Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction

ALZAHRANI, ABDULLAH

doi:10.23889/SUThesis.69777

E-Thesis 496 views 1010 downloads

Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction / ABDULLAH ALZAHRANI

Swansea University Author: ABDULLAH ALZAHRANI

PDF | E-Thesis – open access

Copyright: The Author, Abdullah Saad Alzahrani, 2025
Download (13.95MB)

DOI (Published version): 10.23889/SUThesis.69777

Abstract

This thesis presents a novel, holistic framework for understanding, measuring, and optimising human trust in robots, integrating cultural factors, mathematical modelling, physiological indicators, and behavioural analysis to establish foundational methodologies for trust-aware robotic systems. Throu...

Full description

Published:	Swansea University, Wales, UK 2025
Institution:	Swansea University
Degree level:	Doctoral
Degree name:	Ph.D
Supervisor:	Muneeb I., A.
URI:	https://cronfa.swan.ac.uk/Record/cronfa69777

first_indexed	2025-06-19T15:19:38Z
last_indexed	2025-06-20T04:59:22Z
id	cronfa69777
recordtype	RisThesis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2025-06-19T16:22:29.4743253</datestamp><bib-version>v2</bib-version><id>69777</id><entry>2025-06-19</entry><title>Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction</title><swanseaauthors><author><sid>fc85729b42b753b90537dd1efb84d3cc</sid><firstname>ABDULLAH</firstname><surname>ALZAHRANI</surname><name>ABDULLAH ALZAHRANI</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-06-19</date><abstract>This thesis presents a novel, holistic framework for understanding, measuring, and optimising human trust in robots, integrating cultural factors, mathematical modelling, physiological indicators, and behavioural analysis to establish foundational methodologies for trust-aware robotic systems. Through this com-prehensive approach, we address the critical challenge of trust calibration in human-robot interaction (HRI) across diverse contexts. Trust is essential for effective HRI, impacting user acceptance, safety, and overall task performance in both collaborative and competitive settings. This thesis investigated a multi-faceted approach to understanding, modelling, and optimising human trust in robots across various HRI contexts. First, we explored cultural and contextual differences in trust, conducting cross-cultural studies in Saudi Arabia and the United Kingdom. Findings showed that trust factors such as controllability, us-ability, and risk perception vary signiﬁcantly across cultures and HRI scenarios, highlighting the need for ﬂexible, adaptive trust models that can accommodate these dynamics. Building on these cultural insights as a critical dimension of our holistic trust framework, we developed a mathematical model that emu-lates the layered framework of trust (initial, situational, and learned) to estimate trust in real-time. Experimental validation through repeated interactions demonstrated the model’s ability to dynamically calibrate trust with both trust perception scores (TPS) and interaction sessions serving as signiﬁcant predictors.This model showed promise for adaptive HRI systems capable of responding to evolving trust states. To further enhance our comprehensive trust measurement approach, this thesis explored physiological behaviours (PBs) as objective indicators. By using electrodermal activity (EDA), blood volume pulse (BVP),heart rate (HR), skin temperature (SKT), eye blinking rate (BR), and blinking duration (BD), we showed that speciﬁc PBs (HR, SKT) vary between trust and distrust states and can effectively predict trust levels in real-time. Extending this approach, we compared PB data across competitive and collaborative con-texts and employed incremental transfer learning to improve predictive accuracy across different interaction settings. Recognising the potential of less intrusive trust indicators, we also examined vocal and non-vocal cues—such as pitch, speech rate, facial expressions, and blend shapes—as complementary measures of trust. Results indicated that these cues can reliably assess current trust states in real-time and predict trust development in subsequent interactions, with trust-related behaviours evolving over time in repeated HRI sessions. Our comprehensive analysis demonstrated that integrating these expressive behaviours pro-vides quantiﬁable measurements for capturing trust, establishing them as reliable metrics within real-time assessment frameworks. As the ﬁnal component of our integrated trust framework, this thesis explored reinforcement learning (RL) for trust optimisation in simulated environments. Integrating our trust model into an RL framework, we demonstrated that dynamically calibrated trust can enhance task performance and reduce the risks of both under and over-reliance on robotic systems. Together, these multifaceted contributions advance a holistic understanding of trust measurement and calibration in HRI, encompassing cultural insights, mathematical modelling, physiological and expressive behaviour analysis, and adaptive control. This integrated approach establishes foundational methodologies for developing trust-aware robots capable of enhancing collaborative outcomes and fostering sustained user trust in real-world applications. The framework presented in this thesis represents a signiﬁcant advancement in creating robotic systems that can dynamically adapt to human trust states across diverse contexts and interaction scenarios</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea University, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Human Robot Interaction, Measurement, Model, Physiological Behaviour, Vocal and Non-vocal Cues, Machine Learning, Reinforcement Learning, Optimisation.