700,000 miles and counting for Google self-driving cars (Video)
Posted by: Jon Ben-Mayor on 04/28/2014 11:53 AM [ Comments ]
Google has announced that their vehicles have hit a autonomous milestone; 700,000 miles driven with little human intervention. The next step, Google says, is conquering inner-city driving, with all the pitfalls that go hand in hand with navigating a major city; pedestrians, traffic lights and those untrustworthy human driven vehicles that are double parked, appear to be no match for the ever computing cars.
In a blog post from today, Google explains that 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.
Here’s a video showing how our vehicle navigates some common scenarios near the Googleplex:
As it turns out, what looks chaotic and random on a city street to the human eye is actually fairly predictable to a computer. 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.
Here’s a video showing how our vehicle navigates some common scenarios near the Googleplex:
As it turns out, what looks chaotic and random on a city street to the human eye is actually fairly predictable to a computer. 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.
Comments