Google just gave the world an update on its self-driving cars. The company says it has been focused on making them more city-ready.
Google has improved the cars' software, it says, so it can now detect hundreds of distinct objects at the same time, including pedestrians, buses, a stop sign being held by a crossing guard, or a cyclist making turn signal gestures.
"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," says Chris Urmson, director of Google's self-driving car project.
What could possibly go wrong?
"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 says. "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). We still have lots of problems to solve, including teaching the car to drive more streets in Mountain View before we tackle another town, but thousands of situations on city streets that would have stumped us two years ago can now be navigated autonomously."
Let's just hope that this is the first software in history that's completely flawless.
So far so good. Google says its vehicles have logged about 700,000 miles.
About half of Americans are sold on the idea of the self-driving car. According to a recent Pew Research Internet Project study, 50% said they wouldn't ride in one 48% said they would. Presumably the other 2% were unsure.
Image via Google