When the idea of self-driving cars was first proposed, many critics wondered whether a computer would be able to make the kind of split second decisions that human drivers do. Putting these concerns to rest, Google has announced that their driverless vehicles are now able to recognize and cope with typical occurrences that take place on roads, such as jaywalking pedestrians, double-parked vehicles, and even cyclists.
The roads in an urban environment are notoriously congested and fully of daily hazards. But Google is confident that their self-driving cars are now up to the challenge. In their latest blog post, the search giant says: “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 added that what appears to be chaotic human activity is actually quite easy to predict for computers. As such, Google’s software model is programmed to predict everything from the likely (a car stopping at a red light) to the unlikely (blowing through it).
The company has come a long way in the last two years since the project launched. Now, with over 700,000 autonomous miles logged, Google claims they are one step closer to a vehicle that operates fully without human intervention. Whether that is a good thing or a bad thing, we will let you decide.