Adaptive Control for Evolutionary Robotics

And its effect on learning directed locomotion

Master thesis (2020)

Authors

F. van Diggelen Mechanical Engineering

Contributors

R. Babuska Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering (mentor)
Guszti Eiben Vrije Universiteit Amsterdam (graduation committee member)
D. Dodou Medical Instruments & Bio-Inspired Technology - Mechanical, Maritime and Materials Engineering (coach)
C. Della Santina Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering (coach)
Faculty
Mechanical Engineering, Mechanical Engineering
Copyright: © 2020 Fuda van Diggelen
More Info
expand_more

Published Date

28-10-2020

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

This thesis is motivated by evolutionary robot systems where robot bodies and brains evolve simultaneously. In such a robot system, `birth' must be followed by `infant learning' by a learning method that works for various morphologies evolution may produce. Here we address the task of directed locomotion in modular robots with controllers based on Central Pattern Generators. We present a bio-inspired adaptive feedback mechanism that uses a forward model and an inverse model that can be learned on-the-fly. We compare two versions (a simple and a sophisticated one) of this concept to a traditional (open-loop) controller using Bayesian Optimization as a learning algorithm.
The experimental results show that the sophisticated version outperforms the simple one and the traditional controller. It leads to improvement in performance and more robust controllers that cope better with noise.

Files

Master_Thesis.pdf
(.pdf | 6.73 Mb)