This is my keynote talk and list of related publications on a broader view of self-driving vehicle safety and the need to revisit how we think about safety engineering in the age of autonomous systems.
Abstract:
Removing the human driver from a road vehicle fundamentally changes the assurance argument approach needed for safety. We must start with a deeper inquiry into what we actually mean by acceptable safety. A simplistic "safer than human driver" positive risk balance approach must be augmented with additional considerations regarding risk transfer, negligent driving behavior, standards conformance, absence of unreasonable fine-grain risk, ethics, and equity concerns. Once we have a more robust understanding of what it means to be acceptably safe, we will find that current standards frameworks and accompanying definitions are likely to be inadequate to assure safety due implicit assumptions that are violated when the human driver is removed. We propose a new framework for relating risk to acceptable safety based on satisfying multiple stakeholder constraints rather than taking a risk optimization point of view. This broadens safety approaches in a way needed to deal with autonomous vehicles.
Slides are here: https://users.ece.cmu.edu/~koopman/lectures/L152_2024-10-understanding_AV_safety.pdf
YouTube version here: youtu.be/trEHUVuvX08
Archive.org downloadable video here: https://archive.org/details/l-152-understanding-self-driving-vehicle-safety
Related reading with the details:
Koopman, P., & Widen, W., "Redefining Safety for Autonomous Vehicles," SafeComp 2024.
Extended length preprint including appendix (May 2024): Arxiv | author copy
Koopman, P. & Widen, W., "Breaking the Tyranny of Net Risk Metrics for Automated Vehicle Safety," SCSC eJournal, Jan. 2024. (SSRN preprint | author copy)
Koopman, P., How Safe Is Safe Enough? Measuring and Predicting Autonomous Vehicle Safety, September 2022. ISBN: 979-8848273397 (Details & Preview | Note links)
Share this post