Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controller

TL;DR

This paper introduces a phase-guided reinforcement learning framework enabling quadruped robots to learn and transition between multiple gaits, including complex and mixed gaits, with smooth and robust control.

Contribution

It presents a novel phase-based control policy that simplifies multi-gait learning and transitions for quadruped robots, improving versatility and robustness.

Findings

Robot can perform walk, trot, pacing, and bounding gaits.

Transitions between gaits are smooth and reliable.

The method enables complex gait generation like rhythmic dancing.

Abstract

Gaits and transitions are key components in legged locomotion. For legged robots, describing and reproducing gaits as well as transitions remain longstanding challenges. Reinforcement learning has become a powerful tool to formulate controllers for legged robots. Learning multiple gaits and transitions, nevertheless, is related to the multi-task learning problems. In this work, we present a novel framework for training a simple control policy for a quadruped robot to locomote in various gaits. Four independent phases are used as the interface between the gait generator and the control policy, which characterizes the movement of four feet. Guided by the phases, the quadruped robot is able to locomote according to the generated gaits, such as walk, trot, pacing and bounding, and to make transitions among those gaits. More general phases can be used to generate complex gaits, such as mixed rhythmic dancing. With the control policy, the Black Panther robot, a medium-dog-sized quadruped robot, can perform all learned motor skills while following the velocity commands smoothly and robustly in natural environment.