|Nvidia introduces next-gen AV processor at annual conference|
Nvidia Corp. made several mobility-related announcements this week, reasserting the ambitious role that the tech company hopes to play in autonomous vehicle development.
CEO Jensen Huang unveiled Nvidia's next-generation autonomous vehicle platform, Drive Atlan, during a virtual version of the Santa Clara, Calif., company's annual GTC GPU Conference.
Nvidia said its next system-on-a-chip technology, which will be available in a couple of years, will achieve 1,000 trillion operations per second — known as TOPS — and will also have an additional layer of cybersecurity via Nvidia's BlueField data processing unit.
The chip "fuses AI and software with the latest in computing, networking and security" and expands upon Nvidia's original Drive Xavier processor — already in production cars and trucks – as well as its Drive Orin processor, which will be a part of vehicle production beginning in 2022. Compared with Atlan, Nvidia's Xavier is capable of 30 TOPS, and Orin can achieve 254.
Atlan is slated for 2025 models and beyond.
"The transportation industry needs a computing platform that it can rely on for decades," Huang said in a press release. "The software investment is too immense to repeat for each car.
"Our new Drive Atlan is truly a technical marvel," he said.
During GTC, the company also announced Drive Sim, a simulated, cloud-based "proving ground" for use in development of self-driving vehicles.
Nvidia also said it has booked more than $8 billion in automotive business over the next six years. Among those using Drive products to power their AV development are Zoox, SAIC and Volvo, which said it will use Nvidia's Drive Orin chips to enable more autonomous driving functions starting next year.
"To achieve higher levels of autonomy in more conditions, the number of sensors and their resolutions will continue to increase," Huang added. "AI models will get more sophisticated. There will be more redundancy and safety functionality. We're going to need all of the computing we can get."
– Alexa St. John