Exploring Dimensions of Expertise in AR-Guided Psychomotor Tasks

TL;DR

The paper addresses how novices and experts differ in AR-guided psychomotor tasks by modeling two expertise dimensions: decision making and technical proficiency. It employs a two-session precision-inspection task on 3D-printed parts, using multimodal data from AR devices and wearables (e.g., gaze, GSR) to quantify performance. Key findings show that experts outperform in decision-making efficiency and overall inspection accuracy, while novices exhibit stronger coupling between perceived workload and physiological stress, indicating less stable stress regulation. These results provide a foundation for multidimensional expertise estimation models to enable personalized industrial AR training systems and adaptive AR guidance calibrated to user expertise.

Abstract

This study aimed to explore how novices and experts differ in performing complex psychomotor tasks guided by augmented reality (AR), focusing on decision-making and technical proficiency. Participants were divided into novice and expert groups based on a pre-questionnaire assessing their technical skills and theoretical knowledge of precision inspection. Participants completed a post-study questionnaire that evaluated cognitive load (NASA-TLX), self-efficacy, and experience with the HoloLens 2 and AR app, along with general feedback. We used multimodal data from AR devices and wearables, including hand tracking, galvanic skin response, and gaze tracking, to measure key performance metrics. We found that experts significantly outperformed novices in decision-making speed, efficiency, accuracy, and dexterity in the execution of technical tasks. Novices exhibited a positive correlation between perceived performance in the NASA-TLX and the GSR amplitude, indicating that higher perceived performance is associated with increased physiological stress responses. This study provides a foundation for designing multidimensional expertise estimation models to enable personalized industrial AR training systems.

Figures (6)

• Figure 1: Study's precision inspection gauges and parts.
• Figure 2: AR application interface (HoloLens 2) for inspection tasks. Left: Interface for Session 1, where participants follow detailed instructions and animations for Characteristics 5, 6, and 13 using specific gauges. This session emphasizes step-by-step guidance with full instructions always visible. Right: Interface for Session 2, featuring the Gauge Selection Quiz. Participants choose appropriate gauges and measure Characteristics 15, 32, and 35 with optional access to full instructions. Each participant has three attempts per characteristic, with feedback provided after incorrect responses.
• Figure 3: Left: Real-world view and AR application with visual scanning areas. Right: Blue highlighted regions indicate visual scanning areas, tracking gaze on different components.
• Figure 4: Novice and expert NASA-TLX scores.
• Figure 5: Scatter plots with regression lines showing the relationship between performance and GSR amplitude for experts (left) and novices (right).