Kiro, the Foosball Robot

JasonFleischer writes "Although the official line from the RoboCup competition is that robots should be ready to challenge humans on the soccer field by the year 2050, we don't have to wait that long to see man-machine competition in the bar. Researchers in Germany have developed a table football (foosball, table soccer, whatever) robot. The human challenger(s) take the red team, while the machine works the blue side, using an overhead video camera to see what's happening on the table. The conference paper shows that while the machine generally wins against the normal bar-amatuer it has no chance against a human grandmaster. But these kinds of things are always improving, after all look how big a deal the man-machine chess competition turned out to be. So perhaps the current table football world champions should be watching their backs."

Comments

Another step in AI

[Greenmonkey2021]

I think that they are just trying to utilize current AI technology to further expand it. AI in chess often consisted of analyzing every possible move. Foosball while not as intellectual has much more freedom of movement, relative to chess. Also, the AI has to react with fast reflexes as opposed to the long periods of thinking a chess computer can do. I think Foosball could be used to help advance AI. It has unique challenges but is still constrained enough to prevent the problem from being too big. FYI, there were a group of students in my university that also designed an AI foosball table for a fourth year project. They used sensors on the floor instead of a camera.

Grandmasters, Masters, Pros and MONEY!

[Elk_Moose]

For all of you out there that don't think you can do anything with foosball except drink and talk trash, check out the money you can win at regional, national and international tourneys. VIFA and USTSA

How to be a playa

[evilninja]

I've seen a lot of arguments against this machine in this small thread, but the prominent two seem to be A) foosball doesn't require strategy (like chess) and B) it will be easy to beat.

As an avid foosball player, I first want to refute the "lack of strategy" argument for foosball. I play frequently with Tom Spear and Robbie Mares, two of the greatest foosball players in the world. (I don't know about elsewhere in the world, but in America they are known as "Pro Masters," not "grandmasters.") Either one of those guys will tell you that foosball is like a game of chess on speed. The amount of skill you posess for the game will only take you so far. At a certain point, the game becomes almost entirely mental.

Players reach a skill level where they can, physically, do whatever they want to do with the ball. For a pass or a shot, they choose their hole before they even start to move the ball. Trying to defend the pass or the shot is a matter of being able to predict your opponent's maneuver; if you try to play a straightforward defense and watch to see where they're going, then race them to the opening...you'll lose every time.

That said, I think that a machine could be a very worthy competitor. With a fine-tuned history-based decision-making algorithm for baiting and blocking shots, I'm sure it could play great defense if it's fast enough. As far as offense, I'm sure the machine could hit all sorts of angles and speed shots with deadly precision. It will just take time to teach it how to play.

If you're at all interested in more foosball stuff, check out the Valley International Foosball Association and the United States Table Soccer Association. If you like to play, you should check out some local tournaments. For Colorado, we've got our own site and you might have one for your area, too. Speaking on behalf of tournament players everywhere, we'd love for you to come play our tournaments.