Ever wondered how Google's self-driving cars see the world? Here's all you need to know

The latest re-organisation at Google brings a lot of changes and changes the way we’ve been looking at Google’s miscellaneous projects, not blurred by Android or search it shows how important all of them are for the company. One such, **Google X** , that includes the self-driving cars will also become a subsidiary of Alphabet, and is no longer a part of Google. Self-driving cars has been Google’s pet project for quite some time now, and now under Alphabet, the company is known to have started work on designs of the cars. Over the past year, the company has been **testing several driverless cars** and we’ve also seen prototypes and some early experiences from users taking a ride.  However, ever thought how the driverless car knows it has to take a turn or there is a cyclist on the right or the traffic light has turned red. Self-driving car project head Chris Urmson was at a Ted Talk and explained exactly how the car works and the improvements, so far. Let’s get into the head of the car. Firstly, the car tries to figure out exactly where it is in the world using the map and its sensor data. Now, depending on what it sees, Google adds a layer of how it sees the world. In the image below, the purple boxes are other vehicles on the road. You can see the cyclist in red and come cones. Besides, knowing its surroundings, the car also predicts what’s going to happen next.  Well, what you saw is how the car is thinking about one vehicle, but this process gets really complex as in real life there are many vehicles as well as pedestrians, cyclists, trucks and so on , on the road. The car has to predict what every object plans to do. Moreover, after predicting, the car then decides on how to respond, what trajectory it should follow, whether to go slow or fast, and so on.  On city streets are all new problems and a lot of certainty. There will be pedestrians crossing the road, traffic lights, crosswalks and so on. The vehicle is also taught to deal with construction. There are cones that will force the car to move according, keeping in mind where exactly the construction takes place. Moreover, it will also show people crossing or walking in the construction zone. What if a police van stops the car? yes, the car has been taught that flashing light on the top of the car means that it’s not just a car, it’s actually a police officer. Besides, the car is also taught to differentiate other vehicles from a school bus, which will appear as an orange box and know that it should be treated differently.  All this looks and sounds simple, but driving also involves some human behaviour. So, if a cyclist puts up his arm asking the car to yield and make room for him/her, the vehicle will then slow down and let it change lane or so on. Similarly, it will know when asked to stop by a police officer and continue as soon as the officer signals to leave. Now, this is everything one can possibly expect, but there are several other things that could be new. “So just a couple of months ago, our vehicles were driving through Mountain View, and this is what we encountered. This is a woman in an electric wheelchair chasing a duck in circles on the road. (Laughter) Now it turns out, there is nowhere in the DMV handbook that tells you how to deal with that, but our vehicles were able to encounter that, slow down, and drive safely,” Urmson said. Similarly, it also slows down on seeing a bird fly.  This is advanced tech and there is always doubt if it will pave its way to the market, but Urmson is now confident about the technology making it to the market. But, how soon? “it’s hard to say because it’s a really complicated problem, but these are my two boys. My oldest son is 11, and that means in four and a half years, he’s going to be able to get his driver’s license. My team and I are committed to making sure that doesn’t happen,” he chirped. Urmson also explains how incredibly useful the car would be in many ways. For instance, he cites example of Steve, who is visually impaired and spends hours in public transit and asking friends and family to take him to his workplace, but a self driving car will put an end to all the hassle cutting down the time to mere 30 minutes. On the other hand, another driver, who owns a Porsche also found the car very convenient.  Talking about safety, the report adds that human drivers can make mistakes leading to traffic accidents that is once in every 100,000 miles in America. On the other hand, a self-driving system makes decisions about 10 times per second, in the order of magnitude, that’s about 1,000 times per mile, he claimed. Since the Ted Talk, there have reports about an  accident involving Google's self-driving car that left four injured. The three Google employees on board complained of minor whiplash, were checked out at a hospital and cleared to go back to work following the July 1 collision, Google had said last month. This certainly raises questions like is the car ready to take on roads, yet. In case of an accident of a driverless car, who is liable in case of accidents or injury? While the new innovation is a great step ahead in the world of tech advancements, driverless cars still leave many questions unanswered.