Elon now using HD Maps for his “autopilot” after saying they (and LiDAR) are a crutch-The families of those killed by his ignorance and arrogance would disagree
Elon has said the use of detailed or HD Maps and LiDAR. The problem is his systems have no suitable replacement for either.
Elon Musk Declares Precision Maps A “Really Bad Idea” — Here’s Why Others Disagree
In the case of not using LiDAR Elon and Tesla severely overestimated what cameras can do, especially without true stereo pairs. That has led to several deaths including a repeat scenario involving Joshua Brown and Jeremy Banner 3 years apart. Their systems cannot determine the lateral position of a stationary or crossing object. (Elon won’t capitulate on this until he is forced. Both because of his fragile ego and because they would likely need a massive hardware upgrade in addition to software.)
In the case of mapping data Tesla’s systems cannot dynamically produce miracles at this point. Parking lots are very dense as are some intersections, especially with regards to many lit and until signs. Without detailed maps determining which signs to ignore can be very hard. To make matters worse, and in true Elon arrogant and ignorant fashion, they are crowd sourcing the maps using their overly trusting human Guinea pigs’ customers and their family’s vs buying the maps. As with e Brown/Banner scenario this means the locations will have to be driven several times in several direction to get all the data. That will lead to avoidable accidents, injuries, and deaths. (Yes, it is true Tesla has a massive “geofence”. If they were to buy HD Maps it would be a massive expense. First, you can disallow the cars from operating where an area is not properly learned. In addition, his customers pay a massive and ever-increasing amount for AP and FSD. Spend the money.) What Elon and Tesla should do is switch to proper (DoD not gaming) simulation for most of the development and test since the use of public shadow and safety driving can never yield anything close to a legitimate L4, will never save the lives that tech would save and harms people as unnecessary test subjects for no reason. But even if you ignore that, add LiDAR and proper maps or for the latter disallow features until the locations are mapped.
More below
Tesla using Human Guinea Pigs to Test Autopilot Traffic Light and Stop Sign Development — What Could Go Wrong?
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
Autonomous Vehicles Need to Have Accidents to Develop this Technology
Using the Real World is better than Proper Simulation for AV Development — NONSENSE
An HD Map to Avoid the Crash of the Autonomous Vehicle Industry
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.
