Self-Driving Car Outdrives Professional Race Driver For The First Time [VIDEO]
Engineers at Stanford University just proved you don’t need a race car driver to take turns like a pro — or a human being.
The Telegraph reports that “Shelley” — a souped-up Audi TTS equipped with the latest in driverless technology — has successfully beaten amateur touring class champion David Vodden by 0.4 of a second around his own racetrack in Thunderhill Raceway Park in Northern California.
With the safety switched off, Shelley can reach speeds up to 120 mph around Thunderhill, taking the course’s 15 unique turns with skill on par with professional drivers and making it all the way around the 3-mile course in less than two and a half minutes, according to Stanford.
In Shelley’s latest upgrade, the car stole from drivers themselves — specifically their brainwaves — in order to beat them at their own game.
“We’ve been trying to develop cars that perform like the very best human drivers,” Professor Chris Gerdes, director of the Revs Program at the Centre for Automotive Research at Stanford University, said in The Telegraph. “Race car drivers are really fantastic using all the friction between the tire and the road to get around the track.”
According to Revs, the same physics and reactions are at play when normal drivers encounter icy roads and fight to stay in their lanes, meaning Shelly’s racing principles can be applied to make safer self-driving cars in the future.
“If we can figure out how to get Shelley out of trouble on a race track, we can get out of trouble on ice,” Gerdes said of the project in 2012.
The engineers at Stanford gleaned the data necessary to upgrade Shelley by attaching electrodes to the heads of drivers and monitoring their bran activity while they race. They were surprised to discover that during the most complex maneuvers, drivers responded with less brain activity and more instinct and muscle memory.
“If you’re thinking you’re going too slow,” Vodden said.
To mimic the experience and instinct of human drivers in high-speed sliding situations, engineers developed a stabilizing algorithm for Shelley, which triggers “a set automatic command” when the car starts to lose traction and slide.
“In the future it could mean we can make driverless cars which drive as well as the best racing drivers,” Joe Funke, a PhD student at the Revs Programme, said in the report. “You could have a car with the skill of Michael Schumacher taking your kids to school or the dentist. “ (VIDEO: Watch This Audi Become The World’s Fastest Self-Driving Car)
Follow Giuseppe on Twitter and Facebook