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

Details

• Creators:
  Jiang, Zhong-Ping ; Ozbay, Kaan ; Li, Xianning
• Corporate Creators:
  New York University. Tandon School of Engineering
• Corporate Contributors:
  Connected Communities for Smart Mobility Toward Accessible and Resilient Transportation for Equitably Reducing Congestion (C2SMARTER) Tier-1 University Transportation Center (UTC) ; 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 Machine Learning Trajectory Control Vehicle Mix
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Corporate Publisher:
  Connected Communities for Smart Mobility Toward Accessible and Resilient Transportation for Equitably Reducing Congestion (C2SMARTER) Tier-1 University Transportation Center (UTC)
• Abstract:
  Based on the traffic light prediction and trajectory optimization techniques for a stream of CAVs, the proposed congestion-reducing scheme can increase the throughput of the transportation network by attenuating the deceleration and acceleration of vehicles before the signalized intersections, accompanied by decreased fuel consumption and emissions. By integrating the state-of-art reinforcement learning and control-theoretic methodologies, the motion of the autonomous vehicles can be well guided such that fewer numbers of lane changes are possible and the reference trajectory from the trajectory planning module can be accurately tracked with stability guarantee and collision avoidance with surrounding vehicles and pedestrians.
  
  The proposed congestion-reducing control scheme for CAVs can significantly improve safety, strengthen economics, ameliorate climate, and promote mobility equity. Impact will be measured by a number of performance measures, including safety (miles driven without disengagement, collision rate per mile, adherence to traffic laws, etc.) and economics/congestion (traffic flow improvement, travel time reduction, average vehicle speed in areas with CAVs compared to areas without, etc.).
  
  
• Format:
  PDF
• Funding:
  69A3552348326
• Collection(s):
  University Transportation Centers Autonomous Vehicles
• Main Document Checksum:
  urn:sha-512:efba6dd3e01ee65ac78e1b0f315249ba2981a3399aa3eb4b5ba46efb90de01312432c970059f2aa7ea0f81422d82106d9d6efb0a439abe632d0c3678749207d2
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/86345/dot_86345_DS1.pdf
• File Type:
  [PDF - 5.86 MB ]