Network Level Proactive Traffic Operations Indicator (NPTOI) Using Artificial Intelligence (AI) and Connected Vehicle Data Integration

This project will focus on developing an extensive and implementable artificial intelligence (AI)-driven Network Level Proactive Traffic Operations Indicator (NPTOI) system aimed at mitigating urban traffic congestion and delays through effective and proactive prediction and prevention of traffic disruptions. The system will be built on real-time sensor-based and connected vehicle data, including various crowdsourced data from platforms such as the newly released Streetlight connected vehicles data, Lytx, LYNX, etc. and infrastructure-based data from Automated Traffic Signal Performance Measures (ATSPM), and as needed Microwave Vehicle Detection Systems (MVDS) and data from other available sensors, e.g., Close Circuit TVs (CCTVs), that could be used for validation or augment crowdsourced data. The NPTOI system can be integrated into existing traffic management infrastructure through testing and validation. NPTOI can also be used in a dashboard system that evaluates change over time and alerts operators to changes in the field that may affect traffic operations. Additionally, the University of Central Florida (UCF) team will analyze and report on the most effective Connected Vehicles data types for enhancing Florida Department of Transportation (FDOT) operations. Machine Learning (ML) methods such as Graph Neural Networks (GNN) and other techniques will be deployed to make such predictions since several ML algorithms are able to capture spatial and temporal features. Various data sources would be explored, and a combination of the sources will be experimented to obtain the best output predictions. The expected outcome of the research would enable FDOT to transition to AI-driven analysis reports that can screen network level traffic to give mobility indicators. The expectation is that such metric can enable operators to make decisions that can alleviate congestion.

Language

• English

Project

• Status: Active
• Funding: $247,948.00
• Contract Numbers:

  BED28 977-18

• Sponsor Organizations:

  Florida Department of Transportation

  Research Center
  605 Suwannee Street MS-30
  Tallahassee, FL  United States  32399-0450
• Managing Organizations:

  Florida Department of Transportation

  Research Center
  605 Suwannee Street MS-30
  Tallahassee, FL  United States  32399-0450
• Project Managers:

  Dilmore, Jeremy

• Performing Organizations:

  University of Central Florida, Orlando

  12443 Research Parkway, Suite 207
  Orlando, FL  United States  32826-
• Principal Investigators:

  Aty, Ahmed

• Start Date: 20250327
• Expected Completion Date: 20270228
• Actual Completion Date: 0
• USDOT Program: Advanced Research
• USDOT Program: Air Traffic Control/Technical Operations Human Factors
• USDOT Program: Vehicle Safety Research

Subject/Index Terms

• TRT Terms: Artificial intelligence; Congestion management systems; Connected vehicles; Crowdsourcing; Data fusion; Machine learning; Sensors; Traffic signal control systems
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Vehicles and Equipment;

Filing Info

• Accession Number: 01950201
• Record Type: Research project
• Source Agency: Florida Department of Transportation
• Contract Numbers: BED28 977-18
• Files: RIP, STATEDOT
• Created Date: Mar 28 2025 8:00AM