RoboCup 2007 Opens At Georgia Tech
Craig writes "The 2007 installment of RoboCup has begun; individual events opened to the public today. RoboCup is an international robotics symposium and competition whose goal is to advance the fields of robotics and artificial intelligence to the point that in 2050 a robot soccer team can defeat the human world champions. This year, RoboCup is located on the Georgia Tech campus in Atlanta, GA, marking the first time a university is hosting it and only the second time since it began in 1993 that it is located in the United States."
"point that in 2050 a robot soccer team can defeat the human world champions."
Be rid of "soccer" and "champions" and you have an interesting article!
"ATI cards are like buses...They're huge, red and have bad drivers."
In 2050, I am going to get so fucking high and totally watch that game.
And humid!
And folks who think W is doing a great job - the 30%+- of the population who think Bush is doing a great job? They're my neighbors here in Georgia! You know: the big SUV driving obese folks with the pristine "W '04 " bumper stickers.
Those robots better be running on oil! None of that pansy "alternative fuel" shit - but OIL!!
Great test for robots going into hostile climates!
I prefer Flambe as apposed flamebait.
Got a chance to go to the 2005 games in Osaka Japan when we won second place in the small size league. That whole week of competition was intense.
Last week was the Robotics Science and Systems conference, also at GA Tech. Some of the biggest robotics researchers worldwide (such as the guy who lead the team that won the DARPA Grand Challenge last year) were all there to talk about the latest advances in the field... I think they were originally scheduled to be the same weekend; oh well.
'Every story, if continued long enough, ends in death.' --Ernest Hemingway
wow looks like u n00bs got ***OWNED***!!!
"to the point that in 2050 a robot soccer team can defeat the human world champions" That'll primarily be due to the freakin' laser beams attached to their heads...
Having submitted this story (yes that's me up there) I thought this deserved a mention since Slashdot has reported on RoboCup in the past (2001, 2002) 2004, 2006).
I'm also covering this for our campus newspaper (click my name above for the preview article in last week's issue), so if anybody has anything they wanted to know or see pictures of let me know and I can try to make it happen. As I was bogged down with classes today I haven't seen any of the robots compete yet (although last week I "met" some still-unfinished robots being built by Georgia Tech students) but I intend to spend at least a few hours there tomorrow and every day the rest of the week.
(BTW, is anybody on here a participant in the event?)
audioLibre - freedom of music
Not all RoboCup robots are humanoid though.... Some are small wheeled robots with colored blobs on the top to ease their detection....
Another league exists: FIRA... FIRA's "RoboWorld Cup 2007" takes place between 14 and 17 July.... I'm actually doing a team's vision system... (not for the RoboWorld Cup though....)
Wow! I love symposia.
Watch for the Fix... (I have seen this before)
When IBM used "Deep Blue" to beat Kasparov in 1996 Game 1 of the Chess Challenge and took the series in 1997, The Fix was in. Those freaking collage boyz were paid well and put the fix in when they changed the starting macro parameters on the program against Kasparov every time and tailored it to his playing style. If you let the pro's take them on 100 times in a row "The AI" gets routine they will kick there but without thinking about it. As anyone who has played numerous computer games for years, the AI gets stale. Yea you can pull good PR Stun, but that don't mean the level of technical knowledge has advanced none.
This crap actually hurt development of of AI, in my mind and probably set research back for years.
Georgia Tech is doing some cool stuff with aerial robotics:
i cs.html
http://www.gtri.gatech.edu/atas/teams/aerialrobot
Kinda wish I was there now instead of 1962...;-)
rj
First perhaps I should mention that RoboCup isn't only about football (soccer), although it's a majority, but also has leagues in rescue and a fairly new one called @home. I'm a participant on the rescue league (part of the Swedish team from Uppsala) and so far I can say that none of us is very impressed with Georgia Tech's handling of the cup. To start with there is no internet at the competition and development area which causes a lot of inconveniency whenever you need something of it (which is quite often). You'll either have to use the paid services one floor down, which I clocked to an amazing 700 byte per second when I tried to download the Linux headers I needed for driver installation, or walk at least five minutes to the dorms where the net is ok but you can't really do that every time you want to look something up. Secondly they don't seem to be able to keep the power up for more than a few hours at a time, it can go down quite unexpectedly without warnings. While this isn't much of a problem for my team seeing as we use only laptops and battery powered devices it is a real bother for many of the teams which uses normal stationary computers and other such devices. Being a student I never been to another RoboCup world cup (although I was at the German Open) but my teachers assures us that they never seen anything like this before. It is quite a bit of bad publicity for Georgia Tech.
