Stanford unveils entry for DARPA Urban Challenge

The eggheads at Stanford University are ready to rock and roll and this year’s DARPA Urban Challege — two years after their artificial intelligence robot vehicle won the 2005 Grand Challenge in the Nevada Desert. Yet while some of the lessons learned in 2005 will be valuable, the Urban Challenge — which requires the robot vehicle to navigate city streets unaided — presents unqiue challenges. “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,” said professor Sebastian Thrun. “The current challenge is to move from just sensing the environment to understanding the environment,” including giving pedestrians the right of way.

Known as Junior, the Stanford vehicle is a 2006 Volkswagen Passat whose steering, throttle, and brakes all have been modified to be completely computer-controllable, and which has been custom fitted to hold a suite of sophisticated sensors. These include a range-finding laser array that spins to provide a 360-degree, three-dimensional view of the surrounding environment in near real-time; bumper-mounted lasers; radar; GPS receivers, and inertial navigation hardware to collect data about where it is and what is around. Controlling the sensor apparati are Core 2 Duo processors and specialized software to convert raw sensor data into a cohesive understanding of its situation. “This has a component of prediction,” said researcher Mike Montemerlo. “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?”

-read more in this university news release