Mr. Krafcik — There seems to be a lot of wordsmithing and misdirection here? Are you saying there is no safety driving? Not in any capacity? If not how are you testing? If you mention simulation please specify the % of development and test done in the real-world, test tracks and simulation. Of course if you use the proper simulation, tech from DoD and aerospace where real-time and EVERY model is a legitimate digital twin you could make this statement. But I do not believe that is what you are doing. (I would glad to show you my POV on proper simulation is correct.)

I say and ask this because it appears to me you are trying to hide what you really doing, misleading people and give them false confidence. If I read this article carefully what I see is your mentioning production desires and a small test case with no safety driver. All meant to lead people to believe this is the extent or most of what you do for do regarding development and testing. The omissions and what is clearly stated in your latest safety report tell me you use safety driving for most development and test. A stealth effort you want to hide. Is that not true? At the end of the day skipping L3 for production is good and will save lives. But using safety drivers for development and test will still injure and kill your employees and the public around them when accident scenarios are learned.

Using the Real World is better than Proper Simulation for AV Development — NONSENSE

Autonomous Vehicles Need to Have Accidents to Develop this Technology

The Hype of Geofencing for Autonomous Vehicles

Systems Engineer, Engineering/Program Management -- DoD/Aerospace/IT - Autonomous Systems Air & Ground, FAA Simulation, UAM, V2X, C4ISR, Cybersecurity