Race car drivers are learning from connected car data and now self-driving cars are learning from race car drivers. Standford University researchers are using data from race drivers to enable a supped-up autonomous Audi TTS named Shelley to drive faster than a human race car driver at Thunderhill race track in Willows(near Chico), California.
Stanford University professor Chris Gerdes studies how professional racing drivers make their way around the track at speeds upwards of 150 miles per hour. He then inputs that data into Shelley’s computer
Race cars winners are decided by time and the Stanford Audi TTS times were fantastic. In fact, the time was faster than the track owner David Vodden’s top time by .4 seconds. Vodden is amateur touring class champion.
Gerdes uses cameras to record how race drivers handle turns and straightaways and how they use the steering wheel, the pedals and sift gears. Electrodes are attached to drivers heads to track their vital signs and brain activity.
“Drivers try to use all the friction capability of the tire and the road to be fast,” Gerdes told CBS News. “What we really want to do is have that same capability to use all friction between the tire and road to be safe.”
Shelley is designed to know when to brake and to trade off between braking and steering, on a turn by turn basis. Thunderhill has a series of 15 different area, some high speed, some sharp after long straight, some chicanes and one uphill with no ability to see on the other side. The idea behind the race style driving is that if self-driving cars can go up to the limits, it can help ordinary drivers.
Gerdes in his TED talk noted that combined with new research on professional drivers’ brain activity, the car’s performance could get even better.