Traffic Control based on CARMA Platform for Maximal Traffic Mobility and Safety

Details

• Creators:
  Li, Xiaopeng (Shaw) ; Noyce, David A. ; Huang, Heye
• Corporate Creators:
  Center for Connected and Automated Transportation (CCAT) ; University of Michigan Transportation Research Institute
• 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
• Subject/TRT Terms:
  Autonomous Vehicles Congestion Management Systems Connected Vehicles Mobility Optimization Traffic Platooning Traffic Safety
• Publication/ Report Number:
  CCAT-2025-527
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report (January 2023 – July 2025)
• Corporate Publisher:
  University of Michigan. Center for Connected and Automated Transportation
• Abstract:
  This project developed and evaluated an online adaptive platoon control framework for connected and automated vehicles (CAVs) that simultaneously enhances mobility and safety through integration with digital infrastructure based on the CARMA platform. The proposed Physics Enhanced Residual Learning (PERL) framework combines a physics-based centralized controller, which models vehicle dynamics to ensure stability, with a neural network-based residual learning module that adaptively corrects unmodeled dynamics in real time. PERL can contribute to CARMA’s platooning plugin as a tactical-level cooperative longitudinal control component, enabling adaptive gap regulation and disturbance mitigation. High-fidelity simulations and scaled robot car experiments were conducted to assess performance under diverse traffic and disturbance scenarios. Results show that the PERL framework significantly improves position and speed tracking accuracy, achieves rapid convergence following external disturbances, and maintains robust platoon stability compared to purely physics-based or purely learning-based approaches. These findings demonstrate that the PERL framework can reduce the conventional safety–mobility trade-off in CAV platooning and support deployment within Transportation System Management and Operations (TSMO) strategies. Transportation agencies and system developers may apply this approach to improve cooperative driving efficiency, enhance roadway throughput, and inform future standards for adaptive platoon control systems.
• Format:
  PDF
• Funding:
  69A3551747105
• Collection(s):
  University Transportation Centers Autonomous Vehicles
• Main Document Checksum:
  urn:sha-512:a7c070cd9f877656f348255bc78471ea461e322907f89a9c2df168bc03768a897313494e075f86d962cef5674499e2d36ffe6739009cb1ac31c6e97615d3c28e
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/86274/dot_86274_DS1.pdf
• File Type:
  [PDF - 3.08 MB ]