John Spletzer, assistant professor of computer science and engineering at Lehigh, in red shirt, stands in front of Little Ben.
In the arid terrain of Southern California, just north of San Bernardino and west of the Mojave Desert, a robotic car named “Little Ben” made history on Saturday, Nov. 3.
The car, designed by engineers from Lehigh, the University of Pennsylvania and Lockheed Martin’s Advanced Technology Laboratories, was one of just six vehicles to navigate and drive itself through the entire 60 miles of the 2007 DARPA Urban Challenge
Little Ben did not win any of the $3.5 million in prize money from DARPA, the Pentagon’s research wing, but it recorded several significant honors while exceeding the expectations of its engineers.
"Little Ben" was one of just six driverless cars to complete the 2007 DARPA Urban Challenge and it was the only car of the six finishers whose team had not received $1 million funding from DARPA to prepare for the race.
In completing the course at the former George Air Force Base in Victorville, Calif., Little Ben survived a rigorous, yearlong winnowing process. A total of 89 teams, from around the U.S. and abroad, entered this year’s Challenge, the third such event that DARPA has sponsored. Three dozen, including Little Ben, passed site visits last summer to advance to last week’s national qualifying event.
Only 11 cars, nine fewer than the 20 DARPA expected, survived the qualifying event to advance to the Grand Challenge on Saturday.
And of those 11 cars, only six finished the course, successfully executing complicated tasks that included parking in a specified parking spot, entering and exiting a traffic circle, waiting their turn and proceeding at four-way stop signs, and merging with moving traffic.
“We are all very happy that we finished,” said John Spletzer
, assistant professor of computer science and engineering and lead Lehigh member of the Ben Franklin Racing Team
“We were the fourth car to cross the finish line. We were the only Track B [self-funded] team to finish. And we finished ahead of MIT’s car.”
Lehigh President Alice P. Gast had ample praise for the Ben Franklin Racing Team.
“We are all tremendously proud of how well you have done,” Gast wrote in an email to Spletzer. “To finish in this company is a great accomplishment and a credit to the hard work and persistence that the entire Lehigh-Penn-Lockheed team has put into this endeavor.
“You are all winners in our book.”
David Wu, dean of the P.C. Rossin College of Engineering and Applied Science, also lauded Little Ben’s team.
“Not only did you compete well with the greatest engineering talents nationally and internationally,” Wu wrote in an email to Spletzer, “your design is among the very few that pushed the technological envelope so that [Little Ben] could complete all of its complicated tasks like a human driver would.
“This is absolutely amazing.”
A national security agenda
The goal of the Urban Challenge 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.
Teams from Carnegie-Mellon University, Stanford University and the Virginia Institute of Technology finished first, second and third in the Grand Challenge and were awarded prizes of $2 million, $1 million and $500,000 by DARPA, which stands for the Defense Advanced Research Projects Agency
The Ben Franklin Racing Team and other top finishers stand a good chance of receiving future funding from DARPA as the agency continues its quest towards unmanned military vehicles. The University of Pennsylvania is lead member of the team, and Dan Lee, associate professor of electrical and systems engineering at Penn, is team leader.
The Grand Challenge was webcast live by DARPA. Aerial shots and action footage, combined with expert commentary, made viewers feel like they were watching a NASCAR event, albeit in slow motion, as the average speed of the robotic cars was less than 15 mph, with top speeds reaching only 30 mph.
The announcers billed the event as a “meeting of geeks and gearheads,” and went to some length to describe the “personalities” of the cars. While some vehicles were programmed to act assertively, even aggressively, on the roadways, the announcers said, other cars, including Little Ben, were dubbed “careful” and even “gentle.”
Small but smart
Little Ben was perhaps the smallest vehicle among a field of SUVs, station wagons and even a large green military truck. Teams equipped their cars with sound: While Little Ben cooed a melody befitting an ice cream truck, other vehicles emitted siren sounds and loud, braying honks. Each car sported decals from its sponsors; in Little Ben’s case, these included Lockheed, Oxford Technical Solutions and Thales Communications, whose president and CEO is Mitch Herbets ’79.
The Ben Franklin Racing Team worked day and night for several weeks before the national qualifying event, refining 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 worked more [consecutive] days than I can count,” said Spletzer.
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 require state-of-the-art laser and computer vision systems, two of the areas in which Spletzer contributed 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.”
Jason Derenick, a graduate student in computer science and engineering at Lehigh and a member of the Ben Franklin Racing Team, accompanied Spletzer to California for the Urban Challenge.
Although the purpose of the Urban Challenge is to improve robotic technology for military vehicles, Spletzer is confident engineers can go further. Just as computers have been programmed and trained to beat the world’s grand chessmasters, he says, robotic cars may someday navigate roads more ably than humans can.
“Computers can really do well when you focus them on specific tasks,” he says, citing IBM’s “Deep Blue,” which in the 1990s became the first machine to win a chess tournament against a human.
“Ultimately, we’d like to make robotic cars that can drive better than humans can. That won’t be easy. The driving environment has many complicated aspects. It’s not limited to an eight-by-eight chessboard.”