Google Borg Assimilates Robot Car

One of the big reasons why Stanford's geeks won Darpa's robotic rally across the Mojave was because their car could see better than others. Now Google is hoping the same tech can help it see (and search) the planet.

Combining laser range finders with video data, "Stanley" -- a driverless Volkswagon Touareg R5 -- was able to build 3-D models of the scene in front of it. And that view helped let it finish the 131-mile Grand Challenge course first. (So did a series of learning algorithms, that let the car better interpret what it saw.)
Google has licensed Stanley's vision software, the Merc-News reports, "to map out photo-realistic 3-D versions of cities around the world, and possibly regain ground it has lost to Microsoft's 3-D
mapping application known as Virtual Earth."

*Technologists believe an emerging 3-D Internet will eventually be commonplace as increasing numbers of people work, play and shop in virtual environments.

Microsoft's Virtual Earth, available through the 3-D link on
maps.live.com, gives a hint of what that future will look like. Thanks to a unique approach to aerial photography, clever algorithms and the application of massive computational power, Microsoft has been able to create exact replicas of more than 50 cities, including San Francisco and San Jose.

Google Earth had 3-D cities, too. But until now, the buildings have been modeled by people, not computers, giving Microsoft's computer-generated cities a decided edge in completeness.

(High five: WPN)