A Hormone-Inspired Arbitration System for Self Identifying Abilities Amongst A Heterogeneous Robot Swarm

James Wilson, Jon Timmis, Andy Tyrrell

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

2 Citations (Scopus)

Abstract

Current exploration of adaptation in robot swarms requires the swarm or individuals within that swarm to have knowledge of their own capabilities. Across long term use a swarms understanding of its capabilities may become inaccurate due to wear or faults in the system. In addition to this, systems capable of self designing morphologies are becoming increasingly feasible. In these self designing examples it would be impossible to have accurate knowledge of capability before executing a task for the first time. We propose an arbitration system that requires no explicit knowledge of capability but instead uses hormone-inspired values to decide on an environmental preference. The robots in the swarm differ by wheel type and thus how quickly they are able to move across terrain. The goal of this system is to allow robots to identify their strengths within a swarm and allocate themselves to areas of an environment with a floor type that suits their ability. This work shows that the use of a hormone-inspired arbitration system can extrapolate robot capability and adapt the systems preference of terrain to suit said capability.

Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018
EditorsSuresh Sundaram
PublisherIEEE Press
Pages843-850
Number of pages8
ISBN (Electronic)9781538692769
DOIs
Publication statusPublished - 02 Jul 2018
Event8th IEEE Symposium Series on Computational Intelligence, SSCI 2018 - Bangalore, India
Duration: 18 Nov 201821 Nov 2018

Publication series

NameProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

Conference

Conference8th IEEE Symposium Series on Computational Intelligence, SSCI 2018
Country/TerritoryIndia
CityBangalore
Period18 Nov 201821 Nov 2018

Fingerprint

Dive into the research topics of 'A Hormone-Inspired Arbitration System for Self Identifying Abilities Amongst A Heterogeneous Robot Swarm'. Together they form a unique fingerprint.

Cite this