Data-Driven Approach to Scenario Determination for VR-Based Construction Safety Training

Abstract

The construction industry experiences the greatest proportion of workplace injuries globally. Many efforts have gone to improve the effectiveness of safety training using advanced gaming technology and virtual reality (VR) technology. Most existing serious gaming programs are scenario-based which provide trainees, e.g., construction workers, an immersive virtual environment where they may process the construction tasks at the job site. However, the training scenarios are often determined by the developer or designer’s judgment. This is problematic since some important accident-associated details and elements are ignored during the scenario design. To address this problem, this work presents an approach that enables to automatically identify design elements from real world accident reports. The accident reports (n = 232) used in this study are gained from the National Institute of Occupational Safety and Health (NIOSH) for a period of 27 years (1989–2015). The approach integrates human factors engineering and machine learning techniques to gaming technology. This work also provides a case study that adopts the presented method in developing safety training scenarios using BIM and virtual reality headset for home builders. The case demonstrates improved accuracy and efficiency for the scenario design and storybook which are critical to the success of a VR-based training program.