Implementing and Leveraging Artificial Intelligence and Machine Learning at State Departments of Transportation

As artificial intelligence (AI) and machine learning (ML) technologies are becoming more ubiquitous, it is important for state Departments of Transportation (DOTs) to evaluate, understand, and leverage them for problem solving, advanced data analytics, automation, and to anticipate disruptive change as a result of AI and ML. Data are the fuel for AI and ML; therefore, the right data management strategy is needed to increase the odds of success. State DOTs are eager to capture the potential of AI, but there is confusion around the overwhelming number of potential applications and regarding which use cases are realistic to pursue. For example, analyzing data to predict citizen preferences and behavior, leveraging AI to automatically classify complex data, AI- driven search, and autonomous vehicles are gaining gradual adoption and may soon be deployed to transportation systems. As a result, it is important for state DOTs to anticipate this disruptive change. The emergence of big data from Internet of Things (IoT) devices, UASs, and LiDAR, etc., presents additional challenges for state DOTs with limited resources to be able to consume and react to big data. The objectives of this research are to provide the state DOTs with tools and information to implement and leverage AI and ML for the efficient, intelligent operation of a state DOT, and to facilitate evidence-based decision making. The research will look at the (a) desirability (use cases and scenarios where AI and ML are best positioned to help); (b) feasibility (model validation, pilot and other such confirmation steps); and (c) viability (focusing on ROI, and a set of readiness criteria) of using AI and ML techniques. The proposed research will (1) illuminate the impact of AI/ML on compliance and governance; (2) generate better understanding of AI and ML; (3) identify and learn from existing implementations at state DOTs; (4) develop common use cases; (5) provide investment return analysis; (6) identify data maturity required; (7) develop common tools such as AI and ML models and code repositories that can be shared by state DOTs; and (8) generate an understanding of the skills necessary to leverage AI/ML at a state DOT. This research will benefit state DOTs by helping them chart a course to successfully pursue AI and ML program, set up key foundational elements and technologies, improve their data analytics capability, leverage existing data for insights and decision making, increase automation in state DOT functions, and anticipate disruptive change instead of reacting to it. The desired outcomes and final products may include (a) a report outlining research methods and findings; (b) an approach to build a roadmap for an AI and ML program within a state DOT, including key foundational elements that must be considered; (c) a set of procedures to help narrow the focus toward practical use cases, with examples; (d) AI and ML case studies that were developed during research; (e) code repositories/tools that will be shared with all state DOTs; and (f) a guide to the necessary training for state DOT employees to properly utilize AI and ML.


  • English


  • Status: Proposed
  • Funding: $350000
  • Contract Numbers:

    Project 23-16

  • Sponsor Organizations:

    National Cooperative Highway Research Program

    Transportation Research Board
    500 Fifth Street, NW
    Washington, DC  United States  20001

    American Association of State Highway and Transportation Officials (AASHTO)

    444 North Capitol Street, NW
    Washington, DC  United States  20001

    Federal Highway Administration

    1200 New Jersey Avenue, SE
    Washington, DC  United States  20590
  • Project Managers:

    Mohan, Sid

  • Start Date: 20200520
  • Expected Completion Date: 0
  • Actual Completion Date: 0

Subject/Index Terms

Filing Info

  • Accession Number: 01739666
  • Record Type: Research project
  • Source Agency: Transportation Research Board
  • Contract Numbers: Project 23-16
  • Files: TRB, RiP
  • Created Date: May 18 2020 3:05PM