At its annual press event to kick off CES 2016, Nvidia unveiled its second-generation Drive PX platform.
Dubbed Drive PX 2, this new "automotive supercomputing platform" can process up to 24 trillion deep learning operations per second, and, according to Nvidia, has the processing power of 150 MacBook Pros. "That's 10 times the performance of the first-generation DRIVE PX, now being used by more than 50 companies in the automotive world," said Nvidia in an official blog post. "And it's the size of a lunchbox in contrast to earlier autonomous-driving technology being used today, which takes up the entire trunk of a mid-sized sedan."
The Drive PX 2 will be first deployed by Volvo next year, with some help from Budapest-based automated-driving AI company AdasWorks. "In the world's first public trial of autonomous driving, the Swedish automaker next year will lease 100 XC90 luxury SUVs outfitted with DRIVE PX 2 technology," said Nvidia. "The technology will help the vehicles drive autonomously around Volvo's hometown of Gothenburg, and semi-autonomously elsewhere." The trial is part of Volvo's "Drive Me" self-driving car pilot program. In addition to AdasWorks and Volvo, Toyota and Preferred Networks are working together to bring Nvidia's deep learning platform to autonomous driving. Preferred Networks has been working with the platform on a variety of applications, including image recognition, automated control of robotics, health diagnostics, and more. According to the founder of the Tokyo-based company, all of this was done "with a single Nvidia GPU-powered deep neural network, in a very short time." Nvidia's autonomous car platform is also being used by Tokyo-based ZMP for its proposed driverless "Robot Taxi" service.
Photo: © iStock.