</keywords><publishedDay>16</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-04-16</publishedDate><doi>10.23889/SUThesis.69777</doi><url/><notes>A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information.</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Muneeb I., A.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><apcterm/><funders/><projectreference/><lastEdited>2025-06-19T16:22:29.4743253</lastEdited><Created>2025-06-19T16:15:08.4871160</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>ABDULLAH</firstname><surname>ALZAHRANI</surname><order>1</order></author></authors><documents><document><filename>69777__34532__37ecc8f9f992431fbeb7b7a751f8b1be.pdf</filename><originalFilename>2025_Alzahrani_A.final.69777.pdf</originalFilename><uploaded>2025-06-19T16:18:57.1185421</uploaded><type>Output</type><contentLength>14623717</contentLength><contentType>application/pdf</contentType><version>E-Thesis – open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The Author, Abdullah Saad Alzahrani, 2025</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling	2025-06-19T16:22:29.4743253 v2 69777 2025-06-19 Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction fc85729b42b753b90537dd1efb84d3cc ABDULLAH ALZAHRANI ABDULLAH ALZAHRANI true false 2025-06-19 This thesis presents a novel, holistic framework for understanding, measuring, and optimising human trust in robots, integrating cultural factors, mathematical modelling, physiological indicators, and behavioural analysis to establish foundational methodologies for trust-aware robotic systems. Through this com-prehensive approach, we address the critical challenge of trust calibration in human-robot interaction (HRI) across diverse contexts. Trust is essential for effective HRI, impacting user acceptance, safety, and overall task performance in both collaborative and competitive settings. This thesis investigated a multi-faceted approach to understanding, modelling, and optimising human trust in robots across various HRI contexts. First, we explored cultural and contextual differences in trust, conducting cross-cultural studies in Saudi Arabia and the United Kingdom. Findings showed that trust factors such as controllability, us-ability, and risk perception vary signiﬁcantly across cultures and HRI scenarios, highlighting the need for ﬂexible, adaptive trust models that can accommodate these dynamics. Building on these cultural insights as a critical dimension of our holistic trust framework, we developed a mathematical model that emu-lates the layered framework of trust (initial, situational, and learned) to estimate trust in real-time. Experimental validation through repeated interactions demonstrated the model’s ability to dynamically calibrate trust with both trust perception scores (TPS) and interaction sessions serving as signiﬁcant predictors.This model showed promise for adaptive HRI systems capable of responding to evolving trust states. To further enhance our comprehensive trust measurement approach, this thesis explored physiological behaviours (PBs) as objective indicators. By using electrodermal activity (EDA), blood volume pulse (BVP),heart rate (HR), skin temperature (SKT), eye blinking rate (BR), and blinking duration (BD), we showed that speciﬁc PBs (HR, SKT) vary between trust and distrust states and can effectively predict trust levels in real-time. Extending this approach, we compared PB data across competitive and collaborative con-texts and employed incremental transfer learning to improve predictive accuracy across different interaction settings. Recognising the potential of less intrusive trust indicators, we also examined vocal and non-vocal cues—such as pitch, speech rate, facial expressions, and blend shapes—as complementary measures of trust. Results indicated that these cues can reliably assess current trust states in real-time and predict trust development in subsequent interactions, with trust-related behaviours evolving over time in repeated HRI sessions. Our comprehensive analysis demonstrated that integrating these expressive behaviours pro-vides quantiﬁable measurements for capturing trust, establishing them as reliable metrics within real-time assessment frameworks. As the ﬁnal component of our integrated trust framework, this thesis explored reinforcement learning (RL) for trust optimisation in simulated environments. Integrating our trust model into an RL framework, we demonstrated that dynamically calibrated trust can enhance task performance and reduce the risks of both under and over-reliance on robotic systems. Together, these multifaceted contributions advance a holistic understanding of trust measurement and calibration in HRI, encompassing cultural insights, mathematical modelling, physiological and expressive behaviour analysis, and adaptive control. This integrated approach establishes foundational methodologies for developing trust-aware robots capable of enhancing collaborative outcomes and fostering sustained user trust in real-world applications. The framework presented in this thesis represents a signiﬁcant advancement in creating robotic systems that can dynamically adapt to human trust states across diverse contexts and interaction scenarios E-Thesis Swansea University, Wales, UK Human Robot Interaction, Measurement, Model, Physiological Behaviour, Vocal and Non-vocal Cues, Machine Learning, Reinforcement Learning, Optimisation. 16 4 2025 2025-04-16 10.23889/SUThesis.69777 A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information. COLLEGE NANME COLLEGE CODE Swansea University Muneeb I., A. Doctoral Ph.D 2025-06-19T16:22:29.4743253 2025-06-19T16:15:08.4871160 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science ABDULLAH ALZAHRANI 1 69777__34532__37ecc8f9f992431fbeb7b7a751f8b1be.pdf 2025_Alzahrani_A.final.69777.pdf 2025-06-19T16:18:57.1185421 Output 14623717 application/pdf E-Thesis – open access true Copyright: The Author, Abdullah Saad Alzahrani, 2025 true eng
title	Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction
spellingShingle	Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction ABDULLAH ALZAHRANI
title_short	Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction
title_full	Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction
title_fullStr	Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction
title_full_unstemmed	Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction
title_sort	Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction
author_id_str_mv	fc85729b42b753b90537dd1efb84d3cc
author_id_fullname_str_mv	fc85729b42b753b90537dd1efb84d3cc_***_ABDULLAH ALZAHRANI
author	ABDULLAH ALZAHRANI
author2	ABDULLAH ALZAHRANI
format	E-Thesis
publishDate	2025
institution	Swansea University
doi_str_mv	10.23889/SUThesis.69777
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str	1
active_str	0
description	This thesis presents a novel, holistic framework for understanding, measuring, and optimising human trust in robots, integrating cultural factors, mathematical modelling, physiological indicators, and behavioural analysis to establish foundational methodologies for trust-aware robotic systems. Through this com-prehensive approach, we address the critical challenge of trust calibration in human-robot interaction (HRI) across diverse contexts. Trust is essential for effective HRI, impacting user acceptance, safety, and overall task performance in both collaborative and competitive settings. This thesis investigated a multi-faceted approach to understanding, modelling, and optimising human trust in robots across various HRI contexts. First, we explored cultural and contextual differences in trust, conducting cross-cultural studies in Saudi Arabia and the United Kingdom. Findings showed that trust factors such as controllability, us-ability, and risk perception vary signiﬁcantly across cultures and HRI scenarios, highlighting the need for ﬂexible, adaptive trust models that can accommodate these dynamics. Building on these cultural insights as a critical dimension of our holistic trust framework, we developed a mathematical model that emu-lates the layered framework of trust (initial, situational, and learned) to estimate trust in real-time. Experimental validation through repeated interactions demonstrated the model’s ability to dynamically calibrate trust with both trust perception scores (TPS) and interaction sessions serving as signiﬁcant predictors.This model showed promise for adaptive HRI systems capable of responding to evolving trust states. To further enhance our comprehensive trust measurement approach, this thesis explored physiological behaviours (PBs) as objective indicators. By using electrodermal activity (EDA), blood volume pulse (BVP),heart rate (HR), skin temperature (SKT), eye blinking rate (BR), and blinking duration (BD), we showed that speciﬁc PBs (HR, SKT) vary between trust and distrust states and can effectively predict trust levels in real-time. Extending this approach, we compared PB data across competitive and collaborative con-texts and employed incremental transfer learning to improve predictive accuracy across different interaction settings. Recognising the potential of less intrusive trust indicators, we also examined vocal and non-vocal cues—such as pitch, speech rate, facial expressions, and blend shapes—as complementary measures of trust. Results indicated that these cues can reliably assess current trust states in real-time and predict trust development in subsequent interactions, with trust-related behaviours evolving over time in repeated HRI sessions. Our comprehensive analysis demonstrated that integrating these expressive behaviours pro-vides quantiﬁable measurements for capturing trust, establishing them as reliable metrics within real-time assessment frameworks. As the ﬁnal component of our integrated trust framework, this thesis explored reinforcement learning (RL) for trust optimisation in simulated environments. Integrating our trust model into an RL framework, we demonstrated that dynamically calibrated trust can enhance task performance and reduce the risks of both under and over-reliance on robotic systems. Together, these multifaceted contributions advance a holistic understanding of trust measurement and calibration in HRI, encompassing cultural insights, mathematical modelling, physiological and expressive behaviour analysis, and adaptive control. This integrated approach establishes foundational methodologies for developing trust-aware robots capable of enhancing collaborative outcomes and fostering sustained user trust in real-world applications. The framework presented in this thesis represents a signiﬁcant advancement in creating robotic systems that can dynamically adapt to human trust states across diverse contexts and interaction scenarios
published_date	2025-04-16T05:29:04Z
_version_	1851097920880771072
score	11.089386

Measuring Human’s Trust in Robots in Real-time During Human-Robot Interaction / ABDULLAH ALZAHRANI

Similar Items