Augmenting Learning with Augmented Reality: Exploring the Affordances of AR in Supporting Mastery of Complex Psychomotor Tasks
Project Overview
The document discusses the role of generative AI and Augmented Reality (AR) in enhancing education, particularly for complex psychomotor tasks in industrial environments. It introduces a prototype AR tutoring system designed to provide personalized and adaptive instruction, which aims to increase learner engagement and address skills gaps within manufacturing and similar sectors. The research emphasizes the advantages of integrating AR technology, such as improved task competency, decreased error rates, and effective transfer of acquired skills to various tasks. Additionally, it outlines future developments for the AR system, focusing on the incorporation of advanced AI features to further elevate the learning experience and outcomes for users. Overall, the findings suggest that the convergence of AR and AI holds significant promise for transforming educational practices in industrial training contexts.
Key Applications
AR tutoring system for precision inspection tasks
Context: Industrial workplaces, particularly in sectors like aerospace and medical manufacturing
Implementation: Developed AR prototype using Unity and HoloLens 2; users interact with the system using hand gestures and voice commands
Outcomes: Improved task competency, reduced errors by 31-84%, faster task completion, and enhanced independence from AR after training
Challenges: Technical issues during AR usage, initial unfamiliarity with the technology
Implementation Barriers
Technical barrier
Participants faced technical issues with the AR system, impacting their learning experience. Users were initially unfamiliar with AR technology, which affected their performance during training.
Proposed Solutions: Enhancements in the AR application, including interactive help and voice command systems. Initial online training on the AR app and hardware to familiarize users with the system.
Project Team
Dong Woo Yoo
Researcher
Sakib Reza
Researcher
Nicholas Wilson
Researcher
Kemi Jona
Researcher
Mohsen Moghaddam
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Dong Woo Yoo, Sakib Reza, Nicholas Wilson, Kemi Jona, Mohsen Moghaddam
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai