Reinforcement Learning for Optimal Speed Limit Control Over Network

The goal is to optimize variable speed limit control (VSLC) strategies over network to improve both traffic safety and mobility. The investigators propose to use graph-based deep reinforcement learning to improve the control effectiveness and scalability. The proposed research will advance the current knowledge and practice of VSLC in two aspects. First, this research will enlarge the scope of VSLC from link-based to network-based control to bring a new understanding about its system-level safety implications. Second, it will optimize the impact of VSLC using multi-objective learning approaches considering both safety and mobility.

Project

  • Status: Active
  • Funding: $35000
  • Contract Numbers:

    69A3551747131

  • 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 Iowa, Iowa City

    National Advanced Driving Simulator, 2401 Oakdale Blvd
    Iowa City, IA  United States  52242-5003
  • Performing Organizations:

    University of Central Florida, Orlando

    Department of Civil, Environmental & Contruction Engineering
    1280 Pegasus Drive, 442B Engineering II
    Orlando, FL  United States  32816
  • Principal Investigators:

    Guo, Zhaomiao

  • Start Date: 20210808
  • Expected Completion Date: 20230207
  • Actual Completion Date: 0
  • USDOT Program: University Transportation Centers

Subject/Index Terms

Filing Info

  • Accession Number: 01778677
  • Record Type: Research project
  • Source Agency: Safety Research Using Simulation University Transportation Center (SaferSim)
  • Contract Numbers: 69A3551747131
  • Files: UTC, RIP
  • Created Date: Aug 3 2021 12:06PM