Since our last update, we’ve logged thousands of miles on the streets of our hometown of Mountain View, Calif. A mile of city driving is much more complex than a mile of freeway driving, with hundreds of different objects moving according to different rules of the road in a small area. We’ve improved our software so it can detect hundreds of distinct objects simultaneously—pedestrians, buses, a stop sign held up by a crossing guard, or a cyclist making gestures that indicate a possible turn. A self-driving vehicle can pay attention to all of these things in a way that a human physically can’t—and it never gets tired or distracted.
Google says that what looks chaotic and random on a city street is actually fairly predictable to a computer. They've built software models for thousands of different situations; however, there are still many more to solve.
Check out a video below that shows the Google self-driving car navigating some common scenarios on city streets near the Googleplex.