An HD Map to Avoid the Crash of the Autonomous Vehicle Industry

Switch most Public Shadow and Safety Driving for Development and Testing to Simulation using DoD Simulation Technology

· Please see my articles below explaining this. Without doing this no one can overcome the time, money and liability hurdles.

· Yes, it is possible, and has been in DoD for 25 years, to create a legitimate physics based, all model type digital twin for every single real-world compliment. And to run the most complex and dense scenarios possible. And faster than real time. Yup, I get this sounds like hype. Be glad to show you it is not. (And BTW this process creates an HD Map by default. Far cheaper than HD Mapping folks can create driving around. And the point cloud can have far better fidelity than any real LiDAR can produce.)

Use Dynamic Sense and Avoidance with selective Deep Learning

· Please see my article below explaining this. Without doing this no one can overcome the time, money and liability hurdles.

Use a top down Systems Engineering approach augmented by Agile

· This is not an app. There is far, far, far more engineering needed here in the exception handling or what-if scenarios than the “happy path”. For that reason, working your way up from the bottom stumbling on new areas to cover will result in so much rework and liability issues this alone will cause the whole effort to fail. If you have a legitimate all model type physics based digital twin you can now work on the hardest scenarios in parallel. Drastically speeding up discovery and lowering rework.

Work on the Hardest Scenarios as you work on the Simple Ones

· Now that you are using a real-world digital twin you can now work on the most complex scenarios right away. Doing so will massively speed up the discovery rate and drastically lower rework. If the most complex scenarios work odds are most of the lesser complexity scenarios work as well.

Employ a rules Based Real-time Verification System

· Augment that AI with a parallel non-ML based system that sets rules to avoid ML going off the ranch. Use RSS and what IVEX is doing as a start.

Stop the Hype and Treat Your People Right

· Even with the proper simulation there is a lot of work to do. Depending on the legitimate geofences and quantity of Deep learning being used you still have 5–10 years of work to do. Settle down and focus on your engineering, professional, ethical and moral due diligence. That includes not working your people like every day is critical. If it is, you have a very bad plan.

Help the Government write Testable Safety Standards now

· What is the leading cause of hype besides ignorance and ego? Being afraid of falling behind and funding going to someone else. This is solved by creating a new level playing field. Move the race over to seeing who can prove they meet a legitimate level of provable safety first. And shift or share your liability burden with the government. This is the path aerospace eventually took, after making many of the same mistakes you are. And it worked.

Don’t use Remote Control or Remote Safety Drivers

· Except as a legitimate last resort or where you actually solve the technical issues, stay away from this. Or it will lead to a tragedy. See more in my article below.

More in my articles here

Proposal for Successfully Creating an Autonomous Ground or Air Vehicle


Autonomous Vehicles Need to Have Accidents to Develop this Technology

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

Simulation can create a Complete Digital Twin of the Real World if DoD/Aerospace Technology is used

Why are Autonomous Vehicle makers using Deep Learning over Dynamic Sense and Avoid with Dynamic Collision Avoidance? Seems very inefficient and needlessly dangerous?


How NHTSA and the NTSB can save themselves and the Driverless Vehicle Industry


The Hype of Geofencing for Autonomous Vehicles

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


My name is Michael DeKort — I am a former system 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.

Key Industry Participation

- Lead — SAE On-Road Autonomous Driving SAE Model and Simulation Task

- Member SAE ORAD Verification and Validation Task Force

- Member DIN/SAE International Alliance for Mobility Testing & Standardization (IAMTS) Sensor Simulation Specs

- Stakeholder for UL4600 — Creating AV Safety Guidelines

- Member of the IEEE Artificial Intelligence & Autonomous Systems Policy Committee (AI&ASPC)

- Presented the IEEE Barus Ethics Award for Post 9/11 Efforts

My company is Dactle

We are building an aerospace/DoD/FAA level D, full L4/5 simulation-based testing and AI system with an end-state scenario matrix to address several of the critical issues in the AV/OEM industry I mentioned in my articles below. This includes replacing 99.9% of public shadow and safety driving. As well as dealing with significant real-time, model fidelity and loading/scaling issues caused by using gaming engines and other architectures. (Issues Unity will confirm. We are now working together. We are also working with UAV companies). If not remedied these issues will lead to false confidence and performance differences between what the Plan believes will happen and what actually happens. If someone would like to see a demo or discuss this further please let me know.