Integrating Wearable and Camera Based Monitoring in the Digital Twin for Safety Assessment in the Industry 4.0 Era

The occurrence of human errors in work processes reduces the quality of results, increases the costs due to compensatory actions, and may have heavy repercussions on the workers’ safety. The definition of rules and procedures that workers have to respect has shown to be not enough to guarantee their safety, as negligence and opportunistic behaviours can unfortunately lead to catastrophic consequences. In the Industry 4.0 era, with the advent of the digital twin in smart factories, advanced systems can be exploited for automatic risk prediction and avoidance. By leveraging the new opportunities provided by the digital twin and, in particular, the introduction of wearable sensors and computer vision, we propose an automatic system for monitoring human behaviours in a smart factory in real time. The final goal is to feed cloud-based safety assessment tools that evaluate human errors and raise consequent alerts when required.