User Experience Evaluation of AR Assisted Industrial Maintenance and Support Applications
Akos Nagy, Yannis Spyridis, Gregory J Mills, Vasileios Argyriou
TL;DR
The paper addresses downtime and inefficiency in industrial maintenance by introducing AR-assisted maintenance and expert-supported guidance via HMDs. It develops two AR-enabled applications (maintenance and support) with AI-powered computer vision to identify targets and overlay actionable information, evaluated in a simulated environment using NASA-TLX and SUS metrics plus qualitative feedback. Results show high usability (SUS ~74–77, labeled Excellent) and manageable workload (NASA-TLX with strong performance while cognitive and physical demands remain moderate), with Action Cards and voice communication identified as key value drivers. The study demonstrates the practical potential of AR-based, Industry 5.0 aligned maintenance interfaces to enhance intuitiveness, collaboration, and responsiveness, while outlining paths for real-world validation and feature enhancement.
Abstract
The paper introduces an innovative approach to industrial maintenance leveraging augmented reality (AR) technology, focusing on enhancing the user experience and efficiency. The shift from traditional to proactive maintenance strategies underscores the significance of maintenance in industrial systems. The proposed solution integrates AR interfaces, particularly through Head-Mounted Display (HMD) devices, to provide expert personnel-aided decision support for maintenance technicians, with the association of Artificial Intelligence (AI) solutions. The study explores the user experience aspect of AR interfaces in a simulated industrial environment, aiming to improve the maintenance processes' intuitiveness and effectiveness. Evaluation metrics such as the NASA Task Load Index (NASA-TLX) and the System Usability Scale (SUS) are employed to assess the usability, performance, and workload implications of the AR maintenance system. Additionally, the paper discusses the technical implementation, methodology, and results of experiments conducted to evaluate the effectiveness of the proposed solution.