Smart Trailer Technologies for Data-Driven Safety, Efficiency, and Policy Innovation in Heavy-Duty Fleet Operations

Details

• Creators:
  Jahanbiglari, Ava ; Tang, Pingbo ; Zhang, Peter
• Corporate Creators:
  Carnegie Mellon University ; Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  • Trailers
  • Heavy duty trucks
  • Tractor trailer combinations
  • Automatic data collection systems
  • Blind spots
  • Cameras
  • Calibration
  • Benefit cost analysis
  • Near crashes
  • Fleet safety
  More +
• Publication/ Report Number:
  589
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report (July 1, 2025 - July 31, 2026)
• Corporate Publisher:
  Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)
• Description:
  This project developed an integrated framework for evaluating smart-trailer safety technologies using naturalistic vehicle data, camera-based ground localization, computer-vision auditing, and benefit-cost analysis. Naturalistic data from one trailer operated with two tractors across 13 trips and 10 collection dates produced 56 hours and 201,600 synchronized one-second observations. Tractor and trailer GNSS/IMU measurements, three exterior camera views, detector activity, and roadway context were used to characterize operating behavior across five environments. Ramp-classified operation showed the clearest trailer-specific departure from arterial operation, with lower trailer-relative yaw activity but higher trailer-relative lateral activity, indicating that tractor-only measurements may incompletely represent trailer response. Camera-specific pixel-to-ground mappings were also developed and evaluated. Strict nested validation showed the strongest performance for the driver-side camera, followed by the curb-side camera, while rear-camera continuous-distance estimates remained provisional. A retrospective audit of 156 videos further showed that the project computer-vision pipeline and recorder alarm boxes provided complementary but incomplete evidence, supporting an evidence-fusion approach rather than reliance on either source alone. A deterministic benefit-cost analysis found national side-guard BCRs of 0.106-0.122 under the modeled narrow NHTSA target population and quantified warning-system and targeted-deployment break-even conditions. Overall, the findings support trailer-aware monitoring, context-specific interpretation, camera-specific uncertainty controls, exposure-normalized alert evaluation, and targeted deployment strategies.
• Format:
  PDF
• Funding:
  69A3552344811 ; 69A3552348316
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/93540/dot_93540_DS1.pdf
• File Type:
  [PDF - 1.99 MB]
• Collection(s):
  University Transportation Centers
• Main Document Checksum:
  urn:sha-512:f616544a36f9be850eea68bd94805a33716998849c40fa615bb6c56fcc3e9c723f957f8cad15f33a47a91799ecd43c3d938ae39b57f5e1cd7c7034a4203da5fb