Decentralized Motor Skill Learning for Complex Robotic Systems

TL;DR

This paper introduces DEMOS, a decentralized learning algorithm for robotic motor control inspired by biological limb control, enhancing robustness and transferability in complex robots.

Contribution

It proposes a novel decentralized motor learning method that automatically discovers motor groups, improving robustness and generalization over centralized policies.

Findings

Enhanced robustness against motor malfunctions

Improved transferability to new tasks

Maintained high performance in complex robots

Abstract

Reinforcement learning (RL) has achieved remarkable success in complex robotic systems (eg. quadruped locomotion). In previous works, the RL-based controller was typically implemented as a single neural network with concatenated observation input. However, the corresponding learned policy is highly task-specific. Since all motors are controlled in a centralized way, out-of-distribution local observations can impact global motors through the single coupled neural network policy. In contrast, animals and humans can control their limbs separately. Inspired by this biological phenomenon, we propose a Decentralized motor skill (DEMOS) learning algorithm to automatically discover motor groups that can be decoupled from each other while preserving essential connections and then learn a decentralized motor control policy. Our method improves the robustness and generalization of the policy without sacrificing performance. Experiments on quadruped and humanoid robots demonstrate that the learned policy is robust against local motor malfunctions and can be transferred to new tasks.