Nvidia develops virtual testing platform for self-driving cars

Jasper Gonzales Valdez
            		      2:22 PM

Jasper Gonzales Valdez 2:22 PM

During his keynote today at NVIDIA's GPU Technology Conference, CEO Jensen Huang said the fatal accident reminded the company how important safety is when it comes to this type of technology.

The chipmaker is testing self-driving technology globally including in New Jersey, Santa Clara, Japan and Germany.

Nvidia announced it was working on the technology at last year's summit.

At the same time it's announcing the cessation of real-world testing, Nvidia also unveiled a new system for testing self-driving cars, one that takes place in a virtual rather than real-world environment. "It's a reminder of how hard SDC technology is and that it needs to be approached with extreme caution and the best safety technologies", a Nvidia spokesperson said in an email. Huang said the platform uses two different servers.

The second server is Nvidia's Drive Pegasus AI auto computer that runs a full autonomous-vehicle software stack, processing the simulated data the same way it would process data from a real self-driving auto.

Hamilton laments software glitch as Vettel victorious in Australian Grand Prix
Vettel, who secured his 48th career victory, added: "We are a little bit lucky today". His stoppage led to the deployment of the VSC, and Vettel gaining the lead.

The second server houses the Nvidia DRIVE Pegasus AI, which will process the gathered data as if it's coming from sensors in a self-driving vehicle on the road. The technology can simulate the billions of driving miles necessary to make self-driving cars a reality much faster than it would take to have physical cars drive them.

Uber isn't the only company affected by this incident; the fatality puts heavy scrutiny on other autonomous vehicle initiatives. The server sends driving commands back to the simulator, completing what the company calls the "hardware-in-the-loop cycle".

Around 320 companies involved in self-driving cars - from software developers, automakers and their suppliers, sensor and mapping companies - use Nvidia Drive platform, according to the company's website.

"Deploying production self-driving cars requires a solution for testing and validating on billions of driving miles to achieve the safety and reliability needed for customers", said Rob Csongor, vice president and general manager of Automotive at NVIDIA.

The idea of self-driving cars is gaining a lot of traction these days, but the incident in Arizona may put the idea of autonomous cars on hold for a while.

Recommended News

We are pleased to provide this opportunity to share information, experiences and observations about what's in the news.
Some of the comments may be reprinted elsewhere in the site or in the newspaper.
Thank you for taking the time to offer your thoughts.