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
研究探索用于重型高扭矩四足机器人的强化学习扭矩控制框架，该框架能穿越崎岖地形并有效跟踪期望线速度，借助Isaac Sim和Isaac Lab在宇树B1上仿真，实现一定速度且能上下楼梯，无需外部感知传感器。
AI 中文摘要
用于腿式机器人的强化学习正在推动运动发展，展示了其适应新的挑战性地形的能力。传统上，这些强化学习运动框架基于位置，使得策略对地形类型的适应性较差，并且在观测空间中需要状态估计技术，即线速度。此外，这些强化学习框架通常使用小型、轻型四足机器人，由于硬件限制，它们在执行高复杂性任务时的可行性有限。这项工作探索了一种用于重型高扭矩四足机器人的强化学习扭矩控制框架。本文中的强化学习框架可以穿越崎岖地形并有效跟踪期望线速度，而无需了解智能体的当前速度。使用英伟达的Isaac Sim和Isaac Lab，在宇树B1四足机器人上展示了强化学习扭矩控制策略的仿真结果，实现了3.5米/秒的速度和1.5弧度/秒的角速度。此外，该四足机器人无需外部感知传感器就能上下楼梯。
英文摘要
Reinforcement learning (RL) for legged robots is advancing locomotion, demonstrating its ability to adapt to new and challenging terrain. Traditionally, these RL locomotion frameworks are position-based, making the policy less adaptable to terrain types and requiring state estimation techniques in the observation space, i.e., linear velocity. Moreover, these RL frameworks often use small, lightweight quadrupeds that are limited in their viability for high-complexity tasks due to hardware constraints. This work explores an RL torque control framework for heavyweight high-torque quadrupeds. The RL framework in this paper can traverse rough terrain and effectively track a desired linear velocity without requiring knowledge of the agent's current velocity. Using Nvidia's Isaac Sim and Isaac Lab, simulation results of the RL torque control policy are shown on the Unitree B1 quadruped, achieving speeds of 3.5 m/s and 1.5 rad/s. In addition, the quadruped can walk up and down stairs without the aid of an exteroceptive sensor.
Comments6 pages, 4 figures. Accepted manuscript. Published in the 2026 IEEE/SICE International Symposium on System Integration (SII), pp. 1259-1264
Journal ref2026 IEEE/SICE International Symposium on System Integration (SII), pp. 1259-1264 (2026)
DOI：10.1109/SII64115.2026.11404550
