SYNLOCO: Synthesizing Central Pattern Generator and Reinforcement Learning for Quadruped Locomotion

TL;DR

This paper introduces SYNLOCO, a novel quadruped locomotion framework that combines Central Pattern Generators and Reinforcement Learning to produce stable, adaptable, and natural gaits across diverse terrains and conditions.

Contribution

The paper presents a new method synthesizing CPG and RL for quadruped locomotion, including a two-phased training strategy and performance metrics to enhance robustness and adaptability.

Findings

SYNLOCO generates consistent gaits across various terrains and speeds.

The framework demonstrates resilience to parameter variations.

Empirical tests on Unitree GO1 show improved stability and adaptability.

Abstract

The Central Pattern Generator (CPG) is adept at generating rhythmic gait patterns characterized by consistent timing and adequate foot clearance. Yet, its open-loop configuration often compromises the system's control performance in response to environmental variations. On the other hand, Reinforcement Learning (RL), celebrated for its model-free properties, has gained significant traction in robotics due to its inherent adaptability and robustness. However, initiating traditional RL approaches from the ground up presents computational challenges and a heightened risk of converging to suboptimal local minima. In this paper, we propose an innovative quadruped locomotion framework, SYNLOCO, by synthesizing CPG and RL that can ingeniously integrate the strengths of both methods, enabling the development of a locomotion controller that is both stable and natural. Furthermore, we introduce a set of performance-driven reward metrics that augment the learning of locomotion control. To optimize the learning trajectory of SYNLOCO, a two-phased training strategy is presented. Our empirical evaluation, conducted on a Unitree GO1 robot under varied conditions--including distinct velocities, terrains, and payload capacities--showcases SYNLOCO's ability to produce consistent and clear-footed gaits across diverse scenarios. The developed controller exhibits resilience against substantial parameter variations, underscoring its potential for robust real-world applications.