Infrastructure-Based Sensor Fusion for Tracking Connected and Autonomous Supply Chain Assets in Cyber-Compromised Environments

The ongoing growth and economic benefits of America’s largest container ports are threatened by negative externalities associated with port operations, particularly increasing congestion and air pollution caused by drayage truck and rail modes serving the ports and traveling to inland transloading, rail yard, warehouse and distribution center facilities. For example, the San Pedro Bay Ports (SPBP) of Los Angeles and Long Beach in Southern California, the largest container port complex in the US and one of the largest in the world, is critical to the nation’s future intermodal logistics system and vital to our economic growth and standard of living. One proposed solution to these issues is to transition the heavy duty (HD) drayage fleet (as well as long haul fleets) to zero emission autonomous vehicles (AVs), in order to increase supply chain capacity, throughput, safety, resilience and sustainability. In this research, we plan to extend our Freight Mobility Living Laboratory (FML2) research of Year 1, which explored the feasibility of LiDAR technology for traffic monitoring in an infrastructure-based, side- fire LiDAR configuration. LiDAR-based microscopic longitudinal and lateral trajectories were obtained for HD vehicles at 0.1 second resolution, enabling site-based detection of anomalies in vehicle behavior. In Year 2, we will develop combined LiDAR and automated license plate reader (ALPR)-based models that will re-identify a potentially cyber-compromised HD AV (based on its anomalous trajectories) over long distances across a complex metropolitan highway network. The LiDAR-based approach to truck tracking is resilient and possesses inherent advantages over other competing technologies: Because LiDAR is an active sensor technology which measures light pulses emitted from the unit itself, it is unaffected by lighting conditions and offers an advantage over traditional cameras where glare, shadows and low-light conditions are known to adversely affect performance. And while automated license plate reader (ALPR) technology has demonstrated high accuracies in plate reads, it cannot be relied upon solely for vehicle reidentification as it performs best when a truck possesses a plate that is present and not obscured, which may not be the case for a cyber-compromised operator that is actively avoiding surveillance. Two existing FML2 study sites spanning over 40-miles across the Los Angeles freeway network – on Interstate I-710 near the SPBP, and on the SR-60 freeway en route to the Inland Empire logistics center, will be used in this study. Data will be collected and processed at both locations to develop a LiDAR point-cloud and ALPR-based long distance tracking and re-identification model to investigate proof-of-concept for corridor and network application of these technologies.

• Record URL:
  • https://utc.engineering.osu.edu/infrastructure-based-sensor-fusion-tracking-connected-and-autonomous-supply-chain-assets-cyber-compromised-environments

Language

• English

Project

• Status: Active
• Funding: $300000
• Contract Numbers:

  69A3552348327

• 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:

  Center for Automated Vehicle Research with Multimodal Assured Navigation

  Ohio State University
  Columbus, OH  United States  43210
• Project Managers:

  Kline, Robin

• Performing Organizations:

  University of California, Irvine

  Institute of Transportation Studies
  4000 Anteater Instruction and Research Building
  Irvine, CA  United States  92697
• Principal Investigators:

  Ritchie, Stephen

• Start Date: 20231030
• Expected Completion Date: 20250831
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Computer security; Connected vehicles; Data fusion; Drayage; Sensors; Supply chain management; Tracking systems; Truck traffic
• Subject Areas: Data and Information Technology; Freight Transportation; Motor Carriers; Security and Emergencies; Vehicles and Equipment;

Filing Info

• Accession Number: 01901378
• Record Type: Research project
• Source Agency: Center for Automated Vehicle Research with Multimodal Assured Navigation
• Contract Numbers: 69A3552348327
• Files: UTC, RIP
• Created Date: Dec 4 2023 5:21PM