Google self-driving cars: getting city smart

Google engineers and programmers have been working for over a year at improving how the Google self-driving cars handle city traffic.

Chris Urmson, the head of Google's self-driving-car project, said Monday 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.’

According to Urmson, the car’s software is now able to recognize pedestrian traffic, buses, stop signs held by traffic guides and even hand signals made by cyclists.

Moreover, the software can even handle such situations better than human drivers do: ‘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,’ Urmson stated, adding that ‘as it turns out, what looks chaotic and random on a city street to the human eye is actually fairly predictable to a computer.’

Self-driving vehicles became street-legal in Nevada in 2011 but are now also legal in California, Florida, Michigan even though all states require a human driver behind the wheel.

Since 2011, the only accidents the self-driving vehicles were implicated in happened when a human was driving them or when it was the other driver’s fault.

The technology that allows these cars to practically drive themselves includes a laser radar system, and a laser-based range finder which allows software create 3D maps of the surroundings.