Control of Connected and Autonomous Vehicles for Congestion Reduction in Mixed Traffic: A Learning-Based Approach

Building on prior work on lane keeping and lane changing for connected and autonomous vehicles, this collaborative research project aims at taking a significant step forward to develop innovative learning-based, real-time control algorithms for connected and autonomous vehicles to reduce traffic congestion. This project aims at achieving four major objectives: (1) developing a traffic light prediction method by utilizing advanced deep learning techniques; (2) developing a trajectory optimization framework for a stream of vehicles to efficiently reduce the traffic congestion, attenuate the stop-and-go waves, and increase the throughput of the traffic; (3) integrating reinforcement learning techniques with (control) barrier functions to address the safety-oriented learning-based trajectory tracking control of autonomous vehicles; (4) validating the proposed congestion-reducing scheme with real-world vehicle trajectory data and SUMO testing under different environments in the presence of different vehicle mixes and driver uncertainties.


  • English


Subject/Index Terms

Filing Info

  • Accession Number: 01897925
  • Record Type: Research project
  • Source Agency: Connected Communities for Smart Mobility Towards Accessible and Resilient Transportation for Equitably Reducing Congestion (C2SMARTER)
  • Contract Numbers: 69A3551747124
  • Files: UTC, RIP
  • Created Date: Oct 30 2023 10:33PM