Google’s fleet of self-driving cars have already logged 700,000 autonomous miles, and they’ve become a whole lot smarter along the way.
Google is testing its self-driving cars on the streets of its headquarters’ hometown of Mountain View, Calif. As seen in the video above, the cars can make driving decisions based on what’s happening around them in real time, such as slowing down for jaywalking pedestrians and cars that sneak out of hidden driveways.
“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,” wrote Chris Urmson, director of the self-driving car project. “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.
Although driving is a complex task to master, Urmson said it is much easier for a computer to process everything that is happening on the road at such a rapid pace than the human mind.
“As it turns out, what looks chaotic and random on a city street to the human eye is actually fairly predictable to a computer,” Urmson said. “As we’ve encountered thousands of different situations, we’ve built software models of what to expect, from the likely (a car stopping at a red light) to the unlikely (blowing through it).”
While Google is still working to overcome some challenges, such as teaching the self-driving vehicles to navigate more streets in Mountain View before they head to other towns, it’s come a long way in just a few years.
“Thousands of situations on city streets that would have stumped us two years ago can now be navigated autonomously,” Urmson said.