There could be tough times ahead for Luca Toni. The Bayern Munich striker, just recently crowned Bundesliga champion and currently leading the scoring charts with 21 goals, may soon be confronted with an unsurpassable obstacle… of the robotic kind. Its name is Goalias (or GoalIAS if you prefer), and it’s the first robot-goalkepeer capable of defending a regular-sized football goal.
IAS stands for Institut für Automatisierungs und Softwaretechnik (“Automation and Software technology Institute”, or something along those lines) and is the University of Stuttgart department responsible for the creation of the mechanical goalkeeper. If you’re thinking about a cyborg with a humanoid shape though, you’re way off. The robot in question is simply a cardboard on wheels, shaped in the form of a goalkeeper and moving alongside a track placed on the goal line. The real engineering marvel of GoalIAS comes from its three videocameras and computer processor, calculating with lightning-fast velocity (under 400 ms in fact) the best position to make a save every time a shot is taken.
It works like this: the player takes a shot, the cameras (placed on top of the crossbar) analyze the trajectory the ball is taking, and relay the information to the central processor. The computer then calculates the best position to make the save and moves the “goalkeeper” accordingly. All this is done in under 400 milliseconds.
GoalIAS was recently tested by somewhat of a VIP of German football, namely currently 2nd-ranked Bundesliga topscorer Mario Gómez (I guess Toni was unavailable). The German International took a series of shots on net, and it turned out robo-keeper saved 50% of Mario’s efforts. I bet he wasn’t bragging too much at practice the following week…
Anyways, after Mario Gomez the next test of ‘robo-keeper’ is set for May 22. This time GoalIAS will be facing the German Women’s National football team. Who knows? Perhaps by that time the robot (already in its second version) will have been perfected even more.
Tags: GoalIAS, Mario Gómez, Technology
Posted in German Bundesliga, Miscellaneous |
Related Posts:
.jpg)
Good one marco. Didn’t know bout this. Its good to have multi-talented writers and reseachers (if i may..?) to bring us news related to football. I prolly wouldn’t have found this piece on other sites or forums, so props given when props due.
I suppose a real test would involve having this robo-keeper take part in a real game (with multiple defenders and attackers – 4v4 will do) so that we can test in-game reaction times.
Because if this works out, and if the robo-keeper can ‘learn’ from watching players and from previous games, then this could be a great training tool for young kids.
or for penalty takers…
or it could replace Paul Robinson…
Spitfire: Thanks!
I find these bits of news who are “out of the ordinary” always interesting.
SpiralArchitect: Cheap shot…
Ahmed I’m afraid not, at least not yet. From what I gathered on the official website and the distance the shots were taken, several conditions need to be satisfied for GoalIAS to work.
First, there absolutely can’t be any player interfering with the viewing path of the videocameras. That is, except for the ball and the shooter no one can be in close proximity to the goal or anywhere between the shooter and the “keeper”, something which would be impossible to achieve in a real-time match.
Secondly, the cameras are “fixed”. That is, they are not mobile, and they always point in the same direction. As such, the shots probably have to be taken from the same distance every time. Shoot from a little bit farther away, and the processor probably will no longer be able to compute the ball trajectory. Not to mention that any “curling” shots would be impossible to trace…
The May 22 test vs. the German Women’s National team is probably the same that Mario Gómez did: take a series of shots from a fixed position.
As for using this as a training tool for young kids… well, aside from the practical applications and everything (cost, maintenance, etc.) what would be the interest of facing an almost infallible goalkeeping machine (other than mere curiosity)? Teach the kids how to curl the ball in order to “outsmart” the robot? I fail to see the usefulness. Football is a game played against human opponents, with all the qualities and “defects” that humans bring. Learning to play the game also involves trying to exploit those defects, like fakes and dummies to send the keeper the wrong way on one-on-ones for example. You can’t really learn that from a machine…
[...] This is Goalias. He’s a robot designed by the University of Stuttgart in the mold of a goalkeeper (presumably after the home team’s Champions League run). Goalias is a cardboard cut out placed on a running track attached to video cameras and all sorts of fancy equipment which, as you can see, can track the path of the ball. First player to test it out was Mario Gomez. The robot saved half of Mario’s shots, which isn’t much more than the goalkeepers of the Bundesliga can say. [...]
Really interesting article Marco, just reading on your comments really. It would be f*cked if Raidi Jaidi started doing his tricks!
[...] del campeón Real Madrid al Barcelona, leer frases vía Bar Deportes. 2)El arquero robot, puedes ver algunos diseños vía mCalcio y otro video vía Bar Deportes. 3)Las Chivas USA visitan Disneylandia, ver fotos vía el Blog de [...]
[...] point: it could still be fooled by some hard curving shots with plenty of spin.More on that story here… No tags for this [...]
Is it possible that clubs would be replacing human keepers or other players with robots like this? That would be the end of football. I hope that that is not the way this is going.
this sounds like a good idea but doesnt have a practical side to it and if they could me it usable in a real match it wouldnt react in time
I designed the ball recognition system for the GoalIAS system so i can elaborate on how it works. Marco is generally correct in what he wrote except for a few things.
The cameras are indeed fixed around the field but this does not limit the system in any way. It is true that the system we built will not work if there are players in the cameras’ field of view but this is simply because the cameras are only black and white cameras. by using color cameras one could work around this by using, for example, an orange ball.
with regards to curved balls…the system does account for these shots as well and can easily save curled shots as well. balls with a high degree of rotation and kicked at speeds > 100km/hr into a corner have a high probability of scoring though. this is mainly because we only used 3 cameras and the visibility in the corners is somewhat limited.
finally, the system we built assumes the ball is being kicked from the official penalty kick point (11 meters away). the only reason we did this was because it simplifies calculating the balls trajectory (it was only a 6 month project). it would not be very difficult to modify to work with all balls kicked from surrounding locations.
oh and if ur interested in better videos:
1. http://www.youtube.com/watch?v=fLpqxJOl1K8
2. http://www.youtube.com/watch?v=Xez8y_wvi1M
3. http://www.youtube.com/watch?v=N1cvdfAJEEM
4. http://www.youtube.com/watch?v=qkR8KYzz42M
Thanks for your insight Benjamin, and very cool videos (especially the first one with Mario Gomez).
I guess that will be your next challenge then!