Nvidia has launched its Tegra X1 powered Drive computers for auto-piloted cars, one computers-Drive PX, for developing auto-pilot capabilities, and another Drive CX, for advanced cockpit systems.
Th vision of the future was presented in the first public demo of NVIDIA DRIVE PX by Nvidia CEO Jen-Hsun Huang, kicking off the International Consumer Electronics Show. “When you’re done with dinner, you can say ‘come back to me’ … and it becomes an auto-valet,” Jen-Hsun said. “That car meanders back out and gets back to the driver.”
The Nvidia Drive PX auto-pilot provides new features in computer vision, based on the new Nvidia Tegra X1 mobile superchip, with built-in NVIDIA’s latest Maxwell GPU architecture that delivers over one teraflop processing power.
Drive PX, featuring two Tegra X1 super chips, can take inputs of up to 12 high-resolution cameras, with 1.3 gigapixels per second processing capability and its computer vision has Auto-Valet, that allows the car to find a parking space and park itself, all self-driven. It also finds parking lot even in crowded space and returnd when summoned by the driver with the help of a smartphone.
The Nvidia Drive CX cockpit is fitted with advanced graphics and computer vision for navigation, infotainment, digital devices and provides driver monitoring system, besides Surround-Vision, that too 360-degree view of the car in real time without the need for mirrors.
With Tegra X1 or Tegra K1 processors, the Drive software has been completely tested and can power up to 16.8 million pixels on multiple displays, which is 10 times more than that of the existing car systems.
“It’s an incredibly rich and visually complex environment that simulates the way light reflects from cars and obstacles in real time,” says Mark Daly, who leads our demo team. ““It’s a perfect virtual world.”
DRIVE PX gathers information from the surrounding virtual world, simulated on its five PCs with NVIDIA GPUs, via virtual fisheye-lens cameras attached to a simulated car.
“All the car knows about is what it can see via the simulated front, rear and side cameras that are mounted on it,” says Cem Cebenoyan, director of engineering for computer vision devtech at NVIDIA. Nvidia plans to release it in the market around the second quarter of this year.