AI Powered Conflict Detection and Signal Optimization for Right Turn FYAs in Mixed Modal Intersections

Right turn Flashing Yellow Arrows (FYAs) can support efficient traffic movement, but they also introduce uncertainty for drivers who must judge when to yield to pedestrians and cyclists. This uncertainty can increase the number of near miss interactions at mixed modal intersections. This project will create an artificial intelligence framework that uses video based detection to monitor turning vehicles, pedestrians, and cyclists in real time. The system will compute surrogate safety measures such as post encroachment time and time to collision to identify conditions that may increase the likelihood of a conflict. The project will use these safety measures to support a signal timing optimization engine that balances safety with delay reduction. The research team will test the framework in simulation and explore opportunities for pilot deployment with the Connecticut Department of Transportation. The resulting tools will give agencies a practical method to assess right turn FYA performance, adjust timing plans when needed, and improve intersection safety through proactive conflict identification.

Language

  • English

Project

  • Status: Active
  • Funding: $210,000.00
  • Contract Numbers:

    69A3552348301

  • Sponsor Organizations:

    Office of the Assistant Secretary for Research and Technology

    University Transportation Centers Program
    Department of Transportation
    Washington, DC  United States  20590
  • Managing Organizations:

    University of Massachusetts, Amherst

    Department of Civil and Environmental Engineering
    130 Natural Resources Road
    Amherst, MA  United States  01003
  • Performing Organizations:

    University of Connecticut, Storrs

    Connecticut Transportation Institute
    270 Middle Turnpike, Unit 5202
    Storrs, CT  United States  06269-5202
  • Principal Investigators:

    Zuo, Shan

  • Start Date: 20260101
  • Expected Completion Date: 20261231
  • Actual Completion Date: 0
  • USDOT Program: University Transportation Centers Program
  • Subprogram: University Transportation Centers

Subject/Index Terms

Filing Info

  • Accession Number: 01973940
  • Record Type: Research project
  • Source Agency: New England University Transportation Center
  • Contract Numbers: 69A3552348301
  • Files: UTC, RIP
  • Created Date: Dec 11 2025 1:35PM