Skip to main content

Audi’s self-driving RS 7 prototype uses GPS and cameras to ‘see’

This Sunday, Audi will make a dramatic demonstration of autonomous-car tech, unleashing a self-driving RS 7 on Germany’s Hockenheimring for one hot lap.

The robotic RS 7 is mechanically similar to the ones available in showrooms, right down to the 4.0-liter twin-turbocharged V8, eight-speed automatic transmission, and quattro all-wheel drive.

The engine churns out 560 horsepower and 516 pound-feet of torque, allowing the RS 7 to reach an estimated top speed of 189 mph. Audi expects the car to reach “only” 149 mph on its Hockenheimring lap, though.

To get all of that hardware to function automatically, Audi first needed to make sure the car could see where it was going.

Related: 2014 Audi RS 7 first drive

GPS signals will be used to orient the RS 7 on the track, while cameras will provide more precise situational awareness. Software will compare images from the cameras to a locally-stored database of familiar features to help the car figure out exactly where it is.

Audi says the lap stunt will also be a particularly tough test for the hardware that controls the steering, throttle, and brakes. It says the prototype has already logged several thousand miles on test routes to prepare it.

The RS 7 will only complete one lap at Hockenheim, but Audi says it will follow a “clean racing line,” using full throttle on the straights in pursuit of the fastest possible time. Engineers expect it to complete the lap in 2 minutes, 10 seconds, while pulling up to 1.1 g in the corners and 1.3 g under braking.

Audi’s first autonomous production cars won’t be doing that, though.

The carmaker is planning to launch an autopilot-like system in the near future that will allow cars to autonomously navigate urban traffic. That’s not as exciting as a fast lap on a racetrack, but it’s probably more useful.

Stephen Edelstein
Stephen is a freelance automotive journalist covering all things cars. He likes anything with four wheels, from classic cars…
Aptiv’s machine learning-powered radar sees even what you don’t
lyft and aptivs self driving car program has come a long way but not far enough aptiv screen press

Aptiv traveled to CES 2022 to showcase the improvements it has made to its suite of advanced driver assistance systems. It notably leveraged the power of machine learning technology to help its self-driving prototypes detect and classify objects, even those that are out of sight.

Think of a self-driving car as a human being; radars are the eyes and machine learning technology is the brain. Fitting radars to a car's body allows it to scope out the environment it operates in. It can detect that there's a car in front of it, that there's a bike coming the other way, and that there's a traffic light it needs to stop for. These are fairly straightforward tasks that most self-driving prototypes already perform.

Read more
Tesla pulls latest Full Self-Driving beta less than a day after release
The view from a Tesla vehicle.

False collision warnings and other issues have prompted Tesla to pull the latest version of its Full Self-Driving (FSD) beta less than a day after rolling it out for some vehicle owners.

Tesla decided to temporarily roll back to version 10.2 of FSD on Sunday following reports from some drivers of false collision warnings, sudden braking without any apparent reason, and the disappearance of the Autosteer option, among other issues.

Read more
Waymo’s self-driving cars can’t get enough of one dead-end street
waymo

Waymo has been testing its self-driving cars in San Francisco for the last decade. But an apparent change to the vehicles’ routing has caused many of them to make a beeline for a dead-end street in a quiet part of the city, causing residents there to wonder what on earth is going on.

At CBS news crew recently visited the site -- 15th Avenue north of Lake Street in Richmond -- to see if it could work out why so many of Waymo’s autonomous cars are showing up, turning around, and then driving right out again.

Read more