Robot cars to compete in toughest ever DARPA Challenge

Alex Zaharov-Reutt
Sunday, 18 February 2007 17:07

Opinion and Analysis

The types of robots that will be commonplace in the future are being developed today, with the Stanford Racing Team’s newest robotic car, “Junior”, just one of the competitors in the 2007 DARPA Urban Challenge, where robot cars have to drive in real world conditions – without crashing!

Although commercially available robot toys are growing in number from companies like Wow Wee with their Robosapien series, and Lego's robot building kit with 2nd-generation NXT 'brain', along with Microsoft starting up a special Robotics Division, with predictions that robotic development over the next 15-20 years will mimick the technology advances seen with PCs over a similar time period, we're still some time away from the robots seen in the Jetsons, or as seen in Asimov's many robot science fiction stories. But real robots are being worked on that will be able to deal with real-world situations - like driving through traffic!

The Stanford Racing Team has announced its latest robotic car, dubbed “Junior” (and named after Stanford University founder Leland Stanford Jr.), will be competing at the November 3 DARPA Urban Challenge – which involves the ‘real world’ conditions of handling traffic.

This is a big jump over the 2005 DARPA Grand Challenge in the still Nevada desert, where Stanford’s car, called ‘Stanley’, was the winner and one of five robot cars that completed the course. This is significant because at the previous DARPA Challenge, none of the cars that entered completed the course, meaning the year 2005 was a milestone for artificial intelligence.

But when driving on streets, the need to understand the environment, instead of just observing it, becomes paramount. On city streets, there is other traffic to deal with, pedestrians, road signs, traffic lights, road markings and more. The 2007 Urban Challenge is significantly more difficult than the challenge posed in 2005 and calls for a new generation of technology.

Enter “Junior,” the Stanford Racing Team’s new brainchild. Stanford’s Sebastian Thrun, an associate professor of computer science and electrical engineering said that: “In the last Grand Challenge, it didn’t really matter whether an obstacle was a rock or a bush because either way you’d just drive around it. The current challenge is to move from just sensing the environment to understanding the environment.”

Stanford’s release tells us that’s because in the Urban Challenge, sponsored by the Defense Advanced Research Projects Agency (DARPA), the competing robots will have to accomplish missions in a simulated city environment, which includes the traffic of the other robots and traffic laws. This means that on race day, Nov. 3, the robots not only will have to avoid collisions, but also they will have to master concepts that befuddle many humans, such as right of way.

“This has a component of prediction,” says Mike Montemerlo, a senior research engineer in the Stanford Artificial Intelligence Lab (SAIL). “There are other intelligent robot drivers out in the world. They are all making decisions. Predicting what they are going to do in the future is a hard problem that is important to driving. Is it my turn at the intersection? Do I have time to get across the intersection before somebody hits me?”

Stanford tells us that racing team leaders Thrun and Montemerlo discussed Junior for the first time Feb. 17 at the annual conference of the American Association for the Advancement of Science in San Francisco. Thrun joined fellow roboticists in a panel discussion “Robots—Our Future’s Sustainable Partner” at 8 a.m. He spoke about autonomous guidance systems and machine vision. Afterwards, he and Montemerlo participated in a press conference at noon.

The racing team, based in the School of Engineering, is supported by returning industry team members Intel, MDV-Mohr Davidow Ventures, Red Bull and Volkswagen of America and joined this year by new supporters Applanix, Google and NXP Semiconductors. DARPA also has provided $1 million of funding.

So, what’s inside of Junior that makes him so special? Well, for a start, he’s using the latest Intel Core Duo and Quad Core processors and has four times the computing power of ‘Stanley’, the 2005 winning model. But there's plenty more - read onto the next page to find out!