The transportation industry is going through a major transition with vehicles defined not by horsepower but by computing capability. Driving this revolution is AI and the immense possibilities that it brings by powering autonomous vehicles (AV) that will shape the way people and goods are moved in the days to come.
In his talk entitled Transforming the Transportation Industry with AI at InnoVEX Forum on June 1, Ali Kani shared his belief that the AV represents the most intense AI challenge, and why it is one that will have the greatest impact.
“Autonomous driving technology will no doubt make our roads much safer and more efficient — and ultimately alter how roads, cities and suburbs are designed,” said the Vice President and General Manager of Automotive at NVIDIA.
Speed of development flow vital
NVIDIA is building the end-to-end NVIDIA Drive platform – from AV chip, computer and sensor architecture, to data processing, AV perception and mapping software. Built to the highest functional safety and cybersecurity standards, the platform also extends to the infrastructure that does training and creation of a simulated digital twin, fleet command and operations centre.
“Since AV is such a grand challenge and will take years to develop, we believe what differentiates AV excellence more than anything else is the speed of this development flow. Companies with the best development flows will be the most successful,” said Kani.
AV development process will keep improving to make AI-powered vehicles smarter and smarter over time as software is trained for new tasks, enhanced, tested, and validated, then updated over-the-air.
Asia Pacific startups such as Faraday, Li Auto, NIO, SAIC, and Xpeng are among hundreds of companies globally that are developing cars using NVIDIA Drive.
NVIDIA has also created the Omniverse simulation platform that enables AV to be tested on realistic real-world scenarios. Only with a combination of on road testing and simulated testing can there be the assurance that the AV is ready to drive safely.
“What is exciting about this market is that cars doing full self-driving are putting computers that include not just our SoCs but also use our Ampere-based GPUs,” said Kani.