AI-Driven Predictive Safety Framework for V2X-Based Road User Protection

The Utah Department of Transportation (UDOT) has made notable progress in deploying LiDAR and Vehicle-to-Everything (V2X) systems at intersections to improve roadway safety for both motorized and vulnerable road users (VRUs), including pedestrians and cyclists. These systems can detect multiple road users and broadcast warnings through connected infrastructure, forming the foundation for proactive safety management. However, two major challenges remain. First, current LiDAR-based systems primarily detect VRUs but lack the predictive capability to anticipate their future movements or interactions with vehicles. Without behavior modeling and trajectory forecasting, V2X systems can only respond to imminent risks rather than prevent conflicts before they occur. Second, although V2X technologies are expanding statewide, there is no standardized framework to evaluate how these systems influence driver behavior or reduce VRU-related near-misses and collisions. The absence of field-based performance measurement limits UDOT’s ability to quantify safety benefits and guide data-driven improvements. This project aims to address these gaps by developing and deploying an AI-powered predictive safety framework that integrates LiDAR sensing and V2X communication to protect VRUs in real traffic environments.

Language

• English

Project

• Status: Active
• Funding: $50,000.00
• Contract Numbers:

  268125

• Sponsor Organizations:

  Utah Department of Transportation

  4501 South 2700 West
  Project Development
  Salt Lake City, UT  United States  84114-8380
• Managing Organizations:

  Utah Department of Transportation

  4501 South 2700 West
  Project Development
  Salt Lake City, UT  United States  84114-8380
• Project Managers:

  Jensen, Travis

• Performing Organizations:

  University of Utah

  Department of Civil and Environmental Engineering
  110 Central Campus Drive Suite 2000
  Salt Lake City, UT  United States  84112
• Principal Investigators:

  Liu, Cathy

• Start Date: 20251030
• Expected Completion Date: 20261031
• Actual Completion Date: 0

Subject/Index Terms

• TRT Terms: Connected vehicles; Intersections; Laser radar; Pedestrian movement; Pedestrian vehicle interface; Vehicle to everything communications; Vulnerable road users
• Geographic Terms: Utah
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Safety and Human Factors;

Filing Info

• Accession Number: 01972950
• Record Type: Research project
• Source Agency: Utah Department of Transportation
• Contract Numbers: 268125
• Files: RIP, STATEDOT
• Created Date: Nov 26 2025 7:22PM