Development of a Twin Model for Real-time Detection of Fall Hazards

The Architecture, Engineering and Construction (AEC) industry is still one of the most hazardous industries in the world. Researchers impute this trend to many factors such as the separation between the phases of safety planning and project execution, implicit safety issues and, most of all, the dynamic and complex nature of construction projects. Several studies show that the AEC industry could greatly benefit of latest advances in Information and Communication Technologies (ICTs) to develop tools contributing to safety management. A digital twin of the construction site, which is automatically instantiated and updated by real-time collected data, can run fast forward simulations in order to pro-actively support activities and forecast dangerous scenarios. In this paper, the twin model of the Digital Construction Capability Centre (DC3) at the Polytechnic University of Marche (UNIVPM) is developed and run as a mock-up, thanks to the adoption of a serious game engine. This mock-up is able to mirror all the relevant features of a job site during the execution of works from a safety-wide perspective. In such a scenario, virtual avatars randomly explore the construction site in order to detect accessible, unprotected and risky workspaces at height, while warning the safety inspector in case additional safety measures are needed.