New driverless vehicle maker Waabi is so close to getting how to do this
The article — Self-driving startup Waabi just managed to net $83.5M — how?
“The company’s breakthrough, AI-first approach, developed by a team of world leading technologists, leverages deep learning, probabilistic inference and complex optimization to create software that is end-to-end trainable, interpretable and capable of very complex reasoning. This, together with a revolutionary closed loop simulator that has an unprecedented level of fidelity, enables testing at scale of both common driving scenarios and safety-critical edge cases. This approach significantly reduces the need to drive testing miles in the real world and results in a safer, more affordable, solution.”
The closed-loop simulation environment is a replacement for sending real cars on real roads. In an interview with The Verge, Urtasan said that Waabi can “test the entire system” in simulation. “We can train an entire system to learn in simulation, and we can produce the simulations with an incredible level of fidelity, such that we can really correlate what happens in simulation with what is happening in the real world.”
Yes!!!!!!!!!!!! You understand you cannot rely on the real-world for most of the development and testing. The approach is untenable from a time, cost and safety POV. (More in my article below.) And you need simulation, informed and validated by the real-world to replace over 99% of it.
You are using the wrong simulation technology
The industry currently uses gaming technology to do this. Which from a visual POV is terrific. The problem is the physics and real-time limitations will preclude Waabi or anyone else from getting near L4. You may statistically get over 50% there but that doesn’t matter. You have to finish. Whether that is 49%, 10% or 2% of the work remaining. At some point the real-time limitations, model fidelity gaps especially sensors and sensors in tandem, will give you incorrect information, cause false confidence, rework and tragedies. More on how to do this right in my first article here. I would be glad to go into more detail with anyone who would like to chat. (Notice the head of Epic Unreal’s Sebastien Loze agrees with me. Epic actually gave us a grant to further the transfer of the tech to this domain.) And please do not ignore what I am saying here because your immediate reaction is that air travel is less complex than what is needed here. While that is correct, you would be missing the right use case set. Massive war games. Which take place in urban environments with just as many entities, sensors etc. However, they are far more precise, run in far faster real-time and have to deal with electronic warfare. And ignore the label on the models. It does not matter if the model, or math set, is called a plane, car, radar etc. What matters is the fidelity of the model with respect to the actual object being modified, especially in complex scenarios, and how much of that can be run at the same time and at what real-time rate.
SAE Autonomous Vehicle Engineering Magazine — Simulation’s Next Generation
Finally, please check out USDOT VOICES. They get all of this. (Note-they are starting off with gaming systems like CARLA to get folks in the game, as it were. They will including the right technology as they go.)
USDOT introduces VOICES Proof of Concept for Autonomous Vehicle Industry-A Paradigm Shift?
More in my articles below. Including how to fix of this overall:
The Autonomous Vehicle Industry can be Saved by doing the Opposite of what is being done now
Waymo and Tesla are nowhere near L4. Think anyone else is?
Autonomous Vehicle Industry’s Self-Inflicted and Avoidable Collapse — Ongoing Update
My name is Michael DeKort — I am a former system engineer, engineering, and program manager for Lockheed Martin. I worked in Aerospace/DoD/FAA simulation, as the Software Engineering Manager for all of NORAD, as a PM on the Aegis Weapon System, as a C4ISR systems engineer for the DHS Deepwater program and the lead C4ISR engineer for the Counter-terrorism team at the US State Department. I am now CEO/CTO at Dactle.
Industry Participation — Air and Ground
- Founder SAE On-Road Autonomous Driving Simulation Task Force
- Member SAE ORAD Verification and Validation Task Force
- Member UNECE WP.29 SG2 Virtual Testing
- Stakeholder USDOT VOICES (Virtual Open Innovation Collaborative Environment for Safety)
- Member SAE G-34 / EUROCAE WG-114 Artificial Intelligence in Aviation
- Member CIVATAglobal — Civic Air Transport Association
- Stakeholder for UL4600 — Creating AV Safety Guidelines
- Member of the IEEE Artificial Intelligence & Autonomous Systems Policy Committee
- Presented the IEEE Barus Ethics Award for Post 9/11 DoD/DHS Whistleblowing 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.