Variable Stiffness for Robust Locomotion through Reinforcement Learning

TL;DR

This paper presents a reinforcement learning approach that incorporates variable stiffness control into legged robot locomotion, improving robustness, efficiency, and simplifying tuning across diverse terrains.

Contribution

It introduces a novel control paradigm integrating variable stiffness into the RL action space, enabling grouped stiffness control and robust transfer to outdoor terrains.

Findings

Variable stiffness policies outperform position control in velocity tracking and push recovery.

Hybrid joint-leg stiffness policies improve energy efficiency.

Method demonstrates robust outdoor walking despite training on flat terrain.

Abstract

Reinforcement-learned locomotion enables legged robots to perform highly dynamic motions but often accompanies time-consuming manual tuning of joint stiffness. This paper introduces a novel control paradigm that integrates variable stiffness into the action space alongside joint positions, enabling grouped stiffness control such as per-joint stiffness (PJS), per-leg stiffness (PLS) and hybrid joint-leg stiffness (HJLS). We show that variable stiffness policies, with grouping in per-leg stiffness (PLS), outperform position-based control in velocity tracking and push recovery. In contrast, HJLS excels in energy efficiency. Despite the fact that our policy is trained on flat floor only, our method showcases robust walking behaviour on diverse outdoor terrains, indicating robust sim-to-real transfer. Our approach simplifies design by eliminating per-joint stiffness tuning while keeping competitive results with various metrics.