Google introduces city driving software for driverless cars

29 April 2014
By Tereza Pultarova
Mobile version
Share |
Google says that unlike human drivers, the machine's attention never wavers

Google says that unlike human drivers, the machine's attention never wavers [Credit: Google]

Google has been testing software capable of safely navigating cars in cities without the driver’s intervention.

The software is part of Google’s self-driving vehicle project developed by the company’s experimental branch the X-Lab, which has previously won attention by developing the Google Glass or testing a helium-balloon based WiFi network for remote areas.

Chris Urmson, director of the self-driving car project at Google, described testing of the software in the company’s hometown in Mountain View in a post on Google’s official blog.

"Since our last update, we've logged thousands of miles on the streets of our hometown of Mountain View. 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,” he wrote.

"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.”

Unlike human drivers, Urmson explained, the machine’s focus and concentration never wavers, the system never gets distracted or tired and is capable of paying consistent attention to every detail of the changing traffic situation.

"Our vehicles have now logged nearly 700,000 autonomous miles, and with every passing mile we're growing more optimistic that we're heading toward an achievable goal - a vehicle that operates fully without human intervention", said Chris Urmson, who claimed that the company's computers are already able to comfortably predict what happens on city streets.

During the testing, the Google researchers have collected data about a vast amount of different traffic situations, showing various outcomes of different circumstances.

“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),” Urmson wrote.

Google launched the self-driving car project four years ago as a response to the World Health Organisation figures which reported that more than one million people are killed in road traffic accidents each year.

So far, autonomous Google cars are only capable of driving on certain streets in Mountain View but the team is expanding their reach and plans to move to another city in the future.

Here’s a video showing how our vehicle navigates some common scenarios near the Googleplex:


Latest Issue

E&T cover image 1604

"Should the UK's engineers be in or out of Europe? The IET sets out its official position on the EU referendum this week - will you agree?"


E&T jobs

More jobs ▶


Choose the way you would like to access the latest news and developments in your field.

Subscribe to E&T