Evaluating Autonomous Vehicles' Pedestrian Safety Benefits in Road Networks

Details

• Creators:
  Joe-Wong, Carlee ; Yağan, Osman
• 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. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  • Autonomous vehicles
  • Actuated traffic signal controllers
  • Pedestrians
  • Pedestrian safety
  • Traffic congestion
  • Topology
  • Connected vehicles
  • Data analysis
• Publication/ Report Number:
  604
• 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:
  The purpose of this work was to investigate how CAV (connected autonomous vehicle) deployments affect pedestrian safety and the tradeoffs between safety and traffic congestion that are induced by CAV navigation around a city, particularly in the context of mixed human-driven vehicle and CAV populations. The project focused on developing methods to choose routing and control strategies that navigate this tradeoff, addressing scalability challenges in operating over city-wide road networks as well as exploring the use of large language models (LLMs) to reduce the need to gather new data on the effectiveness of different routing strategies. The main results include an algorithm that provably optimizes traffic congestion subject to a safety constraint, a characterization of the efficiency tradeoffs involved in partitioning a city into different regions for navigation control, techniques for making LLMs more efficient in generating navigation strategies for vehicles over time, and an analysis of how routing strategies must be adapted to local road topology in order to effectively account for traffic congestion.
• Format:
  PDF
• Funding:
  69A3552344811 ; 69A3552348316
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/93554/dot_93554_DS1.pdf
• File Type:
  [PDF - 1.71 MB]
• Collection(s):
  Autonomous Vehicles ; University Transportation Centers
• Main Document Checksum:
  urn:sha-512:851fd97a39ca831141405a986c95a43538174bf6a818e1c76cd83b55b70572ed0faed3d67a7502da8d71234060d37b6751c39ae80bae8a165078fc911baa1e47