HD Mapping, Sensor companies and others relying on L4 systems or mass scenario testing is on a path to Bankruptcy if AV makers don’t change their development approach
Back when I wrote a similar article on Sensor vendors, I neglected to mention HD Mapping companies. Fact is any company who relies on driverless vehicles getting to L4/5, or even widespread test scenarios being run, will go bankrupt soon. Assuming the revenue model of sensor vendors and any other company supporting this industry relies on mass production sales they should be driving an industry to switch to proper simulation to develop and test these systems. If they do not, the limbo period they are in now will literally be perpetual. Bankrupting most of them.
Except for those involved with Tesla, which has no LiDAR, there are only under 2000 autonomous vehicles on the road in the US. Since the approach current shadow and safety driving approach can never yield anything close to a L4 system for time, cost and safety/liability reasons sales and the associated revenue and profits will never come. Not even from Tesla’s who may produce more vehicles with more sensors however that is a fraction of the possible whole and they to will stop when the first child or family is killed by the reckless and unnecessary safety driving process. The reason for all of this is below. While supporting simulation would lower near term sales it would bring L4 in from never to 5–10 years.
Of course, this is all avoidable if AV makers shift most of their development to proper, not gamin-based, simulation. More detail in my article below.
The Autonomous Vehicle Industry can be Saved by doing the Opposite of what is being done now
Proposal for Successfully Creating an Autonomous Ground or Air Vehicle
Simulation can create a Complete Digital Twin of the Real World if DoD/Aerospace Technology is used
Simulation Photorealism is almost Irrelevant for Autonomous Vehicle Development and Testing
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
- Founder SAE On-Road Autonomous Driving Simulation Task Force
- Member SAE ORAD Verification and Validation Task Force
- 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.