Ever since they were outed, I’ve been fascinated by Google’s self-driving cars. They are a combination of awesome potential and scary future vision.
Here’s some interesting information on how they actually work, very cool as expected.
How Google’s Self-Driving Car Works – IEEE Spectrum
As with any algorithm, there are some interesting tweaks:
Sometimes, however, the car has to be more “aggressive.” When going through a four-way intersection, for example, it yields to other vehicles based on road rules; but if other cars don’t reciprocate, it advances a bit to show to the other drivers its intention. Without programming that kind of behavior, Urmson said, it would be impossible for the robot car to drive in the real world.
I also wonder what’s in this for Google. Sure, you could say it’s not being evil, but down the road (pun), Google could diversify its business and license this technology. They must have some vision, given the immense uphill battle they face with liability and legal issues. Not to mention general acceptance of machine-operated cars.
Find the comments.
One comment