Skip to main content

Research Repository

Advanced Search

The transfer of evolved artificial immune system behaviours between small and large scale robotic platforms

Whitbrook, Amanda; Aickelin, Uwe; Garibaldi, Jonathan M.

The transfer of evolved artificial immune system behaviours between small and large scale robotic platforms Thumbnail


Authors

Amanda Whitbrook

Uwe Aickelin

Jonathan M. Garibaldi



Contributors

Pierre Collet
Editor

N. Monmarch�
Editor

P. Legrand
Editor

M. Schoenauer
Editor

E. Lutton
Editor

Abstract

This paper demonstrates that a set of behaviours evolved in simulation on a miniature robot (epuck) can be transferred to a much larger scale platform (a virtual Pioneer P3-DX) that also differs in shape, sensor type, sensor configuration and programming interface. The chosen architecture uses a reinforcement learning-assisted genetic algorithm to evolve the epuck behaviours, which are encoded as a genetic sequence. This sequence is then used by the Pioneers as part of an adaptive, idiotypic artificial immune system (AIS) control architecture. Testing in three different simulated worlds shows that the Pioneer can use these behaviours to navigate and solve object-tracking tasks successfully, as long as its adaptive AIS mechanism is in place.

Citation

Whitbrook, A., Aickelin, U., & Garibaldi, J. M. (2009, October). The transfer of evolved artificial immune system behaviours between small and large scale robotic platforms. Presented at 9th International Conference, Evolution Artificielle, EA 2009, Strasbourg, France

Presentation Conference Type Edited Proceedings
Conference Name 9th International Conference, Evolution Artificielle, EA 2009
Start Date Oct 26, 2009
End Date Oct 28, 2009
Online Publication Date Oct 26, 2009
Publication Date Oct 26, 2009
Deposit Date Aug 11, 2011
Publicly Available Date Aug 11, 2011
Peer Reviewed Peer Reviewed
Pages 122–133
Series Title Lecture notes in computer science
Series Number 5975
Series ISSN 1611-3349
Book Title Artificial evolution
ISBN 9783642141553
DOI https://doi.org/10.1007/978-3-642-14156-0_11
Public URL https://nottingham-repository.worktribe.com/output/1013451
Publisher URL https://link.springer.com/chapter/10.1007/978-3-642-14156-0_11

Files





You might also like



Downloadable Citations