Development and Evaluation of a Large Language Model and Virtual Reality Framework for Improving Flagger Training

Flaggers are essential for maintaining traffic safety in work zones, serving as human traffic controllers who coordinate alternating traffic through the work zone, yet they work under extremely hazardous conditions in close proximity to high-speed traffic and heavy equipment. Traditional classroom-based training is often insufficient for developing situational awareness, hazard recognition, and communication skills, while real-world training exposes trainees to significant risk. Virtual reality (VR) offers immersive, hands-on practice without danger, but current VR systems rely on preprogrammed scenarios and require instructors to manually identify trainee errors. This project develops a large language model (LLM)-based virtual flagger that provides dynamic, realistic interactions within a VR training environment rather than rigid, pre-scripted scenarios. The virtual flagger engages in natural radio communication, responds contextually to trainees’ actions, asks clarifying questions when communication is unclear, and adapts its behavior to create diverse, progressively challenging training experiences.

• Record URL:
  • https://smartercenter.org/about-2/projects/development-and-evaluation-of-a-large-language-model-and-virtual-reality-framework-for-improving-flagger-training/

Language

• English

Project

• Status: Active
• Funding: $400,000.00
• Contract Numbers:

  69A3552348303

• 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:

  Safety and Mobility Advancements Regional Transportation and Economics Research Center

  Morgan State University
  Baltimore, MD  United States 
• Performing Organizations:

  Safety and Mobility Advancements Regional Transportation and Economics Research Center

  Morgan State University
  Baltimore, MD  United States 
• Principal Investigators:

  Khazanovich, Lev

• Start Date: 20260801
• Expected Completion Date: 20280301
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Flaggers; Machine learning; Training; Virtual reality; Work zone safety
• Subject Areas: Data and Information Technology; Education and Training; Highways; Safety and Human Factors;

Filing Info

• Accession Number: 01997628
• Record Type: Research project
• Source Agency: Sustainable Mobility and Accessibility Regional Transportation Equity Research Center
• Contract Numbers: 69A3552348303
• Files: UTC, RIP
• Created Date: Jul 30 2026 4:26PM