Non-Gaited Legged Locomotion with Monte-Carlo Tree Search and Supervised Learning

TL;DR

This paper introduces a novel sampling-based and supervised learning approach to optimize legged robot gait sequences and timings, enabling real-time gait planning on hardware for complex terrains and perturbations.

Contribution

It presents a new method combining Monte-Carlo Tree Search and supervised learning to optimize gait planning, significantly improving real-time applicability over traditional methods.

Findings

Method performs well in simulation and hardware tests

Outperforms fixed gait control on various terrains

Enables real-time gait optimization for quadruped robots

Abstract

Legged robots are able to navigate complex terrains by continuously interacting with the environment through careful selection of contact sequences and timings. However, the combinatorial nature behind contact planning hinders the applicability of such optimization problems on hardware. In this work, we present a novel approach that optimizes gait sequences and respective timings for legged robots in the context of optimization-based controllers through the use of sampling-based methods and supervised learning techniques. We propose to bootstrap the search by learning an optimal value function in order to speed-up the gait planning procedure making it applicable in real-time. To validate our proposed method, we showcase its performance both in simulation and on hardware using a 22 kg electric quadruped robot. The method is assessed on different terrains, under external perturbations, and in comparison to a standard control approach where the gait sequence is fixed a priori.