Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy

TL;DR

This paper introduces SE-Policy, a symmetry-aware reinforcement learning framework for humanoid robots that improves coordination and task performance by embedding symmetry properties into the learning process.

Contribution

The paper presents a novel symmetry equivariant policy framework that enforces bilateral symmetry in DRL for humanoid robots, enhancing coordination and accuracy.

Findings

SE-Policy improves velocity tracking accuracy by up to 40%.

SE-Policy achieves better spatial-temporal coordination.

The approach is effective in both simulation and real-world tests.

Abstract

The human nervous system exhibits bilateral symmetry, enabling coordinated and balanced movements. However, existing Deep Reinforcement Learning (DRL) methods for humanoid robots neglect morphological symmetry of the robot, leading to uncoordinated and suboptimal behaviors. Inspired by human motor control, we propose Symmetry Equivariant Policy (SE-Policy), a new DRL framework that embeds strict symmetry equivariance in the actor and symmetry invariance in the critic without additional hyperparameters. SE-Policy enforces consistent behaviors across symmetric observations, producing temporally and spatially coordinated motions with higher task performance. Extensive experiments on velocity tracking tasks, conducted in both simulation and real-world deployment with the Unitree G1 humanoid robot, demonstrate that SE-Policy improves tracking accuracy by up to 40% compared to state-of-the-art baselines, while achieving superior spatial-temporal coordination. These results demonstrate the effectiveness of SE-Policy and its broad applicability to humanoid robots.