Skip to main content

Volkswagen enlists Nvidia’s powerful Xavier chip for autonomous cars

Nvidia
Image used with permission by copyright holder
Nvidia kicked off CES 2018 on a high note by introducing an autonomous machine processor named Xavier. Designed to help self-driving cars merge into the mainstream, Xavier is billed as the world’s most complex and advanced system on a chip (SoC).

“In the future, every car will be self-driving. There will be 100 million cars built each year, millions of robotaxies, and several hundred thousand trucks. All of it will be autonomous. On top of this, what will define the driving experience is the artificial intelligence (AI),” Nvidia CEO Jensen Huang promised during a press conference in Las Vegas.

Recommended Videos

He pointed out Xavier is, by far, the most complex project Nvidia has ever embarked on. Without getting too technical, the processor relies on nine billion transistors to monitor information sent by the numerous sensors required to make a car drive itself safely and smoothly. “It can never fail because lives are at stake. And it has to make the right decision, running software the world has never known how to write,” Huang explained.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

Nvidia will place Xavier at the center of Pegasus, an AI computing platform built to power level five (fully autonomous) vehicles. It’s built on two Xavier processors and a pair of next-generation GPUs. It handles 320 trillion operations per second; in simpler terms, it delivers the performance of a trunk full of PCs in an apparatus no bigger than a license plate.

Xavier will reach the market this quarter, a little over a year after it was announced, and Nvidia has already received numerous orders. Aurora, the start-up company founded by former Google engineer Chris Urmson, will leverage Xavier’s capacities to develop the level four and five self-driving platforms it will supply to car companies. Volkswagen and Hyundai are currently working with Aurora, and we expect more companies will announce a partnership in the coming months.

“Nvidia Xavier is a key element of Aurora’s computer, delivering the performance needed to power self-driving system,” Urmson said in a statement.

Xavier will help Volkswagen bring the production version of the I.D. Buzz concept to the market. Expected to arrive in 2022, the retro-inspired electric van will offer a high level of autonomy. It’s safe to assume the technology will trickle down to other upcoming members of the German company’s lineup, including more electric cars. AI tech from Nvidia will also continue to power Uber’s ever-growing fleet of self-driving cars and trucks in the coming years.

“We’ve been integrating and running our self-driving cars and trucks on Nvidia’s GPU technology, and will explore other Nvidia platforms as they become available,” an Uber spokesperson told Digital Trends. The tech firm isn’t planning on using Xavier chips, however.

Nvidia’s venture into the automotive industry doesn’t end there. The company also announced it has teamed up with German components manufacturer ZF and Chinese tech giant Baidu to develop a mass production-ready autonomous vehicle platform specifically for the Chinese market. That involves dealing with the chaotic traffic on Chinese roads, a task that’s easier said than done. Designed for mass production, the platform uses Nvidia’s Xavier chip, ZF’s ProAI car computer, and Baidu’s Apollo Pilot.

Updated by Ronan Glon: Added Uber statement.

Ronan Glon
Former Digital Trends Contributor
Ronan Glon is an American automotive and tech journalist based in southern France. As a long-time contributor to Digital…
Nvidia’s latest A.I. results prove that ARM is ready for the data center
Jensen Huang at GTX 2020.

Nvidia just published its latest MLPerf benchmark results, and they have are some big implications for the future of computing. In addition to maintaining a lead over other A.I. hardware -- which Nvidia has claimed for the last three batches of results -- the company showcased the power of ARM-based systems in the data center, with results nearly matching traditional x86 systems.

In the six tests MLPerf includes, ARM-based systems came within a few percentage points of x86 systems, with both using Nvidia A100 A.I. graphics cards. In one of the tests, the ARM-based system actually beat the x86 one, showcasing the advancements made in deploying different instruction sets in A.I. applications.

Read more
Nvidia lowers the barrier to entry into A.I. with Fleet Command and LaunchPad
laptop running Nvidia Fleet Command software.

Nvidia is expanding its artificial intelligence (A.I.) offerings as part of its continued effort to "democratize A.I." The company announced two new programs today that can help businesses of any size to train and deploy A.I. models without investing in infrastructure. The first is A.I. LaunchPad, which gives enterprises access to a stack of A.I. infrastructure and software, and the second is Fleet Command, which helps businesses deploy and manage the A.I. models they've trained.

At Computex 2021, Nvidia announced the Base Command platform that allows businesses to train A.I. models on Nvidia's DGX SuperPod supercomputer.  Fleet Command builds on this platform by allowing users to simulate A.I. models and deploy them across edge devices remotely. With an Nvidia-certified system, admins can now control the entire life cycle of A.I. training and edge deployment without the upfront cost.

Read more
Nvidia is renting out its AI Superpod platform for $90K a month
nvidia hgx 2 supercomputer server nvidiadgx2

Nvidia is looking to make work and development in artificial intelligence more accessible, giving researchers an easy way to access its DGX supercomputer. The company announced that it will launch a subscription service for its DGX Superpod as an affordable way to gain entry into the world of supercomputers.

The DGX SuperPod is capable of 100 petaflops of AI performance, according to the company, and when configured 20 DGX A100 systems, it's designed for large-scale AI projects.

Read more