Dan Lee, associate professor at the University of Pennsylvania, is team leader of the Ben Franklin Racing Team.
“Little Ben,” a self-navigating, self-driving car designed by engineers from Lehigh, the University of Pennsylvania and Lockheed Martin’s Advanced Technology Laboratories, has advanced to the finals of the 2007 DARPA Urban Challenge
and a chance at a $2 million prize.
The souped-up Toyota Prius was one of 11 cars from a field of 36 that were chosen to compete Saturday, Nov. 3, in the final event of the Challenge at the former George Air Force Base in Victorville, Calif. The event will be webcast live on the Grand Challenge Web site
beginning at 10:30 a.m. Eastern Daylight Savings Time.
In the final event, cars must safely navigate a 60-mile urban course in less than six hours, while obeying traffic laws, merging into moving traffic, negotiating intersections, and avoiding moving and stationary obstacles—all this with no human guidance.
Winners will be chosen on the basis of speed as well as ability to comply with California driving laws. Cash prizes of $2 million, $1 million and $500,000 will be awarded to the top three teams.
In addition to Little Ben, cars designed by teams from Carnegie-Mellon, Cornell, and Stanford universities, the University of Central Florida, MIT, the German Research Foundation, the Braunschweig University of Technology in Germany and the Virginia Institute of Technology, qualified for Saturday’s finals.
DARPA, the Defense Advanced Research Projects Agency
, is the research arm of the Pentagon. The goal of the Urban Challenge—this year’s is the third—is to promote the development of sophisticated, driverless, ground-combat vehicles for the U.S. military and thus meet a congressional mandate that one-third of such vehicles be unmanned by 2015.
DARPA had originally planned to qualify 20 vehicles for the final event of the Urban Challenge, but chose only 11 after determining that the remaining cars were not safe enough on the road.
“During the qualifying events,” said an article linked to the Urban Challenge website
, “one autobot after another drove into trouble—some crashed, some made dangerous turns, and some flew off the course entirely.”
Little Ben is the product of the Ben Franklin Racing Team
, a consortium comprising Penn, Lehigh and Lockheed Martin’s Advanced Technology Laboratories. Penn is the lead partner on the team, and Dan Lee, associate professor of electrical and systems engineering at Penn, is team leader.
, assistant professor of computer science and engineering and lead Lehigh member of the team, said the team was not planning to savor its success in the national qualifying round.
“We’re still doing development,” Spletzer said Thursday (Nov. 1) after Little Ben qualified for the finals. “Everyone is working hard. There’s a lot to do. Right now, we’re taking overhead imagery from Google Earth and trying to [align] it with the imagery supplied by DARPA.”
At the national qualifying event Oct. 31 and Nov. 1, Little Ben was required to complete six road tests averaging 25 to 35 minutes in length.
“We had a good run,” said Spletzer, who directs Lehigh’s VADER
(Vision, Assistive Devices and Experimental Robotics) Laboratory. “But there are a lot of very good teams here.”
Working day and night
The Ben Franklin Team has been working day and night the past few weeks to refine Little Ben’s computer vision, laser range-finder and GPS systems. Much of the time was spent testing on the parking lot behind Stabler Arena.
“We’ve worked more [consecutive] days than I can count,” said Spletzer.
A total of 89 teams entered this year’s Challenge and three dozen passed site visits last summer to advance to this week’s qualifying round. DARPA gave Little Ben passing grades after a successful demonstration in July at Lehigh. The sedan navigated a four-way intersection, followed basic navigation and traffic laws, avoided obstacles and reacted intelligently to events. The car also showed an understanding of intersection precedence and successfully interacted with other vehicles by passing at appropriate times.
John Spletzer, assistant professor of computer science and engineering at Lehigh, in red shirt, stands in front of Little Ben.
Little Ben is equipped with video-camera “eyes” and laser range-finder systems called lidar, an acronym for light detection and ranging. Lidar can be used to estimate the distance and speed of clearly defined remote targets.
Robotic cars, said Spletzer, require state-of-the-art laser and computer vision systems, two of the areas in which he is contributing his expertise to Ben Franklin racing team.
Those systems enable a car to recognize the lanes, median and shoulder of the road it is traveling, to detect approaching vehicles and to distinguish between these vehicles and other obstacles.
A car must also be able to determine what parts of a parking lot it can and cannot drive through. If no lines are painted on a road, or if the car’s GPS system fails—a likelihood under bridges and overpasses and in skyscraper-dominated “urban canyons”—the car must be able to continue driving on the paved portion of the road.
“The car must at all times know where the road is, where the car’s half of the road is, and where the edge of the road is,” said Spletzer.
“The car not only needs to stay in its lane and remain the proper distance behind the car in front of it, it also needs to know to stop behind double-parked cars in its lane and wait for traffic ahead to clear before it proceeds.”
The Penn-Lehigh-Lockheed racing team has received funding from Thales Communications, whose president and CEO is Mitch Herbets ’79. Thales is part of the Thales Group, a Fortune 500 company and the ninth largest defense contractor in the world.
Accompanying Spletzer to California for the Urban Challenge was Jason Derenick, a graduate student in computer science and engineering at Lehigh.
The University of Pennsylvania fielded a car in the most recent DARPA Urban Challenge in 2005, but that vehicle did not advance to the national qualifying event.
Photos by Douglas Benedict
Posted on Friday, November 02, 2007