Road work zones are complex traffic environments where temporary changes in roadway geometry, traffic organization, and traffic control devices increase drivers' cognitive workload and road safety risks. Although national and international standards define requirements for temporary traffic control, their assessment is still largely based on prescriptive engineering practices, with limited quantitative evidence on driver behavior and traffic control effectiveness.This project aims to develop a multidimensional framework for evaluating temporary traffic control effectiveness by integrating high-fidelity driving simulation, eye tracking, naturalistic driving data, road infrastructure surveys, and Artificial Intelligence. It is hypothesized that the interaction between traffic control characteristics, human factors, and operational conditions directly influences drivers' perception, decision-making, and driving performance, and that these relationships can be represented through quantitative models.The methodology combines controlled driving simulator experiments with field surveys and georeferenced data collection infrastructure. Behavioral, operational, spatial, and visual information will be integrated into a unified database and analyzed using statistical methods and Artificial Intelligence to identify behavioral patterns, develop predictive models, and establish quantitative indicators of traffic control effectiveness.The project will deliver a quantitative framework integrating human factors, road infrastructure, and computational analysis to support evidence-based assessment of temporary traffic control. Expected outcomes include experimental protocols, computational models, integrated datasets, and technical recommendations to improve work zone planning and operation, support future updates of technical guidelines, and strengthen the application of Artificial Intelligence and human factors in transportation engineering and road safety.
Francisco Roza de Moraes (Sun,) studied this question.