Google's Self-Driving Cars Tackle Urban Traffic Hazards
Written by Sue Gee   
Tuesday, 29 April 2014

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. 

 

 

Related Articles

Google Self-Driving Car For Daily Commute

Sebastian Thrun on Google's driverless car

Driverless Cars - More Than Just Google

Driverless Cars Become Legal - The Implications

Robot cars - provably uncrashable?

 

To be informed about new articles on I Programmer, install the I Programmer Toolbar, subscribe to the RSS feed, follow us on, Twitter, Facebook, Google+ or Linkedin,  or sign up for our weekly newsletter.

Banner


Apollo Adds REST APIs For GraphQL
29/10/2024

Apollo has added a simpler way to integrate REST APIs into a federated GraphQL environment. Available now in public preview, can be used to map REST API endpoints to their GraphQL schema using a decla [ ... ]



IBM Updates Granite Models
28/10/2024

IBM has released new Granite models that it says provide state-of-the-art performance relative to model size. The Granite 3.0 collection includes a new, instruction-tuned, dense decoder-only LLM.


More News

 

espbook

 

Comments




or email your comment to: comments@i-programmer.info

Last Updated ( Tuesday, 29 April 2014 )