The race to fully autonomous cars is on.
And Nvidia is trying to accelerate that push by introducing its new in-car computer, the Drive PX 2, touting a mind-numbing 12 CPU cores and eight teraflops of processing punch. Sheesh!
Tech Times got to see it in action this week in Nvidia's booth in the Las Vegas Convention Center, as part of the Consumer Electronics Show 2016, and it's impressive, to say the least.
The company believes the integration of its PX2 with its previous in-car computer, the CX, can help to deliver a deeper learning-based solution for autonomous driving, not to mention an intuitive human-machine interface for self-driving cars.
How advanced is this supercomputer? Well, the company claims the Drive PX 2 is capable of 24 trillion deep-learning operations per second and packs the processing prowess for deep learning equivalent to that of 150 MacBook Pros.
The company wants autonomous cars to fully rely on its Drive PX 2, which it claims can handle all its demands, including being able to "process the inputs of 12 video cameras, plus Lidar, radar and ultrasonic sensors," fusing them to "accurately detect objects, identify them, determine where the car is relative to the world around it, and then calculate its optimal path for safe travel." Lidar, a remote sensing technology, uses lasers to measure distance by illuminating a target and analyzing the reflected light.
That "optimal path for safe travel" that Nvidia describes is bolstered by an in-depth knowledge of roads, even able to alert the car of things like roadside construction, an accident or traffic, all in real-time.
As confident as Nvidia is with its newest in-car computer's ability, automakers seem to be, too.
Volvo has tabbed the PX 2 to supply powerful in-vehicle artificial intelligence for its own autonomous driving testing.
Does this bring fully autonomous cars one step closer?