One of Google’s more sci-fi projects that it’s working on is its automated vehicles – cars that could drive themselves without a human actively driving them. They see the road and other traffic through sensors. We first got the scoop on this project a year ago. More recently, the Google self-driving cars project was part of a keynote given by those working on the project, Sebastian Thrun and Chris Urmson, for IEEE Spectrum.
If you’re interested in learning more about the project and its progress, IEEE Spectrum had an in-depth write-up earlier this week. It discusses how far the cars have driven so far, the conditions it has faced (city traffic, highways, mountain passes, etc), and what sensors it uses to detect the outside world. It’s an interesting system because driving is so far from purely logical. We have the rules of the road but not everybody follows them and there are a lot of other things going on that requires adaptation.
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.
You can find part 1 and part 3 of the keynote on YouTube.
This is an exciting future to look forward to. The sooner we can get jerks like this off the road the better. 🙂
