Evolving Behaviour Trees for Swarm Robotics

Simon Jones, Matthew Studley, Sabine Hauert, Alan F T Winfield

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

351 Downloads (Pure)

Abstract

Controllers for swarms of robots are hard to design as swarm behaviour emerges from their interaction, and so controllers are often evolved. However, these evolved controllers are often difficult to understand, limiting our ability to predict swarm behaviour. We suggest behaviour trees are a good control architecture for swarm robotics, as they are comprehensible and promote modular reuse. We design a foraging task for kilobots and evolve a behaviour tree capable of performing that task, both in simulation and reality, and show the controller is compact and under- standable.
Original languageEnglish
Title of host publicationDistributed Autonomous Robotic Systems
Subtitle of host publication13th International Symposium on Distributed Autonomous Robotic Systems (DARS 2016)
PublisherSpringer
Pages487-501
Number of pages15
ISBN (Electronic)9783319730080
ISBN (Print)9783319730066
DOIs
Publication statusPublished - 14 Mar 2018
Event13th International Symposium on Distributed Autonomous Robotic Systems - Natural History Museum, London, United Kingdom
Duration: 6 Nov 20169 Nov 2016
http://dars2016.org

Publication series

NameSpringer Tracts in Advanced Robotics
PublisherSpringer
ISSN (Print)1610-7438

Conference

Conference13th International Symposium on Distributed Autonomous Robotic Systems
Abbreviated titleDARS 2016
CountryUnited Kingdom
CityLondon
Period6/11/169/11/16
Internet address

Fingerprint Dive into the research topics of 'Evolving Behaviour Trees for Swarm Robotics'. Together they form a unique fingerprint.

Cite this