Real-time Deep Reinforcement Learning for Evacuation under Emergencies

Aviation emergencies pose high risks to humans, when it occurs, it is imperative to evacuate humans to safe places in an efficient manner. Under the high level of time pressure, decision-makers are facing great challenges of developing an optimal evacuation quickly, especially when the threats involved are not static and the environment is unfamiliar. The research team plans to integrate Asynchronous Advantage Actor Critic (A3C) algorithm with the velocity obstacle (VO) models to optimize evacuation in an airport environment under emergencies. A multi-agent collaborative evacuation modeling framework for a complex environment with moving threats will be developed to provide adaptive continuous decision-aid to each agent, in accordance to the changing environments.


    • English


    • Status: Active
    • Funding: $208835
    • Sponsor Organizations:

      Center for Advanced Transportation Mobility

      North Carolina Agricultural and Technical State University
      Greensboro, NC  United States  27411

      Office of the Assistant Secretary for Research and Technology

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

      North Carolina A&T State University

      1601 E. Market Street
      Greensboro, NC  United States  27411
    • Performing Organizations:

      Embry-Riddle Aeronautical University

      600 S. Clyde Morris Boulevard
      Daytona Beach, Fl  United States  32114
    • Principal Investigators:

      Liu, Dahai

    • Start Date: 20211001
    • Expected Completion Date: 20230731
    • Actual Completion Date: 0
    • USDOT Program: University Transportation Centers Program

    Subject/Index Terms

    Filing Info

    • Accession Number: 01841348
    • Record Type: Research project
    • Source Agency: Center for Advanced Transportation Mobility
    • Files: UTC, RIP
    • Created Date: Apr 2 2022 11:21AM