Investigating hazard recognition in augmented virtuality for personalized feedback in construction safety education and training

Accidents resulting from poorly planned or set up work environments are a major concern within the construction industry. While traditional education and training of personnel offer well-known approaches for establishing safe work practices, serious games in virtual reality (VR) are used more often as a complementary approach for active, personalized learning experiences. Their designs yet have to take full advantage of how trainees can potentially manipulate and interact with virtual objects. In addition, little construction safety research has focused on generating and analyzing the inherent data that can be collected about the trainees’ actions in the virtual environment. The objective analysis of their performance in the virtual environment offers precise feedback to sensitize their work behavior later in real practice. This research presents a novel framework for the generation and assessment of the trainees’ data in augmented virtuality (AV). The proposed approach is tested in a virtual work environment consisting of multiple stages and hazards that are consistent within today’s construction sites and workshops. A real angle grinder has been reworked and repurposed as an interactive AV controller to further enhance immersion. Results on the performance in the proposed system and the experiences of two groups of volunteering participants are presented and discussed. An outlook presents future avenues towards enhancing existing construction safety education and focus points on correlating objective tracking data with self-assessment.