- New computer for self-driving cars
- AI supercomputer adopted by SAP
NVIDIA is pushing ahead with its plans to conquer the road - via self-driving cars. At the inaugural GPU Technology Conference in Europe in Amsterdam, the company's CEO Jen-Hsun Huang unveiled Xavier, a new AI 'supercomputer', designed for use in self-driving cars.
“This is the greatest SoC endeavor I have ever known, and we have been building chips for a very long time,” Huang told the conference’s 1,600 attendees.
Xavier is a complete system-on-chip (SoC), integrating a new GPU architecture called Volta, a custom eight core CPU architecture and a new computer vision accelerator. The processor will deliver 20 TOPS (trillion operations per second) of performance, while consuming only 20 watts of power. As the brain of a self-driving car, Xavier is designed to be compliant with critical automotive standards, such as the ISO 26262 functional safety specification.
Packed with seven billion transistors and manufactured using a 16 nanometre FinFET process technology, Nvidia says a single Xavier AI processor will be able to replace today’s Drive PX 2 configured with dual mobile SoCs and dual discrete GPUs, but with a fraction of the power consumption.
Because autonomous driving is an incredibly compute-intense process, the need for an efficient AI processor is paramount. Xavier will bring self-driving car technology to automakers, tier 1 suppliers, startups and R&D organisations that are building autonomous vehicles, whether cars, trucks, shuttles or taxis.
You can see Nvidia's AI car learning how to drive in this video below.
AI or GPU-based deep learning is a major R&D field for Nvidia. “GPU computing is at the beginning of something very, very important, a brand new revolution, what people call the AI revolution, the beginning of the fourth industrial revolution,” Huang said. “However you describe it, we think something really big is around the corner.”
Huang also detailed the Alpha 1 release of the company's DriveWorks software which incorporates a number of new modules, including support for free space detection - which helps self-driving cars determine where it is safe for cars to drive; distance detection; lane detection; and 3D bounding boxes, which determine the size and shape of objects around the car.
Huang showed how a new neural network, PilotNet, will enable the handling of more challenging situations, such as construction sites, night driving and foul weather. Another neural network, OpenRoadNet, will enable free space computation and enable the creation of the occupancy grid to help cars determine where they can safely drive.
“Together we will work as an industry to move autonomous driving forward, this is going to be an area of research and development for years to come,” Huang said. DriveWorks Alpha 1 will be released to early partners this month.
Huang also announced that global navigation provider, TomTom, will port and run their localisation and mapping software on Nvidia hardware. In addition, the company's DriveWorks software will integrate support for TomTom’s HD mapping environment.
TomTom is working to create high-definition maps of the world’s driveable roads. “You want to localise your car with a centimetre of accuracy, because you don’t want to miss by 20 centimetres when you have a self driving car,” explained Alain De Taeye, of TomTom’s management board.
“People used to believe creating navigable maps was unaffordable, now people believe HD maps, which are very detailed, very accurate is unaffordable - it’s not: you need to be clever about it and use AI and AI platforms to automatically create and maintain them,” De Taeye said.
The announcement follows similar news from Taiwan and China that are building their self-driving car efforts around Nvidia's technologies.
Nvidia is focussed on not just self-driving AI, but other applications of AI as well. Huang announced that two of Europe’s top AI research centers will collaborate with his company to ramp up their efforts in the fast-growing field.
The German Research Center for Artificial Intelligence and Switzerland’s Dalle Molle Institute for Artificial Intelligence will both be early users of the new Nvidia DGX-1 AI supercomputer. Huang also announced that software powerhouse SAP is now using DGX-1 AI supercomputers at its operations in Potsdam, Germany, and in Israel, where teams are building machine learning solutions for enterprises.
“Now with the partnership of SAP, we will soon have applications running on these servers to serve the world’s largest enterprises,” Huang said. Over the last two months, DGX-1 has been adopted by AI labs around the world, including those based at UC Berkeley, Stanford University and OpenAI.
DGX-1 packs some 170 teraflops of computing power, equal to 250 conventional servers, into a single box. It uses eight Nvidia Pascal powered Tesla P100 accelerators, interconnected with high-speed NVLink technology.
AMD unveils world’s first hardware-virtualised GPU line
AMD looks to heaven for salvation
Nvidia announces new graphics card
Review: Nvidia GeForce GTX 1060, the new mainstream champion
For more technology news and the latest updates, follow us on Twitter, LinkedIn or Like us on Facebook.