<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css">
Repository logo

RPD-Grounded Simulated Users for Pre-screening AR Training Interface Designs: A Unity ML-Agents Approach

aut.relation.conference39th International BCS Human-Computer Interaction Conference 2026
aut.relation.endpage107
aut.relation.startpage97
dc.contributor.authorThilakarathna, Thusithanjana
dc.contributor.authorWong, BL William
dc.contributor.authorNguyen, Minh
dc.date.accessioned2026-11-18T03:52:50Z
dc.date.issued2026-11-01
dc.description.abstractEvaluating augmented reality (AR) training interfaces typically requires recruiting domain practitioners, coordinating controlled studies, and incurring the logistical and ethical costs of human-subject testing. This paper presents a pre-screening framework that uses simulated users to surface interface design trade-offs before human trials begin. Agents are built with Unity ML-Agents and grounded in the Recognition-Primed Decision (RPD) model, with distinct reward structures derived from Cognitive Task Analysis of paramedic diagnostic reasoning encoding novice and expert decision strategies. We evaluate three interface configurations varying in button density, spatial layout, and labelling across both agent types, and characterize behaviour using behavioural interaction indicators computed from interaction logs and conceptually organized using a structure inspired by the NASA Task Load Index (NASA-TLX). Results show that dense dispersed layouts impose the highest temporal and search cost on novice agents, while deceptive clustering imposes the highest temporal and effort cost on expert agents. Search Complexity Indicator diverged between cohorts in a pattern consistent with RPD-predicted selective attention: expert agents narrowed search as complexity increased while novice agents maintained broad attention throughout. These patterns were consistent across behavioural indicator scores and raw interaction metrics including path entropy, inter-click intervals, and idle ratios. The framework requires no human participants, produces reproducible behavioural traces across conditions, and is intended as a complement to human-subject evaluation rather than a replacement. Validation against human self-reported ratings and objective performance data is identified as the essential next step.
dc.identifier.citationProceedings of the 39th International BCS Human-Computer Interaction Conference 2026 (BRITCHI26). 1–3 November 2026, Brunel University, UK. Pages: 97-107
dc.identifier.doi10.14236/ewic/britchi26.13
dc.identifier.issn1477-9358
dc.identifier.urihttp://hdl.handle.net/10292/22433
dc.publisherBCS Learning & Development
dc.relation.urihttps://www.scienceopen.com/hosted-document?doi=10.14236/ewic/BRITCHI26.13
dc.rights© Thilakarathna et al. Published by BCS Learning and Development Ltd. Proceedings of BRITCHI 26 2026, UK. Open access.
dc.rights.accessrightsOpenAccess
dc.subject46 Information and Computing Sciences
dc.subject4608 Human-Centred Computing
dc.subject4602 Artificial Intelligence
dc.subjectSimulated users
dc.subjectRecognition-Primed Decision
dc.subjectaugmented reality training
dc.subjectUnity ML-Agents
dc.subjectAR UI evaluation
dc.titleRPD-Grounded Simulated Users for Pre-screening AR Training Interface Designs: A Unity ML-Agents Approach
dc.typeConference Contribution
pubs.elements-id777765

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
RPD-grounded simulated users_2026 BRITCHI.pdf
Size:
1.09 MB
Format:
Adobe Portable Document Format
Description:
Conference paper