How Stanford's Stanley won the Desert Grand Challenge

October 19, 2005 | Matt Marshall

Stanford Car.jpg Here’s the follow-up look into what made Stanford’s car the victor earlier this month at the DARPA Grand Challenge 132-mile driverless race across the desert.

It is by Mercury News colleague Mike Langberg, and explains how smart focus was behind it all. Here’s a snippet:

When the Stanford team first started testing Stanley, a blue sport-utility vehicle, he had a 12 percent blunder rate for “false positives” — incorrectly assuming 12 percent of the objects in front of him were obstacles big enough he had to swerve around them.

So the team instructed Stanley’s software to take notes while a human driver maneuvered the car over different types of terrain. By following this guidance, the false positive rate dropped to one in 50,000 objects.

Next Story: Silicon Valley VCs face tricky Chinese puzzle
Previous Story: Draper Fisher Jurvetson's empire grows

Twitter

Facebook

Google Buzz

Digg

StumbleUpon

Delicious

Google

More...

About the Author, Matt Marshall

Matt launched VentureBeat in September of 2006, with the realization that no one else was covering the entrepreneurial and tech innovation scene with the velocity or depth that he was. Prior to founding VentureBeat, he covered venture capital for the San Jose Mercury News from 2001 to 2006. In 2002, Matt was awarded "Journalist of the Year" by the Northern California Society of Professional Journalists. Prior to working at the Merc, he was a correspondent for the Wall Street Journal in Bonn, Germany from 1995 to 1998, and a writer for the Washington Post in 1994. Matt holds a PhD in Government and an MA in German and European Studies from Georgetown University. In addition to VentureBeat, Matt is also the Executive Producer of DEMO, the leading launchpad event for emerging technologies.