T-minus 10 minutes till kickoff, and everyone's set to go—the athletes are finishing their warm-up laps and the officials are huddling in pre-game conferences on the sidelines. Suddenly, the smell of burnt rubber and fried circuits fills the air. This can only mean one thing: A key player has just gone down.
At the 2006 RoboCup (http://www.robocup.org) in Bremen, Germany, these kinds of electronic mishaps were par for the course—along with kamikaze-swift attack passes to rival any Pelé feat. Billed as the tech equivalent of soccer's FIFA World Cup, the event, which took place from 14-18 June, showcased the cream of the artificial-intelligence crop. Thousands of competitor robots from 36 different countries competed in an array of divisions from ”small” to ”middle-sized” to ”four-legged.” The premise driving the RoboCup, now in its tenth year, is that robotic critical-thinking skills are best honed and demonstrated on pool table-sized playing fields.
”In soccer, it's difficult to plan. You can't just say, 'I'll start up the system, and five minutes later, the ball will be in the goal,'” says Hans-Dieter Burkhard, a robotics engineer at Berlin's Humboldt University and vice president of the RoboCup Federation. ”You always have to adapt, and that is what humans do very well and what robots are learning to do.”
For members of the RFC Cambridge team, made up of engineering students from Harvard University and the Massachusetts Institute of Technology, adaptation became the name of the game by necessity. With one member of their robot squad out of commission, the remaining three bots were tasked with picking up the slack in their first-round faceoff against the Field Ranger team from Singapore Polytechnic. Initially, the numbers deficit seemed to be too much for RFC Cambridge to overcome. Field Ranger mounted an unopposed blitzkrieg mission as its opening gambit, racking up several goals in less than 5 minutes.
But the tables turned as Field Ranger developed a collective case of performance anxiety. The robots converged around the orange ball in a tense semicircle, the goal within striking distance, but then abandoned their strategy, wandering aimlessly like bored kids waiting for a school bus.
” Was ist das Problem ?” one spectator whispered to another.
” Kaputt !” was the reply.
As similar confused moments on other courts illustrated, the biggest challenge for many teams has been designing robots that can respond when unexpected situations crop up. In order for a computer-based brain to be truly adaptable, ”its internal world models have to be very complete,” says Anna Foerst, an artificial intelligence expert at St. Bonaventure University, in New York. ”If not, it might encounter a situation that’s completely new, and it might not have a parallel for that in its memory.”
The Attempto team from Germany's University of Tubingen hit just such a snag in one of its early matches when the sun streamed through the windows of the arena. ”When sun comes in from the outside, the colors on the field change,” says team member Hannes Becker. ”That can interfere with the robots' visual systems.” If the bots can no longer detect the wavelengths of shades they have been precisely trained to recognize—the green of the turf and the orange of the ball, for example—coordinated drives toward the goal lose their momentum.
Before another match, a renegade robot wandered off the field toward the organizers' table, seemingly to greet them—but it was really making a beeline for the nearby orange RoboCup logo banner, which was exactly the same color as the game ball. ”Right now, if a robot sees something orange, it thinks it's a ball,” says Ubbo Visser, a local RoboCup chairman who saw the incident. ”Humans have a larger background information database, so we say, 'It can't be a ball because it's not in the right context.'”
In addition to programming conundrums, RoboCup designers face nuts-and-bolts physical engineering challenges. In the Humanoid division, which featured two-legged players (robots in other divisions move on four legs or wheels), some gimpy competitors had a hard time staying upright. Spectators tittered at referee verdicts like ”There will be no goal because the goalie has fallen down.”
”The problem of balancing on two legs is very tough. The AIBO dog robots have it easier, because they have four legs and more stability,” says Pasan Kulvanit, a member of Team KMUTT from Thailand's King Mongkut's University of Technology. ”And you can't even think about your artificial intelligence until you've built a robot with perfect balance.”
Though false starts were common, the bots could seem invincible when they hit a hot streak, mounting scoring drives capped by hot-dog maneuvers that demonstrate just how far robotics has come in the past decade. For top teams like those from Germany, Korea, and Iran, precise lateral passes and spectacular saves were routine game plan components, eliciting loud cheers from the crowd of 15 000 spectators. Even nascent leagues like the Humanoid division logged significant progress. ”Last year, almost none of the teams could walk, and this year, a lot of them can,” Kulvanit says. ”That's pretty amazing.”
Ideally, according to RoboCup president Minoru Asada, this incremental progress will inspire a generation of robots that can face off against human soccer players and win—a highly specific objective, but one that makes sense given how seamlessly robotics innovations can transfer between fields. Robots designed to perform tasks like aiding senior citizens and retrieving pets from burning homes will need the same flexible thinking skills crucial to soccer success. ”If you're able to make a robot that can win against a human [soccer] team, you'd definitely be able to use it to do things like clean rooms and wash windows,” says Frank Sehnke, a member of Tubingen's Attempto squad.
Despite marketing efforts to play up the competition's similarities to the World Cup, the RoboCup was dominated by an entirely different kind of intensity—in part because of its beta-test feel, in part because with such lofty technical objectives on the horizon, the identity of this year's winners seemed beside the point. Host Germany claimed 11 of the 33 gold cups in the offing, with China and Japan close behind, but most behind-the-scenes conversations between players focused on how they planned to upgrade their robot charges, not on how proud they felt to hoist the trophies.
”Everyone knows what soccer is, so that provides a way of communicating these new technologies to the public,” Burkhard says. ”But mainly, we want to understand what human intelligence means so that we can create it.”
About the Author
Elizabeth Svoboda is a freelance journalist based in San Francisco. She has written for The New York Times , the Christian Science Monitor , the San Francisco Chronicle , Popular Science , Discover , Wired , and IEEE Spectrum , among other publications; she recently concluded a tour of writing and reporting from Europe.