Show simple item record

dc.contributor.authorRaymond, Alexandreen
dc.contributor.authorGunes, Haticeen
dc.contributor.authorProrok, Amandaen
dc.date.accessioned2020-03-24T12:53:02Z
dc.date.available2020-03-24T12:53:02Z
dc.date.issued2020-05-05en
dc.identifier.isbn978-1-4503-7518-4en
dc.identifier.issn1548-8403
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/303694
dc.description.abstractLaw codes and regulations help organise societies for centuries, and as AI systems gain more autonomy, we question how human-agent systems can operate as peers under the same norms, especially when resources are contended. We posit that agents must be accountable and explainable by referring to which rules justify their decisions. The need for explanations is associated with user acceptance and trust. This paper's contribution is twofold: i) we propose an argumentation-based human-agent architecture to map human regulations into a culture for artificial agents with explainable behaviour. Our architecture leans on the notion of argumentative dialogues and generates explanations from the history of such dialogues; and ii) we validate our architecture with a user study in the context of human-agent path deconfliction. Our results show that explanations provide a significantly higher improvement in human performance when systems are more complex. Consequently, we argue that the criteria defining the need of explanations should also consider the complexity of a system. Qualitative findings show that when rules are more complex, explanations significantly reduce the perception of challenge for humans.
dc.description.sponsorshipL3Harris ASV and the Royal Commission for the Exhibition of 1851
dc.publisherACM
dc.rightsAll rights reserved
dc.titleCulture-Based Explainable Human-Agent Deconflictionen
dc.typeConference Object
prism.publicationDate2020en
prism.publicationNameAAMAS '20: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systemsen
dc.identifier.doi10.17863/CAM.50772
dcterms.dateAccepted2020-01-15en
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2020-05-05en
dc.contributor.orcidGunes, Hatice [0000-0003-2407-3012]
dc.contributor.orcidProrok, Amanda [0000-0001-7313-5983]
dc.identifier.eissn1558-2914
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.funder-project-idEPSRC (EP/R030782/1)
pubs.funder-project-idEPSRC (EP/S015493/1)
dc.identifier.urlhttps://dl.acm.org/doi/10.5555/3398761.3398890en
pubs.conference-name19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020)en
pubs.conference-start-date2020-05-09en
cam.orpheus.successThu Nov 05 11:56:14 GMT 2020 - Embargo updated*


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record