A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards

TL;DR

This paper presents a reinforcement learning framework with barrier-based style rewards that enables a single legged robot to learn multiple gaits and tasks, including terrain traversal and obstacle avoidance, without exteroceptive sensors.

Contribution

The work introduces a novel barrier-based reward method for flexible gait control and demonstrates its effectiveness on a real robot achieving diverse locomotion modes.

Findings

KAIST HOUND achieved quadruped, biped, and tripod locomotion

The robot galloped at 4.67 m/s and climbed stairs

Successfully traversed uneven terrain and obstacles

Abstract

This work introduces a model-free reinforcement learning framework that enables various modes of motion (quadruped, tripod, or biped) and diverse tasks for legged robot locomotion. We employ a motion-style reward based on a relaxed logarithmic barrier function as a soft constraint, to bias the learning process toward the desired motion style, such as gait, foot clearance, joint position, or body height. The predefined gait cycle is encoded in a flexible manner, facilitating gait adjustments throughout the learning process. Extensive experiments demonstrate that KAIST HOUND, a 45 kg robotic system, can achieve biped, tripod, and quadruped locomotion using the proposed framework; quadrupedal capabilities include traversing uneven terrain, galloping at 4.67 m/s, and overcoming obstacles up to 58 cm (67 cm for HOUND2); bipedal capabilities include running at 3.6 m/s, carrying a 7.5 kg object, and ascending stairs-all performed without exteroceptive input.