Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility

TL;DR

This paper introduces a hierarchical reinforcement learning framework that leverages flat-ground animal motion priors to enable quadruped robots to adapt to complex terrains with improved locomotion and obstacle avoidance.

Contribution

It presents a novel hierarchical RL approach combining pre-trained motion priors with residual learning for versatile quadruped locomotion in diverse environments.

Findings

Residual learning improves adaptation to uneven terrains.

Motion priors enhance motion regularization and naturalness.

Real-world tests confirm effective navigation on complex terrains.

Abstract

Reinforcement learning (RL)-based motion imitation methods trained on demonstration data can effectively learn natural and expressive motions with minimal reward engineering but often struggle to generalize to novel environments. We address this by proposing a hierarchical RL framework in which a low-level policy is first pre-trained to imitate animal motions on flat ground, thereby establishing motion priors. A subsequent high-level, goal-conditioned policy then builds on these priors, learning residual corrections that enable perceptive locomotion, local obstacle avoidance, and goal-directed navigation across diverse and rugged terrains. Simulation experiments illustrate the effectiveness of learned residuals in adapting to progressively challenging uneven terrains while still preserving the locomotion characteristics provided by the motion priors. Furthermore, our results demonstrate improvements in motion regularization over baseline models trained without motion priors under similar reward setups. Real-world experiments with an ANYmal-D quadruped robot confirm our policy's capability to generalize animal-like locomotion skills to complex terrains, demonstrating smooth and efficient locomotion and local navigation performance amidst challenging terrains with obstacles.