My name is Michael DeKort. I am a former systems engineer, engineering and program manager for Lockheed Martin. I worked in aircraft simulation, the software engineering manager for all of NORAD, the Aegis Weapon System, and on C4ISR for DHS. I also worked in Commercial IT and Cybersecurity. I received the IEEE Barus Ethics Award for whistleblowing regarding the DHS Deepwater program post 9/11 — http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=4468728
I am also a member of the SAE On-Road Autonomous Driving Validation & Verification Task Force
Your decision to restart Uber’s public shadow driving effort to create your autonomous vehicles is an extremely bad decision. Not just for Uber but for those whose lives you will take for absolutely no reason.
I would like to make you are aware of several major safety and viability issues with how Uber and most AV makers are trying to create AVs. Specifically around public shadow driving and L3. It is a myth that public shadow driving is a viable method to create AVs. That process can never come close to creating an AV. You cannot drive the one trillion miles or spend over $300B to do so. You also cannot create any more casualties especially a child or family. The path you are on will create thousands of them as you move into more complex and dangerous scenarios. Both due to handover and because you will have to run thousands of accident scenarios thousands of times. Do you really think you will ever run complex and accident scenarios enough times to get close to finishing? One more death, especially that of a child or family and you and the industry are mostly likely done. I will do my best to ensure that. As I would greatly prefer you and every AV maker are successful I implore you to replace 99% of your public shadow driving with proper simulation. Unfortunately it appears from your quote below you do not understand what proper simulation can do.
“Manual driving allows us to see in real-time different scenarios that our self-driving cars will encounter on the road,” Meyhofer writes. “We then recreate those scenarios in a virtual world, and on the test track, to improve overall system performance under similar conditions.” No word, though, on the breadth of Uber’s simulation program.” (Verge — Uber’s self-driving cars are back on public roads, but under human control)
Should you do the right thing and switch to 99% simulation use you must look outside of the products in this industry to ensure you have what you need to complete all the scenarios required and not be lulled into a significant level of false confidence. There are simply to may capability gaps in the simulation systems available especially in the cloud. Examples being vehicle, road, tire and environmental models are not precise enough, systems have latency and timing issues and most don’t use full motion simulators. I suggest the solution is to leverage the FAA simulation testing and aerospace/DoD technology to fill those gaps.
Please find more information in my article below.
Impediments to Creating an Autonomous Vehicle
Autonomous Levels 4 and 5 will never be reached without Simulation vs Public Shadow Driving for AI