Skip to main content

Research Repository

Advanced Search

A Quality-Diversity Approach to Evolving a Repertoire of Diverse Behaviour-Trees in Robot Swarms

Montague, Kirsty; Hart, Emma; Paechter, Ben; Nitschke, Geoff

Authors

Geoff Nitschke



Contributors

João Correia
Editor

Stephen Smith
Editor

Raneem Qaddoura
Editor

Abstract

Designing controllers for a swarm of robots such that collabo-rative behaviour emerges at the swarm level is known to be challenging. Evolutionary approaches have proved promising, with attention turning more recently to evolving repertoires of diverse behaviours that can be used to compose heterogeneous swarms or mitigate against faults. Here we extend existing work by combining a Quality-Diversity algorithm (MAP-Elites) with a Genetic-Programming (GP) algorithm to evolve repertoires of behaviour-trees that define the robot controllers. We compare this approach with two variants of GP, one of which uses an implicit diversity method. Our results show that the QD approach results in larger and more diverse repertoires than the other methods with no loss in quality with respect to the best solutions found. Given that behaviour-trees have the added advantage of being human-readable compared to neural controllers that are typically evolved, the results provide a solid platform for future work in composing heterogeneous swarms.

Citation

Montague, K., Hart, E., Paechter, B., & Nitschke, G. (2023). A Quality-Diversity Approach to Evolving a Repertoire of Diverse Behaviour-Trees in Robot Swarms. In J. Correia, S. Smith, & R. Qaddoura (Eds.), Applications of Evolutionary Computation: 26th European Conference, EvoApplications 2023, Held as Part of EvoStar 2023, Brno, Czech Republic, April 12–14, 2023, Proceedings (145-160). https://doi.org/10.1007/978-3-031-30229-9_10

Conference Name EVOStar 2023
Conference Location Brno, Czechia
Start Date Apr 12, 2023
End Date Apr 14, 2023
Acceptance Date Jan 18, 2023
Online Publication Date Apr 9, 2023
Publication Date Apr 10, 2023
Deposit Date Feb 20, 2023
Publicly Available Date Mar 28, 2024
Publisher Springer
Pages 145-160
Series Title Lecture Notes in Computer Science
Series Number 13989
Series ISSN 0302-9743
Book Title Applications of Evolutionary Computation: 26th European Conference, EvoApplications 2023, Held as Part of EvoStar 2023, Brno, Czech Republic, April 12–14, 2023, Proceedings
ISBN 9783031302282
DOI https://doi.org/10.1007/978-3-031-30229-9_10
Keywords Swarm-robotics, Quality-Diversity, Genetic-Programming

Files

A Quality-Diversity Approach To Evolving A Repertoire Of Diverse Behaviour-Trees In Robot Swarms (accepted version) (706 Kb)
PDF







You might also like



Downloadable Citations