This site may earn affiliate commissions from the links on this page. Terms of utilize.

Jen-Hsun Huang raving about the Nvidia powered Robocar for Roboracing

Nvidia doesn't always announce new consumer graphics cards at its annual technology conference, but it was widely expected to this year. Instead, GTC 2022 is all well-nigh AI, VR, and especially self-driving cars. Following up on its annunciation of the Drive PX two car estimator, Nvidia updated its plans to ship a complete set of developer tools — fueled by its own autonomous vehicle research — for car makers, and to sponsor and help equip a robot car racing league.

DriveWorks is the power behind the Bulldoze PX 2

A supercomputer in your trunk, similar Nvidia's Drive PX 2, isn't much good without the software to run information technology. That'due south where Nvidia'south DriveWorks platform comes in. Outset announced at CES, it is getting closer to reality with a "Leap 2022" ship date. Nvidia CEO Jen-Hsun Huang as well used his keynote to get into more than detail about what it will include. The developer platform starts with sensor fusion and calculator vision software that can piece of work with up to 12 cameras and other sensors to provide a comprehensive model of the vehicle's surroundings. From at that place, advanced machine learning capability will assist with navigation, vehicle command, and path planning.

Path planning is the tricky process of deciding where to navigate the car in traffic or through an intersectionLoftier-quality maps, similar those from Hither, are too going to be supported. Ane interesting feature is support for map cosmos using the DriveWorks in-car platform coupled with cloud-based processing for the actual map creation. It was a lilliputian unclear from Huang'south description exactly how all this would work — except that he hopes and expects that that cloud volition be populated with Nvidia'south new $130K DGX-ane supercomputer — but what is articulate is that he sees this technology greatly reducing the cost of mapping areas, and of training autonomous vehicles. In particular, it should make it possible to practise a amend job of keeping maps upwards to date. Instead of needing routes to be re-driven with expensive, specialized, vehicles to pick up changes in the road layout or obstacles, data from "regular" Drive PX two-equipped cars could be used.

Self-driving with DAVENET, or "I can do that, Dave"

Rounding out Nvidia's DriveWorks offer will be a deep neural network (DNN) that has been trained to know how to drive. Traditionally, democratic vehicles, such equally the ones used in the DARPA challenge, have relied on manually-coded algorithms to follow a desired route, and provide vehicle control. Nvidia (along with many other current vehicle research teams) has been experimenting with using deep learning neural networks instead. According to Huang (and illustrated with a demo video), later only iii,000 miles of supervised driving, its car — powered by its DAVENET (formerly named DRIVENET) neural network — was able to navigate on freeways, country roads, gravel driveways, and in the rain.

The computing power required to recoginize and accurately track dozens of objects across many cameras and sensors is definitely supercomputer worthyOf class, what he showed was only a demo video. But all in all, it was quite a remarkable achievement when contrasted with the hundreds of human years of coding that went into the much-less-sophisticated driving of the DARPA challenge cars only ten years ago. Patently, Nvidia isn't suddenly planning to go a car visitor, simply it will be providing its applied science as role of the ready of tools for the auto industry to utilise to take advantage of its Bulldoze PX ii. Huang showed, for example, how the PX two's ability to process 12 cameras at once not only assists driving safely through traffic and obstacles, but builds a sufficient model of the world around it to allow for adjusting to road atmospheric condition and routing.

Roborace: Full-size robotic motorcar racing

For decades, machine and motorcar accessory manufacturers have used racing every bit both an advertising tool and a way to advance their ain research and development. Whether information technology is F1, IndyCar, or NASCAR, mill teams are e'er present and e'er using what they learn to aid them with their adjacent generation of street vehicles. Now that autonomous operation is an increasingly realistic time to come path for road cars, bringing computing front and center in car development, it makes sense racing should become a platform for AI-based vehicle R&D.

Nvidia's Drive PX 2 replaced a supercomputer in Baidu's autonomous vehicle project

That's exactly what Nvidia and others are planning for the newly announced Roborace league. Piggybacking off the fast-growing Formula East (all Electrical) schedule and car design, the league volition feature 20 identical Roborace cars allocated to x teams. They will race on the same courses as Formula E, except without drivers. The cars won't be remote-controlled, either. They'll be fully autonomous, using an Nvidia Drive PX ii portable supercomputer to run their software. So the teams' innovation and differentiation volition be in the software they develop for the race. The Roborace is scheduled to kickoff alongside the 2022-2017 Formula E season, later this year. Roborace founder Dennis Sverdlov told GTC attendees he expected it to make heroes out of software developers: "It'due south not possible to get competitive advantage based on how much money you lot put in hardware. Our heroes are not the drivers. Our heroes are engineers."

Jealous? You also can build a (small) cocky-driving car!

You can DIY your own robo racecar by following along with JetsonhacksAlong with each new autonomous vehicle proclamation, there is ever a statement of the massive investment needed to make it happen. But for those of us who desire to do more than be passive spectators, there is an exciting new opportunity to learn how to build your own — scaled-downwards — robotic race car. Startup JetsonHacks has taken MIT's RACECAR autonomous car learning platform and fabricated it accessible to the DIY customs with detailed associates instructions, and cost-saving hardware options to make it more than affordable than the University's original version. The RACECAR is a massive kit bash of an offf-the-shelf RC vehicle — a Traxxas Rally — so that all the DIY fun is concentrated on the control and programming. The brain is (naturally) a Jetson TK1, running Robot Bone (ROS).

In an exclusive interview, JetsonHacks Founder Pecker Jenson excitedly explained that this twelvemonth will characteristic an upgraded model based on this Spring's MIT Controls Course — which will be available online — and a new design featuring a more-powerful Jetson TX1. If y'all'd rather flex your maker muscle with a drone, he likewise offers a lot of great DIY drone communication based on the DJI Matrice 100 development platform.