A new video from Google shows how its self-driving cars are learning to cope with all the problems of city driving - intersections, pedestrians, cyclists, blockages caused by road repair works or large vehicles. Is Google near to its goal of a fully autonomous vehicle?
Google Self-Driving Car Project has already clocked-up around 700,000 miles but most of these have been in the context of freeway driving, which is relatively problem-fee when compared to city driving.
The number of hazards per mile increases dramatically once you add jaywalking pedestrians, double parked delivery trucks and cyclists who give hand signals to indicate they intend to make a turn and then decide not to. And these hazards don't come singly - it's a case of taking all of them into account. Luckily this is something that computers are better prepared for than humans - and they don't suffer from road rage.
In this video Priscilla, one of the team of test drivers who gather information on traffic scenarios that is then fed into the software used by Google's self-driving cars, is behind the wheel, although not controlling the car, as it navigates itself around Mountain View, California, the area close to Google's HQ. In the bottom left of the screen you see the view of the road ahead while the rest of the screen shows how the car is moving through the traffic and coping with the situations encountered.
Autonomous cars are also now legal in California, Florida and Michigan, although all states still require a human driver behind the wheel. So how soon can we expect them to move to "community preview testing"?
Google is taking things slowly. On the Google Official Blog, Chris Urmson, Director, Self-Driving Car Project, writes:
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.
As professional programmers we are obviously interested in which languages are in demand and how they compare in terms of how much they pay. This information can be found from an analysis of job adv [ ... ]