World First Driverless Race Car Will Be Powered By NVIDIA
Back in January NVIDIA had launched the DRIVE PX 2, the world's first in-car artificial intelligence supercomputer. Now it is planning to put it into use in building the first autonomous race car. The racing car tentatively titled ‘Deep Green’ will make a debut at the Formula E ePrix electric racing series, Roborace. At Roborace the same rules of electric racing apply except in this case the cars will be driverless. At the Roborace 10 teams will take part each with two driverless cars equipped with NVIDIA DRIVE PX 2 in one-hour long races. The teams will be given identical cars but they will be allowed to develop the software that will be at the heart of this challenge.
These race cars with NVIDIA DRIVE PX 2 at heart have been designed by auto designer Daniel Simon, the same man who designed those Tron: Legacy’s light cycles. The race cars are equipped with radar, lidar, cameras, GPS and high-definition mapping sensors that help them make sense of the race track. All this information is fed to the DRIVE PX 2 which has the combined computing powers of 150 MacBook Pros. The DRIVE PX 2 can perform 24 trillion deep learning operations per second with the help of two next-generation Tegra processors plus two next-generation discrete GPUs, based on the Pascal architecture.
So why is NVIDIA doing this? Well it’s to showcase the capabilities of the liquid cooled DRIVE PX 2 that it plans to sell to autonomous car makers in the future. The first edition of Roborace kicks off in September 2016 and if you want a chance to name the new autonomous car from NVIDIA head over to this #-Link-Snipped-#.
These race cars with NVIDIA DRIVE PX 2 at heart have been designed by auto designer Daniel Simon, the same man who designed those Tron: Legacy’s light cycles. The race cars are equipped with radar, lidar, cameras, GPS and high-definition mapping sensors that help them make sense of the race track. All this information is fed to the DRIVE PX 2 which has the combined computing powers of 150 MacBook Pros. The DRIVE PX 2 can perform 24 trillion deep learning operations per second with the help of two next-generation Tegra processors plus two next-generation discrete GPUs, based on the Pascal architecture.
So why is NVIDIA doing this? Well it’s to showcase the capabilities of the liquid cooled DRIVE PX 2 that it plans to sell to autonomous car makers in the future. The first edition of Roborace kicks off in September 2016 and if you want a chance to name the new autonomous car from NVIDIA head over to this #-Link-Snipped-#.
0
