CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion

• Published in: IEEE robotics and automation letters Vol. 7; no. 4; pp. 1 - 8
• Main Authors: Bellegarda, Guillaume, Ijspeert, Auke
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.10.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bioinspired Robot Learning; Deep learning; Foot; Generators; Legged locomotion; Legged Robots; Locomotion; Machine Learning for Robot Control; Oscillators; Quadrupedal robots; Railroad car couplings; Reinforcement learning; Robot sensing systems; Robustness; Sensory feedback
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2022.3218167

In this letter, we present a method for integrating central pattern generators (CPGs), i.e. systems of coupled oscillators, into the deep reinforcement learning (DRL) framework to produce robust and omnidirectional quadruped locomotion. The agent learns to directly modulate the intrinsic oscillator...