Achieving Stable High-Speed Locomotion for Humanoid Robots with Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning method combined with kinodynamic priors to enable humanoid robots to walk and run at high speeds with improved stability and velocity tracking.

Contribution

The novel KSLC approach integrates kinodynamic priors with deep RL to enhance high-speed locomotion stability and generalization in humanoid robots.

Findings

Successfully tracked 3.5 m/s velocity in simulation

Achieved more accurate velocity control than baseline

Validated robustness in high-fidelity simulation

Abstract

Humanoid robots offer significant versatility for performing a wide range of tasks, yet their basic ability to walk and run, especially at high velocities, remains a challenge. This letter presents a novel method that combines deep reinforcement learning with kinodynamic priors to achieve stable locomotion control (KSLC). KSLC promotes coordinated arm movements to counteract destabilizing forces, enhancing overall stability. Compared to the baseline method, KSLC provides more accurate tracking of commanded velocities and better generalization in velocity control. In simulation tests, the KSLC-enabled humanoid robot successfully tracked a target velocity of 3.5 m/s with reduced fluctuations. Sim-to-sim validation in a high-fidelity environment further confirmed its robust performance, highlighting its potential for real-world applications.