Nvidia has unveiled a palm-sized, artificial intelligence (AI) computer for providing convenience in the technology of autonomous vehicles. With the Nvidia Drive PX 2 AI,automakers can power automated and autonomous vehicles for driving and mapping. AutoCruise functions like highway automated driving and HD mapping can be enabled with the help of its single-processor configuration. The Drive PX 2’s config is said to be energy efficient since it uses only 10 watts of power. Even with a less power consumption, the device enables vehicles to use deep neural networks to process data from multiple cameras and sensors.
Volvo and Uber join forces to develop autonomous cars
Nvidia Drive PX is part of the brand’s computing solutions and data scientists who train their deep neural networks in the data center on the Nvidia DGX-1 can run on Drive PX 2 inside the vehicle. The Drive PX 2 enables automakers and their tier 1 suppliers to accelerate production of automated and autonomous vehicles. A car using this device can understand in real time what is happening around it, precisely locate itself on an HD map and plan a safe path forward. The same Nvidia DriveWorks algorithms, libraries, and tools that run in the data center also run in the car. This end-to-end approach leverages Nvidia’s unified AI architecture, and enables cars to receive over-the-air updates to add new features and capabilities throughout the life of a vehicle.
This semi-autonomous Mercedes-Benz Future Bus just drove 20 KM inside Amsterdam all by itself
Baidu’s autonomous car will employ the Nvidia Drive PX 2 for its self-driving cloud-to-car system. It will be the AI engine of the Baidu self-driving car and a partnership has been announced that will deliver a self-driving cloud-to-car system for Chinese automakers, as well as global brands. On the initiative, Liu Jun – Vice President of Baidu expressed that Baidu and Nvidia are leveraging AI skills together to create a cloud-to-car system for self-driving.The new, small form-factor Drive PX 2 will be used in Baidu’s HD map-based self-driving solution for car manufacturers.
To this, Rob Csongor, Vice President and General Manager of Automotive at Nvidia added that bringing an AI computer to the car in a small, efficient form factor is the goal of many automakers. Nvidia Drive PX 2 in the car solves the challenge for their OEM and tier 1 partners, and complements their data center solution for mapping and training.
Some key features of the Nvidia Drive PX 2 are as follows-
- Nvidia Drive PX 2 is powered by the company’s newest system-on-a-chip.
- Features a GPU based on the Nvidia Pascal architecture.
- A single Nvidia Parker system-on-chip (SoC) configuration can process inputs from multiple cameras, plus lidar, radar and ultrasonic sensors.
- Supports automotive inputs/outputs, including ethernet, CAN and Flexray.
The new single-processor Drive PX 2 will be available to production partners in the last quarter of 2016. DriveWorks software and the Drive PX 2 configuration with two SoCs and two discrete GPUs are available already for developers working on autonomous vehicles.