Risk Assessment in Road Work Zones Using Artificial Intelligence, Expert Evaluation, and Driver Surveys

Road work zones represent one of the most challenging segments in the traffic safety system, as they frequently involve sudden changes in traffic flow regulation, reduced vehicle speeds, the presence of construction machinery, and road workers operating within the roadway. Inadequate traffic signage and poorly marked work zones significantly increase the risk of traffic accidents, especially when drivers are not properly and timely informed. In order to analyze risk perception and assess safety in road work zones, a comprehensive study was conducted, covering three representative scenarios on three different road categories: state road category I (motorway), state road category II (main road), and an urban street (local road). The research included 146 drivers of various profiles (professional and non-professional drivers) and 15 experts from the fields of traffic and civil engineering. The results indicate a statistically significant difference in risk perception between the artificial intelligence model, drivers, and experts. Notably, drivers often underestimate the complexity and hazards present in both urban and non-urban work zones. Based on the findings, an integrated model is proposed, which can be implemented within navigation systems to provide real-time dynamic alerts to drivers and enhance safety in active work zones.