The PX 2 is palm-sized and energy efficient but is supposed to be powerful enough for automated and autonomous vehicles to use for driving and mapping.
Advertisement
First recipient of the Drive PX 2 will be Chinese web services company Baidu which is deploying it as an in-vehicle computer for its own self-driving system.
The new single-core configuration will be used by Baidu in its own self-driving cars, as part of the previously announced partnership between the two companies to create a complete, “cloud-to-car” autonomous driving system. The Drive PX 2 system implements Nvidia’s Parker system-on-chip (SoC) configuration, which can process multiple cameras plus light detection and ranging, radar and ultrasonic sensors.
So the new NVIDIA DRIVE PX 2 for AutoCruise is practically a smaller DRIVE PX 2 with only one processor instead of the usual two. The company states that data scientists who train their deep neural networks in the data center on the Nvidia DGX-1 can then seamlessly run on Nvidia Drive PX 2 inside the vehicle.
It uses 10 watts of power and is mostly looking at providing AutoCruise functions including highway automated driving and HD mapping.
It was announced last week that the Drive PX 2 will be the AI engine of the Baidu self-driving auto.
The new DRIVE PX2 AI computer is chiefly aimed at automakers that are interested in developing fully or partially self-driving vehicles, which would typically require human intervention. This compatibility helps the unified AI architecture to enable cars to receive over-the-air updates and add new features and capabilities throughout the life of a vehicle. DriveWorks software and the Drive PX 2 configuration with two SoCs and two discrete GPUs are available already for developers working on autonomous vehicles. It supports automotive inputs/outputs, including ethernet, CAN and Flexray. “NVIDIA DRIVE PX 2 in the auto solves this challenge for our OEM and tier 1 partners, and complements our data center solution for mapping and training”.
Advertisement
To put its power in context, there is the stated capability of the AI’s single processor to combine incoming data inputs so that the computer could make sense of the complex picture and condition surrounding the vehicle and make decisions such as how it can plan a safe path forward.