I was actually a volunteer there yesterday during the team-practice session. I have some pictures and videos of the event at Hizook.com.
What a moronic project. Just ask yourself: would you put your legs in for full contact with metal (or any other material that can't feel pain)? Didn't think so.
And don't even start with the "we'll understand pain" line by 2050. Ridiculous.
Well, if there are no limits, somebody should see me about my robot soccer team concept. 1. RoboGoalie is slightly taller than the goals and slightly wider than the goals, and is made of completely solid material. Now all you need to do is come up with a robot that can kick _one_ goal in 90 minutes.......
I got live and ready Internet for a whopping $3 dollars a day for all around campus access and availability -- What a rip. OH and Georgia Tech drew FREE Internet lines to the dorms -- I am SO UNHAPPY!
When I read through some of the replies I get the feeling that people may perceive this competition as a pointless little toy problem. And you are partly right - it is a toy problem. But it is far from being pointless one.
o gram/
c le/2007/07/07/AR2007070700774.html
s chneider.robocup.competition.cnn
To me (and I assume most of the other participants), RoboCup is about something else entirely. It is about developing new technologies on a complete systems level. Apart from finding some neat hardware solutions ranging from simple wheels to dynamic humanoid gaits the more interesting overarching theme is the advance of technology on AI aspects - such as goal oriented behavior and agent cooperation.
Sure, it is a lot about hardware and toys. You start tinkering with the hardware platform of your choice - be it some shop-bought Aibo doggy or your own awesome little humanoid creation. There is no limit but costs and human resources. And even if you are just a student with not many resources at hand you can always bring your ball-pushing Lego creation.
And it is true that a large part of the competition seems to consist of robots miserably standing and wiggling in place or randomly tipping over every other minute. But to be fair, the participants are trying to catch up on a few billion years of good old-fashioned evolution while unfortunately fighting with rather pathetic problems such as bad network connectivity and random power outages (see the comment by Spearhawk).
My point is that for most of us it is often very hard to get the proper funding and benchmarking environment for research on autonomous and self-sufficient agents exhibiting semi-intelligent behavior.
Personally, I do not care all that much about soccer. But similar to the DARPA Grand Challenge everybody understands the game and more importantly it is a good way to gain public interest in and acceptance of robotics. From a roboticist's perspective soccer is just the right mix of a fairly simple rule-based environment and open-end multi-agent complexity. The real fun starts once you have teams competing on the field - since now you have the whole real-time adaptivity thing going.
I guess my point is that you can go on and develop robots from a complete-agent perspective by solving the perfect toy problem without worrying too much about when and how the technology will benefit society and why anybody would pay for it right now.
Personally I have absolutely no doubts that the solutions found by working on a toy problem such as soccer will more or less directly benefit society in the near future. We for example are a Swiss team from ETH Zurich participating in the brand new "Nanogram League". We are able to fully control robots with sizes of only a few times the width of a human hair - and not many people in the world can do that. In about 6 months we have developed an entirely new technology just to compete in this event. And yes, it is still "simple" tasks in a two-dimensional environment.
Sure, at this point we are talking mere speculation... but there is no reason why this technology does not scale into 3D fluidic environments... in clear text: you can potentially propel tiny agents that go and find that hidden tumor somewhere in your body and destroy it... how useful would that be?
Here some illustrating movies of our robots and links to other fun stuff that might be of interest to you:
http://www.youtube.com/watch?v=lnLGpl1N7Ns
http://www.iris.ethz.ch/msrl/research/special/nan
some media coverage:
http://www.washingtonpost.com/wp-dyn/content/arti
http://www.cnn.com/video/#/video/tech/2007/07/07/
Here is the video of the Humanoid Soccer Final: http://www.youtube.com/watch?v=ICgL1OWsn58 In the match the titleholder Team Osaka (Japan) met team NimbRo from Freiburg University (Germany). The same two teams had met in the two previous years. The 2007 final was one of the best humanoid soccer games ever, if not the best. Team Osaka played with one goalie and one field player while NimbRo used two field players. The Osaka robots were very quick to approach the ball and to kick it across the field. The NimbRo robots excelled in one-on-one fights for the ball and also demonstrated nice team play. The exciting game was open until the end. The final score was 8:6 for NimbRo. The NimbRo robots not only won the KidSize soccer competition, but also the TeenSize Penalty Kick, where they defeated Pal Technology (Spain) 5:4 in the final. More information and images can be found here: http://www.nimbro.net/