Regardless of how you feel about self-driving cars, it seems reasonable to think they are safer on the highway (as opposed to the busy city streets). Well, take that potentially terrifying thought about city street driving and begin to think of it as reality. Google has given an update on the self-driving car project and it includes just that — city street driving.

This actually isn’t something just happening today. Google mentioned how “over the last year” they shifted the project and began to focus on the busy city streets. They admit how “a mile of city driving is much more complex than a mile of freeway driving.” Just to name a few — some of the potential distractions include jaywalking pedestrians, cars coming out of a driveway and double-parked vehicles.

The interesting part here is how Google feels a “self-driving vehicle can pay attention to all of these things in a way that a human physically can’t.” To further that, there was the reminder about how the self-driving vehicle also never gets tired or distracted.

“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).”

While an overall positive sounding status update, there was another side here. Google made it clear they aren’t navigating on city streets everywhere. So far the testing has been “near the Googleplex” and it seems like it will remain so for a bit more time. Google mentioned they have “lots of problems to solve, including teaching the car to drive more streets in Mountain View before we tackle another town.”

The cars have now logged roughly 700,000 autonomous miles and Google is at a point where they believe a self-driving car is an “achievable goal.”

SOURCE: Official Google Blog

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.