Tuning Legged Locomotion Controllers via Safe Bayesian Optimization

TL;DR

This paper introduces a safe, data-efficient Bayesian optimization method for tuning legged robot controllers, effectively handling model mismatch and enabling diverse gait parameter tuning through safe exploration.

Contribution

It develops a model-free safe learning algorithm that automates control gain tuning and extends to multiple gait parameters for versatile, safe robot locomotion optimization.

Findings

Successfully tuned controllers in simulation and hardware

Achieved safer and more efficient gait parameter optimization

Demonstrated superior performance over baseline methods

Abstract

This paper presents a data-driven strategy to streamline the deployment of model-based controllers in legged robotic hardware platforms. Our approach leverages a model-free safe learning algorithm to automate the tuning of control gains, addressing the mismatch between the simplified model used in the control formulation and the real system. This method substantially mitigates the risk of hazardous interactions with the robot by sample-efficiently optimizing parameters within a probably safe region. Additionally, we extend the applicability of our approach to incorporate the different gait parameters as contexts, leading to a safe, sample-efficient exploration algorithm capable of tuning a motion controller for diverse gait patterns. We validate our method through simulation and hardware experiments, where we demonstrate that the algorithm obtains superior performance on tuning a model-based motion controller for multiple gaits safely.