EPSCoR Research Fellow: NSF: Enhancing Workforce Development through Advanced Integration of Mixed Reality and Digital Twins

Industry 4.0 has introduced a transformative era in manufacturing, driven by the integration of advanced digital technologies into smart manufacturing systems. These advances require human operators to adapt and learn new skills to interact with complex machinery. However, many workers face challenges in understanding these complex tasks, leading to potential safety and health risks, labor shortages, and declining productivity in U.S. manufacturing.

This project aims to address these challenges by developing immersive training environments that enhance skill acquisition, knowledge transfer, and workplace safety. By integrating Mixed Reality (MR) with Digital Twin (DT) technologies, the project will transform traditional training methods and provide workers with practical, self-guided modules to acquire essential skills.

Collaboration with the University of South Carolina’s Future Factories Laboratory will help develop scalable training models that can be used across a wide range of industries, improving worker adaptability and safety. This initiative will not only enhance U.S. manufacturing competitiveness but also expand STEM education opportunities, particularly for underrepresented groups in the workforce.

By promoting a diverse, highly skilled workforce, the project aligns with NSF’s mission to advance the nation's economic prosperity, public health, and scientific progress.

The technical goal of this project is to optimize workforce training in smart manufacturing through the integration of MR and DT technologies. This will be achieved through three key objectives: (1) enhancing learning and skill transfer via MR-enabled environments, (2) evaluating instructional design factors that influence learning outcomes, and (3) synthesizing DTs to optimize ergonomics and work processes.

Using MR head-mounted displays and wearable motion capture systems, expert techniques and ergonomic practices will be overlaid onto real-world manufacturing environments, enabling workers to interact with virtual elements that guide task performance. The project will focus on machine assembly tasks, which pose high risks for musculoskeletal disorders (MSDs) due to repetitive movements—one of the leading causes of worker injuries and lost productivity.

Controlled experiments will assess how different instructional designs—such as point of view, augmented paths, and real-time feedback—impact worker performance, safety, and learning efficiency. A combined productivity-biomechanical analysis will quantitatively assess these factors using statistical techniques, including ANOVA and factorial experimental designs, to isolate the effects of each instructional factor.

Integration of DTs will provide real-time data analytics to optimize ergonomic practices and predict task performance, resulting in safer, more efficient manufacturing processes. This research will significantly advance workforce training by developing highly effective, scalable, and ergonomic training systems that address the need for a skilled and adaptable workforce in Industry 4.0

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.