No Cover Image

Conference Paper/Proceeding/Abstract 4 views

Optimising Human Trust in Robots: A Reinforcement Learning Approach

Abdullah Alzahrani, Muneeb Ahmad Orcid Logo

ACM Proceedings

Swansea University Authors: Abdullah Alzahrani, Muneeb Ahmad Orcid Logo

Abstract

This study explores optimising human-robot trust using reinforcement learning (RL) in simulated environments. Establishing trust in human-robot interaction (HRI) is crucial for effective collaboration, but misaligned trust levels can restrict successful task completion. Current RL approaches mainlyp...

Full description

Published in: ACM Proceedings
Published:
URI: https://cronfa.swan.ac.uk/Record/cronfa68696
first_indexed 2025-01-15T12:26:10Z
last_indexed 2025-01-15T20:37:15Z
id cronfa68696
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-01-15T12:26:08.2670444</datestamp><bib-version>v2</bib-version><id>68696</id><entry>2025-01-15</entry><title>Optimising Human Trust in Robots: A Reinforcement Learning Approach</title><swanseaauthors><author><sid>d2f9f67e9bfd515f861a917fe1d00321</sid><firstname>Abdullah</firstname><surname>Alzahrani</surname><name>Abdullah Alzahrani</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>9c42fd947397b1ad2bfa9107457974d5</sid><ORCID>0000-0001-8111-9967</ORCID><firstname>Muneeb</firstname><surname>Ahmad</surname><name>Muneeb Ahmad</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-01-15</date><abstract>This study explores optimising human-robot trust using reinforcement learning (RL) in simulated environments. Establishing trust in human-robot interaction (HRI) is crucial for effective collaboration, but misaligned trust levels can restrict successful task completion. Current RL approaches mainlyprioritise performance metrics without directly addressing trust management. To bridge this gap, we integrated a validated mathematical trust model into an RL framework and conducted experiments in two simulated environments: Frozen Lake and Battleship. The results showed that the RL model facilitated trust by dynamically adjusting it based on task outcomes, enhancing task performance and reducing the risks of insufficient or extreme trust. Our findings highlight the potential of RL to enhance human-robot collaboration (HRC) and trust calibration in different experimental HRI settings.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>ACM Proceedings</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2025-01-15T12:26:08.2670444</lastEdited><Created>2025-01-15T12:23:30.0099957</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><author><firstname>Muneeb</firstname><surname>Ahmad</surname><orcid>0000-0001-8111-9967</orcid><order>2</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2025-01-15T12:26:08.2670444 v2 68696 2025-01-15 Optimising Human Trust in Robots: A Reinforcement Learning Approach d2f9f67e9bfd515f861a917fe1d00321 Abdullah Alzahrani Abdullah Alzahrani true false 9c42fd947397b1ad2bfa9107457974d5 0000-0001-8111-9967 Muneeb Ahmad Muneeb Ahmad true false 2025-01-15 This study explores optimising human-robot trust using reinforcement learning (RL) in simulated environments. Establishing trust in human-robot interaction (HRI) is crucial for effective collaboration, but misaligned trust levels can restrict successful task completion. Current RL approaches mainlyprioritise performance metrics without directly addressing trust management. To bridge this gap, we integrated a validated mathematical trust model into an RL framework and conducted experiments in two simulated environments: Frozen Lake and Battleship. The results showed that the RL model facilitated trust by dynamically adjusting it based on task outcomes, enhancing task performance and reducing the risks of insufficient or extreme trust. Our findings highlight the potential of RL to enhance human-robot collaboration (HRC) and trust calibration in different experimental HRI settings. Conference Paper/Proceeding/Abstract ACM Proceedings 0 0 0 0001-01-01 COLLEGE NANME COLLEGE CODE Swansea University 2025-01-15T12:26:08.2670444 2025-01-15T12:23:30.0099957 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Abdullah Alzahrani 1 Muneeb Ahmad 0000-0001-8111-9967 2
title Optimising Human Trust in Robots: A Reinforcement Learning Approach
spellingShingle Optimising Human Trust in Robots: A Reinforcement Learning Approach
Abdullah Alzahrani
Muneeb Ahmad
title_short Optimising Human Trust in Robots: A Reinforcement Learning Approach
title_full Optimising Human Trust in Robots: A Reinforcement Learning Approach
title_fullStr Optimising Human Trust in Robots: A Reinforcement Learning Approach
title_full_unstemmed Optimising Human Trust in Robots: A Reinforcement Learning Approach
title_sort Optimising Human Trust in Robots: A Reinforcement Learning Approach
author_id_str_mv d2f9f67e9bfd515f861a917fe1d00321
9c42fd947397b1ad2bfa9107457974d5
author_id_fullname_str_mv d2f9f67e9bfd515f861a917fe1d00321_***_Abdullah Alzahrani
9c42fd947397b1ad2bfa9107457974d5_***_Muneeb Ahmad
author Abdullah Alzahrani
Muneeb Ahmad
author2 Abdullah Alzahrani
Muneeb Ahmad
format Conference Paper/Proceeding/Abstract
container_title ACM Proceedings
institution Swansea University
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 0
active_str 0
description This study explores optimising human-robot trust using reinforcement learning (RL) in simulated environments. Establishing trust in human-robot interaction (HRI) is crucial for effective collaboration, but misaligned trust levels can restrict successful task completion. Current RL approaches mainlyprioritise performance metrics without directly addressing trust management. To bridge this gap, we integrated a validated mathematical trust model into an RL framework and conducted experiments in two simulated environments: Frozen Lake and Battleship. The results showed that the RL model facilitated trust by dynamically adjusting it based on task outcomes, enhancing task performance and reducing the risks of insufficient or extreme trust. Our findings highlight the potential of RL to enhance human-robot collaboration (HRC) and trust calibration in different experimental HRI settings.
published_date 0001-01-01T20:37:15Z
_version_ 1821348657232871424
score 11.04748

Similar Items