Advancing AI Applications for Knowledge Discovery, Capture, And Delivery at State DOTs

State departments of transportation (DOTs) are facing a critical workforce transition as large numbers of experienced engineers, planners, maintenance managers, and technical experts approach retirement. This demographic shift threatens the loss of institutional and tacit knowledge that supports effective decision-making, project delivery, operations, and innovation. Existing knowledge-management approaches are often fragmented and insufficient for systematically capturing and transferring experiential knowledge across agencies. At the same time, transportation agencies are becoming increasingly digital and data-driven, relying on technologies such as intelligent transportation systems, analytics, digital twins, and artificial intelligence (AI)-enabled tools. Advances in AI, particularly in Large Language Models (LLMs), semantic models, and Retrieval Augmented Generation (RAG), offer opportunities to improve knowledge discovery, synthesis, retrieval, and delivery within transportation agencies. AI applications such as chatbots, intelligent assistants, semantic search, and interactive knowledge exploration tools can help employees quickly locate technical standards, business processes, lessons learned, datasets, and expert guidance. Several DOTs are independently piloting AI-based knowledge discovery and delivery (KDD) applications, but there is limited research on scalable, transferable frameworks that support knowledge capture, workforce onboarding, training, and enterprise-wide information access. There is also a need to address governance, data quality, privacy, interoperability, model transparency, and long-term maintenance of AI-enabled knowledge systems. The objective of this research is to advance AI applications for knowledge discovery, capture, and delivery within state DOTs by developing a scalable transportation-specific LLM framework that captures, organizes, synthesizes, and disseminates institutional knowledge. The research will assess current AI-based KDD practices; identify promising applications and use cases; develop standardized protocols for data ingestion, annotation, and evaluation; and establish governance frameworks for responsible AI deployment.

• Record URL:
  • http://apps.trb.org/cmsfeed/TRBNetProjectDisplay.asp?ProjectID=6072
• Supplemental Notes:
  • Contract to a Performing Organization has not yet been awarded.

Language

• English

Project

• Status: Proposed
• Funding: $500,000.00
• Contract Numbers:

  Project 23-56

• 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: 20260608
• Expected Completion Date: 0
• Actual Completion Date: 0

Subject/Index Terms

• TRT Terms: Artificial intelligence; Knowledge management; State departments of transportation
• Subject Areas: Data and Information Technology; Planning and Forecasting; Transportation (General);

Filing Info

• Accession Number: 01992223
• Record Type: Research project
• Source Agency: Transportation Research Board
• Contract Numbers: Project 23-56
• Files: TRB, RIP
• Created Date: Jun 10 2026 11:08AM