The real challenge was to get the intelligence right, and the intelligence was in the software.
Using machine learning, we reduced Stanley's error rate from about 12 percent in the beginning to about 1 in 50,000 by race time. We gave Stanley a framework to approach the problems he had to tackle.
The project is just beginning. We feel that, ultimately, you'll be able to go to the dealer and buy a car that drives itself.
It's all about the big picture. Using machine learning, Stanley was able to look at the big picture more effectively than a human could have.