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

Authors:
J. H. Walker;S. M. Garrett;M. S. Wilson
Affiliations:
Dept. of Comput. Sci., Univ. of Wales, Aberystwyth, UK;-;-
Venue:
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Year:
2006

Citing 0
Cited 12

An Idiotypic Immune Network as a Short-Term Learning Architecture for Mobile Robots

ICARIS '08 Proceedings of the 7th international conference on Artificial Immune Systems
Fitness functions in evolutionary robotics: A survey and analysis

Robotics and Autonomous Systems
Is situated evolution an alternative for classical evolution?

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
What is situated evolution?

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Grammatical evolution of a robot controller

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot

Applied Soft Computing
On-line, on-board evolution of robot controllers

EA'09 Proceedings of the 9th international conference on Artificial evolution
The transfer of evolved artificial immune system behaviours between small and large scale robotic platforms

EA'09 Proceedings of the 9th international conference on Artificial evolution
Task allocation for robots using inspiration from hormones

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Racing to improve on-line, on-board evolutionary robotics

Proceedings of the 13th annual conference on Genetic and evolutionary computation
An on-line on-board distributed algorithm for evolutionary robotics

EA'11 Proceedings of the 10th international conference on Artificial Evolution
Vector-valued function estimation by grammatical evolution for autonomous robot control

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

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.