Watch Georgia Tech's Mini Self-Driving Car Shred a Drift Track
Drone technology just got radical.
![](https://imgix.bustle.com/inverse/80/c1/08/4e/d2b2/4014/9f7e/030d5163307f/screen-shot-2016-05-20-at-113511-ampng.png?w=400&h=300&fit=crop&crop=faces&q=50&dpr=2)
Computers are getting better at doing all sorts of complicated, delicate tasks without humans. The big craze right now is about self-driving cars, which could revolutionize freight shipping and personal transport. But until now, self-driving technology has been mostly confined to nifty forklifts and helping people walk even less. But no longer, as Georgia Tech just figured out how to make autonomous vehicles totally gnarly.
One of the problems with self-driving cars is they lack the capability to make the sort of fine-tuned, split-second adjustments to rapidly changing stimuli, like their tires sliding at high speeds. Naturally, a bunch of Georgia Tech computer scientists decided the best way to fix this was to program an autonomous car capable of doing powerslides.
“The exciting thing about this technology that we have is the ability for the car to perform what are known as aggressive maneuvers,” said Jim Rehg, a professor at Georgia Tech’s School of Interactive Computing. “So during turns, for example, the car is literally sliding around the turn it’s not maintaining its complete contact with the road surface. Yet in spite of that sliding maneuver, which gives us a lot of speed in the turns, the car is actually stable and safe.”
As literally every teenager who has put rubber tires on a dirt road or empty parking lot (or the neighbor’s front lawn, once, in 2006, I’m so sorry Mrs. Johannsen) can attest, drifting is really exciting, but the researchers say their programming is capable of far more stuff than just sick-ass drifts.
“The algorithms that we have developed are able to project into the future what the vehicle is going to do in the next three or four or five seconds and generate approximately two or three thousand possibilities of what is going to happen,” said Panagiotis Tsiotras, a professor at Georgia Tech’s school of aerospace engineering.
The ability to project future possibilities and analyze them could be used in almost every field of autonomous technology, but after this video, we sure hope it leads to even bigger and better drift-drones. Sure, they might be less valuable than a replacement for the Humvee or other military A.I.s, but they’ll sure as hell be savage on the mean streets.
Watch the video below.