Watch a Self-Driving DeLorean Burn Rubber on a Stunt Course
"Back to the Future" meets "Tokyo Drift."
Great Scott! Engineers at Stanford’s Dynamic Design Lab have taught a self-driving DeLorean — the iconic early 80s sports car of “Back to the Future” fame — how to drift around a complex, kilometer-long track that even human drivers would struggle with.
The vehicle, lovingly dubbed MARTY after the protagonist of “Back to the Future,” completed a full circuit without any hiccups on its very first try.
The onboard computer system learns, from dozens of runs, how the dynamics of the vehicle respond to the road conditions and twists and turns.
The same kind of technology could one day make the difference between a pedestrian getting hit or not getting hit by a driverless car, according to the team.
“We’re trying to develop automated vehicles that can handle emergency maneuvers or slippery surfaces like ice or snow,” lead engineer Chris Gerdes said in a statement. “We’d like to develop automated vehicles that can use all of the friction between the tire and the road to get the car out of harm’s way. We want the car to be able to avoid any accident that’s avoidable within the laws of physics.”
Very little of the original DeLorean made it into the final drifting machine. Two powerful electric motors on each rear wheel supply power now, and a custom suspension system provides high-performance drifting capabilities. Steering, braking, and throttling are all handled by electronic systems.
In fact, the vehicle’s creators say, it can change direction even faster than any human using mechanical steering controls could pull off, unlocking the full potential of the machine.
“The results so far are rather outstanding,” Gerdes added. “The stability control systems of modern cars limit the driver’s control to a very narrow range of the car’s potential.”
Drifting is an excellent exercise for teaching a car what to do to evade an object or person in the road.
“Through drifting, we’re able to get to extreme examples of driving physics that we wouldn’t otherwise,” Stanford graduate Jon Goh, who was involved in the project, said. “If we can conquer how to safely control the car in the most stable and the most unstable scenarios, it becomes easier to connect all the dots in between.”
More on driverless cars: Watch a Self-Driving Car Careen Around Corners Like a Racecar