Adaptive Energy Regularization for Autonomous Gait Transition and Energy-Efficient Quadruped Locomotion

TL;DR

This paper introduces an adaptive energy-based reward strategy in reinforcement learning that enables quadruped robots to autonomously select energy-efficient gaits across speeds, improving stability and efficiency in simulation and real-world tests.

Contribution

It proposes a simplified, energy-centric reward function with adaptive weighting based on velocity, facilitating autonomous gait selection in quadruped robots without prior gait knowledge.

Findings

Robots autonomously select appropriate gaits at different speeds.

Energy efficiency and velocity tracking are improved over previous methods.

The approach works in both simulation and real-world environments.

Abstract

In reinforcement learning for legged robot locomotion, crafting effective reward strategies is crucial. Pre-defined gait patterns and complex reward systems are widely used to stabilize policy training. Drawing from the natural locomotion behaviors of humans and animals, which adapt their gaits to minimize energy consumption, we propose a simplified, energy-centric reward strategy to foster the development of energy-efficient locomotion across various speeds in quadruped robots. By implementing an adaptive energy reward function and adjusting the weights based on velocity, we demonstrate that our approach enables ANYmal-C and Unitree Go1 robots to autonomously select appropriate gaits, such as four-beat walking at lower speeds and trotting at higher speeds, resulting in improved energy efficiency and stable velocity tracking compared to previous methods using complex reward designs and prior gait knowledge. The effectiveness of our policy is validated through simulations in the IsaacGym simulation environment and on real robots, demonstrating its potential to facilitate stable and adaptive locomotion.