Skip to main content

Research Repository

Advanced Search

Morpho-evolution with learning using a controller archive as an inheritance mechanism

Le Goff, Leni K.; Buchanan, Edgar; Hart, Emma; Eiben, Agoston E.; Li, Wei; De Carlo, Matteo; Winfield, Alan F.; Hale, Matthew F.; Woolley, Robert; Angus, Mike; Timmis, Jon; Tyrrell, Andy M.

Authors

Edgar Buchanan

Agoston E. Eiben

Wei Li

Matteo De Carlo

Alan F. Winfield

Matthew F. Hale

Robert Woolley

Mike Angus

Jon Timmis

Andy M. Tyrrell



Abstract

Most work in evolutionary robotics centres on evolving a controller for a fixed body-plan. However, previous studiessuggest that simultaneously evolving both controller and body-plan could open up many interesting possibilities. However, thejoint optimisation of body-plan and control via evolutionaryprocesses can be challenging in rich morphological spaces. Thisis because offspring can have body-plans that are very differentfrom either of their parents, leading to a potential mismatchbetween the structure of an inherited neural controller and thenew body. To address this, we propose a framework that combinesan evolutionary algorithm to generate body-plans and a learning algorithm to optimise the parameters of a neural controller. The topology of this controller is created once the body-plan of each offspring has been generated. The key novelty of the approach is to add an external archive for storing learned controllers that map to explicit ‘types’ of robots (where this is defined with respect to the features of the body-plan). By initiating learning froma controller with an appropriate structure inherited from thearchive, rather than from a randomly initialised one, we show that both the speed and magnitude of learning increases over time when compared to an approach that starts from scratch, using two tasks and three environments. The framework also provides new insights into the complex interactions between evolution and learning

Journal Article Type Article
Acceptance Date Jan 16, 2022
Online Publication Date Feb 2, 2022
Publication Date 2023-06
Deposit Date Feb 4, 2022
Publicly Available Date Feb 4, 2022
Journal IEEE Transactions on Cognitive and Developmental Systems
Print ISSN 2379-8920
Electronic ISSN 2379-8939
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
Volume 15
Issue 2
Pages 507-517
DOI https://doi.org/10.1109/tcds.2022.3148543
Keywords Evolutionary robotics, Embodied Intelligence
Public URL http://researchrepository.napier.ac.uk/Output/2842294

Files

Morpho-evolution With Learning Using A Controller Archive As An Inheritance Mechanism (accepted version) (2.1 Mb)
PDF







You might also like



Downloadable Citations