AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarms

Dhaminda B Abeywickrama*, James S Wilson*, Suet Lee, Greg Chance, Peter Winter, Arianna Manzini, Ibrahim Habli, Shane P Windsor, Sabine Hauert, Kerstin I Eder

*Corresponding author for this work

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

Abstract

The behaviours of a swarm are not explicitly engineered. Instead, they are an emergent consequence of the interactions of individual agents with each other and their environment. This emergent functionality poses a challenge to safety assurance. The main contribution of this paper is a process for the safety assurance of emergent behaviour in autonomous robotic swarms called AERoS, following the guidance on the Assurance of Machine Learning for use in Autonomous Systems (AMLAS). We explore our proposed process using a case study centred on a robot swarm operating a public cloakroom.
Original languageEnglish
Title of host publicationComputer Safety, Reliability and Security - SAFECOMP 2023 Workshops
PublisherSpringer Nature
Pages341-354
Number of pages14
ISBN (Electronic)9783031409530
ISBN (Print)9783031409523
DOIs
Publication statusPublished - 14 Sept 2023
EventSAFECOMP2023: 42nd International Conference on Computer Safety, Reliability and Security - Toulouse, France
Duration: 19 Sept 202322 Sept 2023

Publication series

NameLecture Notes in Computer Science
PublisherSpring Nature
Volume14182
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceSAFECOMP2023
Country/TerritoryFrance
CityToulouse
Period19/09/2322/09/23

Fingerprint

Dive into the research topics of 'AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarms'. Together they form a unique fingerprint.

Cite this