘要
近年来，基于学习的运动方法越来越受欢迎，展示了复杂腿部运动和全身控制的能力。强化学习（RL）作为运动的主要基于学习的方法，通常利用高性能模拟工具，提供可控且高效的训练和开发环境。然而，在模拟中表现良好的策略在物理系统上部署时经常遇到意外挑战，即模拟到现实的差距。这项工作提出了一个能够进行全身控制的强大RL运动框架。所提出的RL框架利用英伟达的新模拟工具Isaac Sim及其配套的RL框架Isaac Lab进行训练，实现了零样本模拟到现实策略。我们的策略在使用宇树Go1的物理硬件上进行了性能验证，实验结果表明，其速度跟踪性能与四足动物的集成控制器相似，具有更强的从大干扰中恢复的能力，实现了2.0 m/s的线速度和1.8 rad/s的角速度。
英文摘要
Learning-based approaches to locomotion have risen in popularity in recent years, showing the capability for complex legged locomotion and whole-body control. Reinforcement learning (RL), the primary learning-based approach for locomotion, often utilizes a high-performance simulation tool, providing a controlled and efficient training and development environment. However, policies that perform well in simulation frequently encounter unexpected challenges when deployed on a physical system, known as the sim-to-real gap. This work presents a robust RL locomotion framework capable of whole-body control. The proposed RL framework utilizes Nvidia's new set of simulation tools, Isaac Sim, and its companion RL framework, Isaac Lab, for training, achieving a zero-shot sim-to-real policy. The performance of our policy is validated on physical hardware using the Unitree Go1, with experimental results showing similar velocity tracking performance to the quadruped's integrated controller, with a greater ability to recover from large disturbances, and achieve linear velocities of 2.0 m/s and angular velocities of 1.8 rad/s.
Comments6 pages, 5 figures. Accepted manuscript. Published in the 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE), pp. 2194-2199
Journal ref2025 IEEE 21st International Conference on Automation Science and Engineering (CASE), pp. 2194-2199 (2025)
DOI：10.1109/CASE58245.2025.11163761
