Real-Time Proactive Road Safety Monitoring and Optimization

This study proposes a new signal optimization technique that can help reduce crashes at intersections. Using data from sensors installed at the intersections, vehicle trajectories can be used to identify near-misses that would provide insight into crash-risk. By quantifying the crash-risk using extreme value models, a crash-risk metric is derived that can be used to optimize signal timing. Recognizing that safety is a dynamic quantity which fluctuates over time, adjusting signal timing can effectively alter and reduce crash risk. A multi-objective optimization approach is thus taken by leveraging AI technologies, allowing for the crash risk to be reduced at a location in real-time alongside delay. As such, this proposal demonstrates a proactive approach to safety in a departure away from traditional reactive safety approaches.

Faculty Supervisor:

Tarek Sayed

Student:

Partner:

Rogers Communications Inc.

Discipline:

Engineering

Sector:

Information and cultural industries

University:

The University of British Columbia

Program: