Automatic Controller Selection on a Humanoid Robot

Using Optimization Techniques

Master thesis (2021)

Authors

E.A. D'Elia Mechanical Engineering

Contributors

J. -B. Mouret INRIA (supervisor 1)
S. Ivaldi INRIA (supervisor 1)
J. Kober Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering (supervisor 1)
L. Laurenti Team Luca Laurenti - Mechanical, Maritime and Materials Engineering (supervisor 2)
Faculty
Mechanical Engineering
Copyright: © 2021 Evelyn D'Elia
Bayesian optimization Multi-objective optimization Humanoid robotics Task priority-based control
More Info
expand_more

Published Date

25-08-2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical Engineering

Abstract

Designing controllers for complex robots is not an easy task. Often, researchers hand-tune controllers for humanoid robots, but this is a time-consuming approach that yields a single controller which cannot generalize well to varied tasks. This thesis presents a method which uses the NSGA-II multi-objective optimization (MOO) algorithm with various training trajectories to output a diverse Pareto set of well-functioning controller weights and gains. The best of these are shown to also work well on the real Talos robot. The learned Pareto front is then used in a Bayesian optimization (BO) algorithm both as a search space and as a source of prior information in the initial mean estimate. This learning approach, which combines the two optimization methods, is capable of finding a suitable parameter set for a new trajectory within 20 trials and outperforms both BO in the continuous parameter search space and random search along the Pareto front. The few trials required for this formulation of BO suggest that it could feasibly be applied on the physical robot using a Pareto front generated in simulation.