While autonomous driving is on its way to roadways everywhere, according to Rand Corp such vehicles will need to drive 10 billion miles in order to reach a human-level error rate—and that can take years to achieve. Even the largest developers of autonomous vehicles have only accumulated a few million miles in autonomous mode after years of testing.

Led by Danny Atsmon, a deep-learning expert who formerly served as Harman’s director of ADAS and senior director of machine learning, Cognata says it provides a realistic virtual automotive environment that simulates real-world test driving and generates fast, highly accurate results. The simulation engine reproduces sensor input in high fidelity by emulating interactions with real-world materials.

Furthermore, Cognata can recreate cities anywhere in the world, allowing a significantly expanded range of testing scenarios beyond the current limited geographies.

Every autonomous vehicle developer faces the same challenge—it is really hard to generate the numerous edge cases and the wide variety of real-world environments. Our simulation platform rapidly pumps out large volumes of rich training data to fuel these algorithms. We’re excited to introduce a scalable, safe, and cost-effective solution that not only accelerates the development and validation of autonomous vehicles, but also ensures that vehicles can be much safer when they’re deployed in the real world.

—Danny Atsmon

After extensive technical evaluation of the team and the technology, we look forward to using Cognata’s technology, which can accelerate the time to market for land-based autonomous systems as well as the kind of aerial systems we are focusing on.

—François Auque of Airbus Ventures