While the premise is to be applauded and Applied Intuition offers some assistance, like most of the simulation products in this domain, they rely on gaming architectures and approaches. While the tech can have value it cannot create anything close to a legitimate digital twin. As a result you cannot rely on it for most edge cases, nor that last "10%" or so. The system simply cannot model active sensors properly nor most objects. And it cannot run in proper real-time or faster when loaded. All of this will result in major model fidelity gaps when compared to the real-world, false confidence, flawed stack planning and execution, continued over reliance on public human Guinea pigs, needless harm to people and massive amounts of lost time and money.
More in my articles here
The Autonomous Vehicle Industry can be Saved by doing the Opposite of what is being done now
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