Development of Laborer Digital Twin Generation and Visualization Function for Hazard Prediction in Off-Site Training

Abstract

We developed an MR-based system to enhance safety education for hazard prediction in off-site training by generating and visualizing digital twins of laborers. This system focuses on digitizing full-body movements, particularly foot movements and postures, to identify unsafe behaviors during training. Through trials with Vietnamese technical intern trainees, the system effectively identified these issues, highlighting its potential to improve safety training by providing detailed feedback on unsafe behaviors.