Behavioral Safety Assessment towards Large-scale Deployment of Autonomous Vehicles, Part II: Assessment Results

Key points

• In Part I of this study, we propose a dedicated third-party testing initiative for systematically evaluating AV behavioral safety.1
• In this paper, we validate our proposed framework using Autoware.Universe, an open-source Level 4 Automated Driving System (ADS), tested both in simulated environments and on the physical test track at the University of Michigan's Mcity Testing Facility.1
• The results indicate that Autoware.Universe possesses 6 out of 14 behavioral competencies and exhibited a crash rate of 3.01x10^-3 crashes per mile, approximately 1,000 times higher than the average human driver crash rate.1
• During the tests, we also uncovered a number of unknown unsafe scenarios for Autoware.Universe.1

Sources (1)

• [1]Behavioral Safety Assessment towards Large-scale Deployment of Autonomous Vehicles, Part II: Assessment Results
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 02:43 PM

  Third-party evaluations of autonomous vehicle (AV) safety can play a vital role in improving public acceptance, building consumer confidence, and establishing effective safety standards.

  In Part I of this study, we propose a dedicated third-party testing initiative for systematically evaluating AV behavioral safety.

Extractive summary: sentences quoted from the sources.