Generating Safety-Critical Driving Scenarios for the Design of the CAV Proving-Ground - Using Domain Knowledge, Causality, and Large Language Models

Details

• Creators:
  Zhao, Ding
• Corporate Creators:
  Mobility21, Carnegie Mellon University
• Corporate Contributors:
  Carnegie Mellon University. Traffic21 Institute. Safety21 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:
  • Artificial intelligence
  • Autonomous vehicles
  • Connected vehicles
  • Forecasting
  • Machine learning
  • Safety
  • Test procedures
  • Virtual reality
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report
• Corporate Publisher:
  Mobility21, Carnegie Mellon University
• Abstract:
  The goal of this project is to study the critical scenario generation, design a testing framework, and use the generated scenarios to help the design of autonomous vehicle proving ground infrastructure aiming at the connected and autonomous vehicles evaluation. These scenarios should reflect the critical factors and risky driving conditions in the real world. Therefore, this objective encompasses the utilization of real-world datasets and the reasoning ability of large language models (LLMs).
• Format:
  PDF
• Funding:
  69A3552344811
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/78030/dot_78030_DS1.pdf
• File Type:
  [PDF - 215.79 KB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; Autonomous Vehicles ; University Transportation Centers
• Main Document Checksum:
  urn:sha-512:5ac92082974708296af16b5ce6dbc44fb4d17cc6994bbca0782c182fbc9788d3f594bb88b30012dd2d98f18db9ea26d35c1f5bf6211cd4309edab7f7ba331423