The balance between initial training and lifelong adaptation in evolving robot controllers

Type Article
Original languageEnglish
Pages (from-to)423-432
Number of pages10
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
Volume36
Issue number2
DOI
Publication statusPublished - 01 Apr 2006
Links
Permanent link
View graph of relations
Citation formats

Abstract

A central aim of robotics research is to design robots that can perform in the real world; a real world that is often highly changeable in nature. An important challenge for researchers is therefore to produce robots that can improve their performance when the environment is stable, and adapt when the environment changes. This paper reports on experiments which show how evolutionary methods can provide lifelong adaptation for robots, and how this evolutionary process was embodied on the robot itself. A unique combination of training and lifelong adaptation are used, and this paper highlights the importance of training to this approach.