Tuning Legged Locomotion Controllers via Safe Bayesian Optimization

Daniel Widmer, Dongho Kang, Bhavya Sukhija, Jonas Hübotter, Andreas Krause, Stelian Coros

Keywords: Legged Robotics, Bayesian Optimization, Controller Tuning, Locomotion, Machine Learning, Safe Learning

TL;DR: A safe learning approach to tune legged locomotion controllers via safe bayesian optimization to address the mismatch between the simplified model used in the control formulation and the real system.

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.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Video: https://youtu.be/zDBouUgegrU

Website: https://donghok.me/tuning-legged-locomotion-controllers/

Code: https://github.com/lasgroup/gosafeopt