用扭矩控制让重型四足机器人在无速度感知下稳速行进
Towards Torque-Driven Reinforcement Learning for Quadruped Locomotion
- 直接控制电机扭矩，摆脱对速度观测的依赖
- 实现在粗糙地形上3.5米/秒、1.5弧度/秒的高速稳定行走
- 无需外部传感器，可自主上下楼梯，适合真实复杂场景
腿部机器人的强化学习正推动运动能力发展，展现其适应新地形的能力。传统方法基于位置控制，政策对地形变化适应性差，且需在观测中引入线速度状态估计。此外，这些方法多用于轻量小型四足机器人，受限于硬件难以完成高复杂度任务。本文探索面向重型高扭矩四足机器人的强化学习扭矩控制框架。该框架可在不依赖当前速度信息的情况下，实现粗糙地形上的有效行进与目标线速度跟踪。通过Nvidia Isaac Sim与Isaac Lab仿真，在Unitree B1四足机器人上验证，最高速度达3.5 m/s，转向角速度达1.5 rad/s。同时，机器人可自主完成上下楼梯动作，无需外感知传感器。
原文摘要 · Abstract (English)
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.
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。