Nvidia’s new simulator brings virtual learning to autonomous vehicle developers

Nvidia’s Drive Constellation autonomous vehicle simulation system is ready for manufacturers to use to rack up millions of virtual miles testing and proving their technologies.

Nvidia announced the availability of its data center simulator for testing self-driving automotive technologies at the company’s annual GPU Technology Conference in San Jose, California. Designed to speed up autonomous driving development, Drive Constellation is an open, cloud-based platform technology vendors can use to validate systems efficiently, safely, and much faster than with vehicles on real roads.

Drive Constellation is an answer to the conundrum that has plagued autonomous vehicle technology: How can you test vehicles in real-world driving situations to prove they’re safe before they’ve been validated and certified as safe?

Self-driving car technology companies have logged millions of miles on public roads under restricted conditions. However, the public, automotive manufacturers, and government regulatory agencies are all leery of the dangers of testing unfinished, unproven technology where people can be injured or killed. Higher order statistics consistently show human error is responsible for more than 90 percent of fatal accidents, but allowing un-piloted or partially piloted vehicles on public roadways for testing is still fraught with its own difficulties.

Public road testing is also limited and slow, compared to the possibilities of simulated testing. For example, if you wanted to know how a car’s autonomous system would work if a mattress flew off the back of a pickup truck the car was behind on the highway traveling 70 miles per hour, setting up a real-world test is out of the question. The same test on a simulator would be relatively easy, and no lives or property would be at risk.

Nvidia introduced Drive Constellation at the GPU Tech conference last year as the solution to the difficult problem of testing autonomous vehicle technologies.

The Nvidia platform uses two servers that work together: Drive Constellation Simulator and Drive Constellation Vehicle. The Simulator server utilizes Nvidia graphics processing units (GPUs) and Drive Sim software to generate output from a virtual car driving on virtual roads. The Vehicle server processes the data from the Simulator using Nvidia’s DRIVE AGX Pegasus A.I. car computer. When the Vehicle makes driving decisions during simulation, the decision data is fed back to the Simulator immediately for continuous processing.

The Drive Constellation platform is ready for manufacturers who want to work with Nvidia to validate autonomous vehicle technologies.

Nvidia announced Toyota Research Institute-Advanced Development (TRI-AD) is the first Drive Constellation customer. “We believe large-scale simulation tools for software validation and testing are critical for automated driving systems,” said TRI-AD CEO James Kuffner.


Qiantu K50 electric sports car was designed in China, will be built in the U.S.

The Qiantu K50 is a Chinese electric sports car that will be marketed in the United States by California-based Mullen Technologies. The carbon-fiber bodied, 402-horsepower K50 is expected to go on sale in 2020.

Stop backing into your neighbor's car with the best backup cameras

The right backup camera will allow you to better avoid vehicles and other obstacles without taking your eyes off the road, rendering "sorry, I hit your car!" notes a thing of the past. Here are our current favorites.

Apple’s interest in self-driving cars reported to be revving up

A new report suggests that Apple is in talks with a number of suppliers to purchase lidar sensors, an essential tool for self-driving cars. The news is once again spiking rumors that Apple might be building vehicles.

The VR goggles you wear to shoot alien ships is helping Magna design car parts

Canadian automotive supplier Magna has started using virtual reality in its research and development department. The technology helps engineers get a better view of what they're working on, whether it's an interior part or a powertrain.

Tesla Model S and Model X charge faster and go farther with the same battery

An all-new drivetrain for the Tesla Model S and X enables the EVs to travel farther per charge than the previous design. Tesla Model S Long Range sedans have a 370-mile range and Model X Long Range SUVs can travel 325 miles per EPA cycle.

2019 Ford F-150 RTR gets a light dose of off-road, style upgrades

Vaughn Gittin Jr.'s RTR Vehicles is turning its attention to the 2019 Ford F-150 pickup truck. RTR gave Ford's bestseller new suspension components and tires, as well as more extroverted exterior styling.

Electric truck maker Rivian scores $500 million investment from Ford

Alongside Amazon, Rivian can now count Ford as one of its backers. The Blue Oval will invest $500 million in Rivian, and will use the company's "skateboard" chassis as the basis for a future electric vehicle.

The best diagnostic adapters monitor your car so you don't have to

Sometimes called dongles, the best car adapters will tell you what's wrong under the hood while help you keep tabs on your family and routine maintenance.
Emerging Tech

Japanese taxis will use facial recognition to target you with ads as you ride

A Japanese startup is trying to reinvent in-taxi advertising by using facial recognition technology to identify the key characteristics of riders and then presenting them with appropriate ads.

Nvidia agrees with Tesla’s take on self-driving cars, but corrects specifics

Nvidia vice president Rob Csongor agreed with broad statements by Elon Musk at Tesla's April 22 Autonomy Investor Day. Csongor then took exception to what he termed were inaccuracies about Nvidia's self-driving car chip.

Waze vs. Google Maps: Which map app should you be using?

Waze and Google Maps are two of the most popular apps for those looking for turn-by-turn navigation, yet there are some notable differences to point out. Here, we examine both to decide which offers the best feature set.

Tesla posts $702M Q1 loss as deliveries fall sharply; Musk promises turnaround

Tesla lost $702 million during the first quarter of 2019 as deliveries fell sharply, and demand for the Model X and the Model S flattened. The company predicts it will again lose money in the second quarter.

Ambitious but not rubbish: The best Top Gear episodes

Since its relaunch in 2002, Top Gear has become required viewing for any serious gearhead. The great moments from this show may seem too numerous to count, but we've managed to pick some of the highlights from the first 26 seasons.

Volkswagen prepares its electric ID R race car for its toughest challenge yet

The Volkswagen ID R electric race car will head to the Nürburgring to set a lap record. With Romain Dumas at the wheel, the ID R will try to become the fastest electric car around the grueling, 12.9-mile long track.