Michael DeKort
1 min readFeb 27, 2019

--

Starsky says “miles per disengagement can be gamed. Yes they can. But so is Starsky’s overall response here.

— They say accidents are a lagging indicator. yes but only if you use public shadow or remote driving vs proper simulation.

— The key problem with miles and disengagement metrics are the lack of scenario context. Starsky never says they will provide that.

— “Safety is the number one priority”. No it is clearly not. You cannot use processes that put people’s lives at risk for no reason and claim safety matters. Neither public shadow or remote driving can be made safe in critical scenarios. If they keep this up they will create thousands of needless casualties running thousands of accident scenarios thousands of times over to train the system.

If Starsky and most of the AV makers looked outside the echo chamber they would see the answer is aerospace/DoD/FAA level simulation and systems/safety engineering practices.

SAE Autonomous Vehicle Engineering Magazine End Public Shadow Driving

https://www.nxtbook.com/nxtbooks/sae/ave_201901/index.php

Remote Control for Autonomous Vehicles — A far worse idea than the use of Public Shadow “Safety” Driving

https://medium.com/@imispgh/remote-control-for-autonomous-vehicles-a-far-worse-idea-than-the-use-of-public-shadow-safety-df2ad64772c6

Common Misconceptions about Aerospace/DoD/FAA Simulation for Autonomous Vehicles

https://medium.com/@imispgh/common-misconceptions-about-aerospace-dod-faa-simulation-for-autonomous-vehicles-2b3ad84b0aa1

--

--

Michael DeKort
Michael DeKort

Written by Michael DeKort

Non-Tribal Truth Seeker-IEEE Barus Ethics Award/9–11 Whistleblower-Aerospace/DoD Systems Engineer/Member SAE Autonomy and eVTOL development V&V & Simulation

No responses yet