BACKGROUND
State and local departments of transportation (DOTs) are being asked to solve ever more complex transportation problems and issues. Artificial Intelligence (AI) is being proposed and implemented to help address a number of these issues, such as improving safety, alleviating traffic congestion, assisting in real-time systems management, accommodating connected/automated vehicles, preserving the infrastructure, improving organizational efficiency, and customer service, among others. According to Gartner Information Technology Glossary (2021), AI applies advanced analysis and logic-based techniques, including machine learning, to interpret events, support and automate decisions, and take actions. At the same time, large amounts of both structured and unstructured data from various sources have become available for transportation applications.
A Transport Research International Documentation (TRID) literature search identified almost 100 papers on AI applications in transportation published in the Transportation Research Board’s (TRB) Transportation Research Record (TRR) in the last 5 years alone. However, almost all of these papers deal with very specific applications of AI. With the exception of the Transportation Research Circular E-C113: “Artificial Intelligence in Transportation” (2007) and Transportation Research Circular E-C168: “Artificial Intelligence Applications to Critical Transportation Issues” (2012), there is no strategic guidance that state and local DOTs can use to develop guidance, policies, and standards, and ensure a knowledgeable workforce that will enable them to effectively understand, develop, and apply AI solutions to improve their operations and to solve transportation problems. There is also a need to document and share current information on agency experiences with AI, including promising applications.
STATUS
