Morphogenetic Engineering For Evolving Ant Colony Pheromone Communication

Hdl Handle:
http://hdl.handle.net/10034/621023
Title:
Morphogenetic Engineering For Evolving Ant Colony Pheromone Communication
Authors:
Vaughan, Neil
Abstract:
This research investigates methods for evolving swarm communication in a simulated colony of ants using pheromone when foriaging for food. This research implemented neuroevolution and obtained the capability to learn pheromone communication autonomously. Building on previous literature on pheromone communication, this research applies evolution to adjust the topology and weights of an artificial neural network which controls the ant behaviour. Comparison of performance is made between a hard-coded benchmark algorithm, a fixed topology ANN and neuroevolution of the ANN topology and weights. The resulting neuroevolution produced a neural network which was successfully evolved to achieve the task objective, to collect food and return it to the nest.
Affiliation:
University of Chester
Citation:
Vaughan, N. (2018-forthcoming). Morphogenetic Engineering For Evolving Ant Colony Pheromone Communication In Proceedings of Artificial Intelligence and Simulation of Behaviour (AISB2018). The Society for the Study of Artificial Intelligence and Simulation for Behaviour (AISB).
Publisher:
The Society for the Study of Artificial Intelligence and Simulation for Behaviour (AISB)
Journal:
Proceedings of Artificial Intelligence and Simulation of Behaviour (AISB2018)
Publication Date:
6-Apr-2018
URI:
http://hdl.handle.net/10034/621023
Additional Links:
http://www.aisb.org.uk/aisbpublications/93-aisb/publications/proceedings/91
Type:
Meetings and Proceedings
Language:
en
ISSN:
NA
Appears in Collections:
Computer Science

Full metadata record

DC FieldValue Language
dc.contributor.authorVaughan, Neilen
dc.date.accessioned2018-03-23T15:54:45Z-
dc.date.available2018-03-23T15:54:45Z-
dc.date.issued2018-04-06-
dc.identifier.citationVaughan, N. (2018-forthcoming). Morphogenetic Engineering For Evolving Ant Colony Pheromone Communication In Proceedings of Artificial Intelligence and Simulation of Behaviour (AISB2018). The Society for the Study of Artificial Intelligence and Simulation for Behaviour (AISB).en
dc.identifier.issnNA-
dc.identifier.urihttp://hdl.handle.net/10034/621023-
dc.description.abstractThis research investigates methods for evolving swarm communication in a simulated colony of ants using pheromone when foriaging for food. This research implemented neuroevolution and obtained the capability to learn pheromone communication autonomously. Building on previous literature on pheromone communication, this research applies evolution to adjust the topology and weights of an artificial neural network which controls the ant behaviour. Comparison of performance is made between a hard-coded benchmark algorithm, a fixed topology ANN and neuroevolution of the ANN topology and weights. The resulting neuroevolution produced a neural network which was successfully evolved to achieve the task objective, to collect food and return it to the nest.en
dc.language.isoenen
dc.publisherThe Society for the Study of Artificial Intelligence and Simulation for Behaviour (AISB)en
dc.relation.urlhttp://www.aisb.org.uk/aisbpublications/93-aisb/publications/proceedings/91en
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectAnt Colonyen
dc.subjectEvolutionary algorithmsen
dc.subjectNeuroevolutionen
dc.subjectartificial intelligenceen
dc.titleMorphogenetic Engineering For Evolving Ant Colony Pheromone Communicationen
dc.typeMeetings and Proceedingsen
dc.contributor.departmentUniversity of Chesteren
dc.identifier.journalProceedings of Artificial Intelligence and Simulation of Behaviour (AISB2018)en
dc.date.accepted2018-02-01-
or.grant.openaccessYesen
rioxxterms.funderRoyal Academy of Engineeringen
rioxxterms.identifier.projectCSIS17/03en
rioxxterms.versionAMen
rioxxterms.licenseref.startdate2018-04-06-
This item is licensed under a Creative Commons License
Creative Commons
All Items in ChesterRep are protected by copyright, with all rights reserved, unless otherwise indicated.