Multi-Domain Walking with Reduced-Order Models of Locomotion

TL;DR

This paper introduces a novel multi-domain reduced-order model for robotic walking inspired by human locomotion, enabling versatile and robust gait behaviors on a complex bipedal robot.

Contribution

It presents a hybrid dynamical system framework and a multi-domain linear inverted pendulum model to achieve multi-domain walking on a high-DOF robot.

Findings

Successful implementation of multi-domain walking on Cassie robot

Achieved versatile speed-tracking performance

Demonstrated robust push recovery behaviors

Abstract

Drawing inspiration from human multi-domain walking, this work presents a novel reduced-order model based framework for realizing multi-domain robotic walking. At the core of our approach is the viewpoint that human walking can be represented by a hybrid dynamical system, with continuous phases that are fully-actuated, under-actuated, and over-actuated and discrete changes in actuation type occurring with changes in contact. Leveraging this perspective, we synthesize a multi-domain linear inverted pendulum (MLIP) model of locomotion. Utilizing the step-to-step dynamics of the MLIP model, we successfully demonstrate multi-domain walking behaviors on the bipedal robot Cassie -- a high degree of freedom 3D bipedal robot. Thus, we show the ability to bridge the gap between multi-domain reduced order models and full-order multi-contact locomotion. Additionally, our results showcase the ability of the proposed method to achieve versatile speed-tracking performance and robust push recovery behaviors.