Simulation Evidence of Trust Calibration: Using POMDP with Signal Detection Theory to Adapt Agent Features for Optimised Task Outcome During Human-Agent Collaboration

Herse, S; Vitale, J; Williams, MA

Simulation Evidence of Trust Calibration: Using POMDP with Signal Detection Theory to Adapt Agent Features for Optimised Task Outcome During Human-Agent Collaboration

Herse, S Vitale, J

Williams, MA

Permalink

Publisher:: SPRINGER
Publication Type:: Journal Article
Citation:: International Journal of Social Robotics, 2023
Issue Date:: 2023-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (1.63 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Herse, S
dc.contributor.author	Vitale, J https://orcid.org/0000-0001-6099-675X
dc.contributor.author	Williams, MA
dc.date.accessioned	2024-05-08T07:02:51Z
dc.date.available	2024-05-08T07:02:51Z
dc.date.issued	2023-01-01
dc.identifier.citation	International Journal of Social Robotics, 2023
dc.identifier.issn	1875-4791
dc.identifier.issn	1875-4805
dc.identifier.uri	http://hdl.handle.net/10453/178743
dc.description.abstract	Appropriately calibrated human trust is essential for successful Human-Agent collaboration. Probabilistic frameworks using a partially observable Markov decision process (POMDP) have been previously employed to model the trust dynamics of human behavior, optimising the outcomes of a task completed with a collaborative recommender system. A POMDP model utilising signal detection theory to account for latent user trust is presented, with the model working to calibrate user trust via the implementation of three distinct agent features: disclaimer message, request for additional information, and no additional feature. A simulation experiment is run to investigate the efficacy of the proposed POMDP model compared against a random feature model and a control model. Evidence demonstrates that the proposed POMDP model can appropriately adapt agent features in-task based on human trust belief estimates in order to achieve trust calibration. Specifically, task accuracy is highest with the POMDP model, followed by the control and then the random model. This emphasises the importance of trust calibration, as agents that lack considered design to implement features in an appropriate way can be more detrimental to task outcome compared to an agent with no additional features.
dc.language	English
dc.publisher	SPRINGER
dc.relation.ispartof	International Journal of Social Robotics
dc.relation.isbasedon	10.1007/s12369-023-01041-w
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0915 Interdisciplinary Engineering, 2002 Cultural Studies
dc.subject.classification	4602 Artificial intelligence
dc.subject.classification	4608 Human-centred computing
dc.title	Simulation Evidence of Trust Calibration: Using POMDP with Signal Detection Theory to Adapt Agent Features for Optimised Task Outcome During Human-Agent Collaboration
dc.type	Journal Article
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0915 Interdisciplinary Engineering
utslib.for	2002 Cultural Studies
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	open_access	*
dc.date.updated	2024-05-08T07:02:49Z
pubs.publication-status	Published

Abstract:

Appropriately calibrated human trust is essential for successful Human-Agent collaboration. Probabilistic frameworks using a partially observable Markov decision process (POMDP) have been previously employed to model the trust dynamics of human behavior, optimising the outcomes of a task completed with a collaborative recommender system. A POMDP model utilising signal detection theory to account for latent user trust is presented, with the model working to calibrate user trust via the implementation of three distinct agent features: disclaimer message, request for additional information, and no additional feature. A simulation experiment is run to investigate the efficacy of the proposed POMDP model compared against a random feature model and a control model. Evidence demonstrates that the proposed POMDP model can appropriately adapt agent features in-task based on human trust belief estimates in order to achieve trust calibration. Specifically, task accuracy is highest with the POMDP model, followed by the control and then the random model. This emphasises the importance of trust calibration, as agents that lack considered design to implement features in an appropriate way can be more detrimental to task outcome compared to an agent with no additional features.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/178743