On Sunday, Oct. 10, Google (GOOG) dropped the stunning news that it had developed a fleet of Toyota Priuses that can drive themselves -- and had already logged 140,000 miles of road time around the San Francisco Bay area. The announcement shows that big-picture research work is still alive and well at Google, despite the increased competition in advertising markets and the slowing growth in revenues for the search engine giant. The fact that Google is still willing to bet on this type of tech is heartening.
From the blog post by Sebastian Thrun, a distinguished Google engineer:
"...we have developed technology for cars that can drive themselves. Our automated cars, manned by trained operators, just drove from our Mountain View campus to our Santa Monica office and on to Hollywood Boulevard. They've driven down Lombard Street, crossed the Golden Gate bridge, navigated the Pacific Coast Highway, and even made it all the way around Lake Tahoe. All in all, our self-driving cars have logged over 140,000 miles. We think this is a first in robotics research."
This is amazingly cool. According to the post, the automated cars use video cameras, radar sensors and a laser range finder to "see" other traffic. The cars rely on detailed maps, collected by other Google vehicles as part of its mapping efforts, to drive on roads and know what's coming while not crashing or making a wrong turn. Naturally, Google's data centers and a stream of real-time information coming from wireless data allows the cars to more effectively navigate their surroundings.
How KITT Got Built
To build out this self-driving car tech, Google tapped engineers from various participating teams in the DARPA Challenges. These are a series of vehicle races organized by the legendary Defense Advanced Research Projects Agency (you know, the agency that actually did underwrite the discovery of the Internet). The races awarded prizes to teams that could make autonomically operated vehicles that navigated urban, desert and other race courses.
"Chris Urmson was the technical team leader of the CMU team that won the 2007 Urban Challenge. Mike Montemerlo was the software lead for the Stanford team that won the 2005 Grand Challenge. Also on the team is Anthony Levandowski, who built the world's first autonomous motorcycle that participated in a DARPA Grand Challenge, and who also built a modified Prius that delivered pizza without a person inside," writes Thrun.
To be sure, the cars always had a human behind the steering wheel to make sure that nothing untoward happened -- and to quickly take control if the automated guidance system malfunctioned. Local police were briefed and sworn to secrecy, one would assume. Google also prepped the system for an upcoming route by sending out a driver in a normal Google mapping car to record more details of the route, road conditions, and detailed locations of lane markers and traffic signs, among other things.
The ultimate goal of Google is to eliminate human errors from the roads, something Google CEO Eric Schmidt has spoken of on several occasions. The post also mentions how this type of tech could be used to create automotive "highway trains" where cars travel more efficiently and take advantage of aerodynamic factors such as drafting without endangering drivers and passengers. For me, I'd love to be able to safely make and take phone calls on the road without having to look at a smart phone screen or rely on still balky voice activation software that most phones still run.
Says Thrun: "We've always been optimistic about technology's ability to advance society, which is why we have pushed so hard to improve the capabilities of self-driving cars beyond where they are today. While this project is very much in the experimental stage, it provides a glimpse of what transportation might look like in the future thanks to advanced computer science. And that future is very exciting." Right on.