Car

The Brains behind Fully Self-Driving Taxis Just Got Smarter

 

The brains behind self-driving vehicles are rapidly evolving to meet the ambitions of automakers and tech companies that intend to launch truly driverless cars over the next few years.

Silicon Valley chip maker Nvidia, one of the industry’s most prominent suppliers of artificial-intelligence systems, unveiled a supercomputer tailored for use in autonomous taxis that can reach Level 5 automation—that is, operation without human oversight or input—and handle every conceivable road situation. The company’s system, dubbed the Drive PX Pegasus, can process more than 320 million operations per second.

That’s about 13 times faster than the company’s current Drive PX 2, which crunches 24 million operations per second. As more than two dozen companies set their sights on deploying fleets of driverless taxis, industry analysts say that’s the kind of processing power necessary to fuse raw data provided by lidar, radar, and cameras, allowing self-driving vehicles to detect obstacles and determine where they are on the road.

“Today, dozens of companies are racing to develop robo-taxis, but they are still gated by the massive computation needs of a truly driverless car,” said Luca De Ambroggi, senior principal automotive analyst at IHS Markit. Nvidia’s latest, he said, “shows the path to production for the automakers, startups and automotive ecosystem working to deliver this.”

“We need more computational horsepower to train
-cars on how bad drivers drive.”

– Danny Shapiro, Nvidia

Without human oversight, readying these cars means preparing them for every possible circumstance they’ll encounter. The increase in mental horsepower allows for developers of these vehicles to better plan for a wider range of driving scenarios.

“We’ve been working with a lot of different automakers, and they already have their cars driving through a lot of challenging situations,” said Danny Shapiro, the senior director of Nvidia’s automotive division. “The next challenge, though, is to instill the ability humans have to understand subtleties and other randomness on the road. We need more computational horsepower to train cars on how bad drivers drive. We’re not going to be able to prevent other people from hitting us, but the more we can have automated vehicles on the road, the greater the benefit to society and the better the reduction of accidents.”

Nvidia-DHL
  • Facebook
  • Google+
  • Pinterest
  • StumbleUpon

The advent of the Pegagus specifically, along with advances in self-driving technology in general, comes at a time when rates of traffic fatalities and injuries continue to climb on U.S. roads. Fresh statistics released by the National Highway Traffic Safety Administration last week said 37,461 people died in traffic crashes in 2016, a 5.6 percent increase over the previous year.

While more mental horsepower might be the signature advance for this company’s latest product, it’s not the only distinguishing feature. The Pegasus packs its power on a device roughly the size of a license plate—the same size as its predecessor with about 13 times more processing power. It’s also more energy efficient, an important consideration for companies basing their autonomous plans around battery-powered vehicles.

“Dozens of companies are racing to develop robo-taxis,
-but they are still gated by the massive computation needs
-of a truly driverless car.”

– Luca De Ambroggi, IHS Markit

Shapiro said the first Pegasus units will be ready for customers in the second half of 2018. Nvidia’s announcement comes at a time when the company is facing increasing competition from Intel, which spent $15 billion on computer-vision software provider Mobileye earlier this year and revealed last month that it has been a secret partner involved in Google’s self-driving-car project for the past eight years.

Beyond Pegasus, Nvidia further announced a partnership Tuesday with German supplier ZF Group and global delivery company DHL Group that aims to deploy a test fleet of autonomous delivery trucks starting in 2018. The trucks will be equipped with ZF’s ProAI self-driving system, which is based on Nvidia’s Drive PX platform.

Working together, the companies hope to push new innovations in moving goods from central distribution hubs to their destinations, with a focus on the last mile of the journey. DHL says it hopes to wring a 30 percent increase in package-delivery efficiency as the technology evolves.

  • Facebook
  • Google+
  • Pinterest
  • StumbleUpon



Source link

قالب وردپرس

0

Leave a Reply

Pin It on Pinterest

Share This
Close