How Cognata and NVIDIA enable autonomous vehicle simulation
FYI, this story is more than a year old
Cognata announced it is one of the ecosystem partners working with NVIDIA to accelerate testing and validation within the automated driving development process.
Cognata and NVIDIA are delivering a wide array of scenario and traffic models for validation using large-scale, hardware-in-the-loop simulation.
Cognata will provide AI-powered traffic agents based on real-world driver behaviour and an interface for easy creation of highly-realistic scenarios to advance autonomous vehicle (AV) development on the NVIDIA DRIVE Constellation platform.
Using the computing power of two different servers, DRIVE Constellation can generate millions of miles of AV testing in bit-accurate simulation.
The first server runs DRIVE SIM software to simulate a self-driving vehicle’s sensors, while the second server contains the powerful DRIVE AGX Pegasus AI car computer, processing the simulated data as if it were actually driving on the road.
Cognata’s solution leverages AI, deep learning, and computer vision to create a realistic traffic environment, where virtual cars behave just as they would in the real world.
Cognata CEO Danny Atsmon says, “Cognata and NVIDIA are creating a robust solution that will efficiently and safely accelerate autonomous vehicles’ market entry.
“Highly accurate and scalable traffic model simulation technology is essential to validate autonomous vehicle systems within nearly infinite combinations of real-world scenarios.”
Bit-accurate simulation not only reduces testing time and cost but also produces better product quality and increases safety.
This integration makes new, more advanced scenarios possible and simplifies the process of creating them.
NVIDIA GM Zvi Greenstein says, “NVIDIA and Cognata share the vision of using large-scale, cloud-based, open simulation to thoroughly and safely train and test self-driving cars under endless challenging situations.
“This offering will help accelerate the safe deployment of autonomous vehicles.”