If that’s the case then NVIDIA’s new chip aims to gear up the next generation of driverless racing cars. It’s the Drive PX 2 inside the automobile competing in Roborace then. Although the GPU maker has made autonomous cars a major company focus a few years ago, but today, Nvidia announced something a bit more daring at the GPU Technology Conference in San Jose.
CEO Jen-Hsun Huang claims that the new NVIDIA technology would empower the custom sports cars rivaling in the upcoming driverless racing series Roborace. Announced at CES actually! Specifically, the company’s Drive PX 2 liquid-cooled supercmputer would at first make up the brains of these futuristic vehicles.
Now, it’s a bit clear to say that Nvidia’s Drive PX 2 will be used in autonomous racecars for the Roborace championship. Also revealed that the company is owrking on an end-to-end mapping system using the same technology-based cars and Tesla GPUs, the latter of which are typically installed in the data center.
For starters, the Roborace Championship is a part of the Formula E ePrix “electric” racing series, meaning the racecars are driverless and only utilize alternative “earth-friendly” enrgy sources. Thse racings consist of ten teams that use two idential cars packing Nvidia’s Drive PX 2 and those cars doesn’t rely on driver intuition to win the car race, the teams must program the AI to be highly strategic.
About it! The Drive PX 2 itself will work with a host of sensors, including radar, GPS, LIDAR, cameras and high-definition mapping sensors and will learn and improve over time on real-time cars race. According to Nvidia, its supercompuer is the size of a lunchbox, keeping with the overall compact design of the cars. The Drive PX 2 is also capable of up to 24 trillion operations a second for AI applications, further providinbg “supercomputer-class” performance, or the processing power of 150 MacBook Pros. With deep integration of capabilities, the cars will become more uniqe and smarter – and thus – more than an actually racing cars.
However, the HD mapping system found on the Drive PX 2 is an open platform based purely on Nvidia’s DriveWorks SDK, which is “highly-efficient” that pushes most of the data processing onto the Chip to make communication to be on cloud at minimal. It also uses a new tecnique that Nvidia calls “visual simultanious localization and mapping” along with deep learning that manages to handle the whole mapping process.
It’s the world’s first in-car artificial intelligence supercomputer, that Nvidia launched it at this year’s CES 2016 in January. Called Drive PX 2! Additional information regarding Nvidia’s Drive solutions can be found here. Witness! The first Roborace series will kick off this September.
You may also like to check out:
- NVIDIA Announces Quadro M5500 VR-Ready GPU For Use In Laptops, Details Professional Plans
- Tesla Model 3 Electric Car Pitched As An ‘Affordable’ Electric Car: Price, Features, Release Date And More