Vehicle-in-Virtual-Environment (VVE) Method for Developing and Evaluating VRU Safety of Connected and Autonomous Driving

The current approach to connected and autonomous driving function development and evaluation uses model-in-the-loop (MIL) simulation, hardware-in-the-loop (HIL) simulation and limited proving ground use, followed by public road deployment of the beta version of software and technology. The rest of the road users are involuntarily forced into taking part in the development and evaluation of these beta level connected and autonomous driving functions. This is an unsafe, costly and inefficient method and has resulted in many problems in the deployment of autonomous vehicles with an associated loss of trust. Motivated by these shortcomings, this project focuses on the Vehicle-in-Virtual-Environment (VVE) method of safe, efficient and low-cost connected and autonomous driving function development, evaluation and demonstration. The VVE method places the vehicle inside a highly realistic virtual environment with realistic virtual sensor feeds while the actual vehicle is physically running inside a large and empty test area. This is as if the vehicle is using a virtual reality headset. It is possible to easily change the virtual development environment and also inject rare and difficult events which can be tested very safely. This is a two-year project and will focus on the use of the VVE method for development and application of Vulnerable Road User (VRU) safety functions. Pedestrian safety will be treated in the first year of the project and bicyclist safety will be treated in its second year. The research will start by considering the following five pedestrian crash scenario use cases of: Crossing Roadway – Vehicle Not Turning (FARS 750), Walking/Running Along Roadway (FARS 400), Dash / Dart-Out (FARS 740), Crossing Roadway – Vehicle Turning (FARS 790), Crossing Expressway (FARS 910) during year 1 and the five bicyclist crash scenario use cases of: Motorist Overtaking Bicyclist (FARS 230), Bicyclists Failed to Yield – Midblock (FARS 310), Bicyclist Failed to Yield – Sign – Controlled Intersection (FARS 145), Bicyclist Left Turn / Merge (FARS 220), Motorist Left Turn / Merge (FARS 210) in year 2 where FARS is short for NHTSA’s Fatality Analysis Reporting System. Vehicle-to-VRU communication-based pedestrian/bicyclist detection which also works for non-line-of-sight cases will be combined with camera and lidar based detection within the VVE method. A data-driven approach will be used to predict the vulnerable road user trajectory which will be compared with the trajectory of the vehicle to predict a future collision possibility. Vehicle trajectory modification to avoid a possible future collision will be developed and evaluated safely using the VVE approach with the vehicle and VRUs at separate locations physically but on a collision risk path in the virtual environment which will enable very realistic evaluation of the designed VRU safety function. Robust and delay tolerant trajectory control will be developed and evaluated using the VVE method also, for executing the calculated collision free modified vehicle trajectory which may involve slowing down, braking or braking and steering. Virtual environments and collision risk scenarios will be developed and evaluated first in MIL and HIL, followed by development and evaluation using the VVE method.

• Record URL:
  https://ppms.cit.cmu.edu/projects/detail/422

Language

• English

Project

• Status: Active
• Funding: $155867
• Contract Numbers:

  69A3552344811

• Sponsor Organizations:

  Carnegie Mellon University

  Safety21 National UTC for Promoting Safety
  Pittsburgh, PA  United States  15213

  Office of the Assistant Secretary for Research and Technology

  University Transportation Center Program
  ,    
• Managing Organizations:

  Carnegie Mellon University

  Safety21 National UTC for Promoting Safety
  Pittsburgh, PA  United States  15213
• Project Managers:

  Stearns, Amy

• Performing Organizations:

  The Ohio State University

  ,    
• Principal Investigators:

  Guvenc, Levent

• Start Date: 20230701
• Expected Completion Date: 20240630
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Connected vehicles; Pedestrian safety; Test procedures; Trajectory control; Vehicle tests; Virtual reality; Vulnerable road users
• Subject Areas: Highways; Pedestrians and Bicyclists; Planning and Forecasting; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01900234
• Record Type: Research project
• Source Agency: Safety21
• Contract Numbers: 69A3552344811
• Files: UTC, RIP
• Created Date: Nov 20 2023 7:43PM