Abnormality Detection in Robots Exhibiting Composite Swarm Behaviours

Danesh Tarapore, Anders Lyhne Christensen, Jon Timmis

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

3 Citations (SciVal)

Abstract

Fault detection is one of the most prominent challenges in the field of multirobot systems (MRS). Most existing fault-tolerant systems prescribe a characterisation of normal behaviours (fault-free behaviours), and train a model to recognise them. Behaviours not recognised by the model are labelled abnormal. MRS employing these models do not transition well to scenarios involving gradual changes in normal behaviour. In such scenarios, existing fault-detection systems may not be applicable, or may incur potentially costly false positive detections. We propose to address this challenging problem by taking inspiration from the regulation of tolerance and (auto)immunity in the adaptive immune system. We deploy an immune system-based fault-detection approach to detect abnormalities in heterogeneously behaving robots. Results of extensive simulation-based experiments demonstrate that a distributed MRS can correctly tolerate delayed propagation of different normal behaviours in the collective, at low false-positive rates. Furthermore, the fault-detection system is able to reliably detect robots performing different fault-simulating behaviours.

Original languageEnglish
Title of host publicationProceedings of the 13th European Conference on Artificial Life, ECAL 2015
PublisherMIT Press Journals
Pages406-413
Number of pages8
ISBN (Electronic)9780262330275
DOIs
Publication statusPublished - 2015
Event13th European Conference on Artificial Life, ECAL 2015 - York, United Kingdom of Great Britain and Northern Ireland
Duration: 20 Jul 201524 Jul 2015

Publication series

NameProceedings of the 13th European Conference on Artificial Life, ECAL 2015

Conference

Conference13th European Conference on Artificial Life, ECAL 2015
Country/TerritoryUnited Kingdom of Great Britain and Northern Ireland
CityYork
Period20 Jul 201524 Jul 2015

Fingerprint

Dive into the research topics of 'Abnormality Detection in Robots Exhibiting Composite Swarm Behaviours'. Together they form a unique fingerprint.

Cite this