Discovery of skill switching criteria for learning agile quadruped locomotion

TL;DR

This paper presents a hierarchical reinforcement learning framework enabling quadruped robots to learn, switch between, and recover multi-skill locomotion seamlessly in real-world environments.

Contribution

It introduces a novel multi-skill learning approach with automatic skill switching based on goal distance, combining deep RL and optimization for agile quadruped locomotion.

Findings

Successful multi-skill locomotion on simulated and real quadruped robots

Automatic, smooth skill transitions based on goal proximity

Prompt recovery from unexpected failures during locomotion

Abstract

This paper develops a hierarchical learning and optimization framework that can learn and achieve well-coordinated multi-skill locomotion. The learned multi-skill policy can switch between skills automatically and naturally in tracking arbitrarily positioned goals and recover from failures promptly. The proposed framework is composed of a deep reinforcement learning process and an optimization process. First, the contact pattern is incorporated into the reward terms for learning different types of gaits as separate policies without the need for any other references. Then, a higher level policy is learned to generate weights for individual policies to compose multi-skill locomotion in a goal-tracking task setting. Skills are automatically and naturally switched according to the distance to the goal. The proper distances for skill switching are incorporated in reward calculation for learning the high level policy and updated by an outer optimization loop as learning progresses. We first demonstrated successful multi-skill locomotion in comprehensive tasks on a simulated Unitree A1 quadruped robot. We also deployed the learned policy in the real world showcasing trotting, bounding, galloping, and their natural transitions as the goal position changes. Moreover, the learned policy can react to unexpected failures at any time, perform prompt recovery, and resume locomotion successfully. Compared to discrete switch between single skills which failed to transition to galloping in the real world, our proposed approach achieves all the learned agile skills, with smoother and more continuous skill transitions.