Bayesian Optimization Meets Hybrid Zero Dynamics: Safe Parameter Learning for Bipedal Locomotion Control

TL;DR

This paper introduces a hybrid Bayesian Optimization and Hybrid Zero Dynamics framework for safe, efficient learning of bipedal robot control parameters, enabling smooth and stable locomotion with minimal real-world trials.

Contribution

It presents a novel multi-domain learning approach combining simulation and real-world data for bipedal robot control without needing a pre-existing controller.

Findings

Successful transfer from simulation to real robot

Improved gait smoothness and stability

Reduced steady-state tracking errors

Abstract

In this paper, we propose a multi-domain control parameter learning framework that combines Bayesian Optimization (BO) and Hybrid Zero Dynamics (HZD) for locomotion control of bipedal robots. We leverage BO to learn the control parameters used in the HZD-based controller. The learning process is firstly deployed in simulation to optimize different control parameters for a large repertoire of gaits. Next, to tackle the discrepancy between the simulation and the real world, the learning process is applied on the physical robot to learn for corrections to the control parameters learned in simulation while also respecting a safety constraint for gait stability. This method empowers an efficient sim-to-real transition with a small number of samples in the real world, and does not require a valid controller to initialize the training in simulation. Our proposed learning framework is experimentally deployed and validated on a bipedal robot Cassie to perform versatile locomotion skills with improved performance on smoothness of walking gaits and reduction of steady-state tracking errors.