Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
Technology

Robocup 2002 World Robot Soccer Championships 126

Posted by michael from the slide-tackle dept.
dipfan writes "While the rest of the world is watching the soccer world championships in Korea and Japan this summer, at the same time the Robocup 2002 competition for soccer-playing robots is to take place there - the sixth time the tournament has been held, with 35 countries competing and this time including a "humanoid league" competition. The purpose is to foster research in robotics, with the aim of building a team of robots that can play and win against the best human teams by 2050. One of the pre-tournament favourites this year is Iran, who did well in 2000 but not in 2001. The Swedish team includes a star player named Priscilla, described as "looking like a sister of the Terminator". One of the Swedish designers comments: 'you don't want to give too much freedom to the robots as they will go crazy.' Much like flesh-and-blood highly-paid sports stars really."
This discussion has been archived. No new comments can be posted.

Robocup 2002 World Robot Soccer Championships More

Robocup 2002 World Robot Soccer Championships

Comments Filter:

  • Finally! (Score:3, Funny)

    by Yoda2 ( 522522 ) on Thursday April 25, 2002 @08:51AM (#3408643)
    Finally, a robot with balls.
  • you don't want to give too much freedom to the robots as they will go crazy


    Oh, great, crazy robots and soccer. Like there isn't enough soccer violence already. Next we'll have robot soccer players wigging out and pulling spectators out of the stands.

  • I am dreading to imagine what the father looks like if he finds out I was messing around with her...

  • robocup all the way... (Score:4, Interesting)

    by durfal ( 265688 ) on Thursday April 25, 2002 @08:57AM (#3408688) Homepage
    While i was talking to this phillips guy, who worked on this project in his spare time, some weeks ago he gave a demonstration (showing some video) this was my first contact with this sport, but it looked very cool...although there not one of the favourites (yet) i think its nice to c what kinda work is being done.
    And above what parts of this research can be used for other parts of lets say the medical industry etc.

    Keep up the good work guys

  • Disqualified (Score:5, Funny)

    by thatguywhoiam ( 524290 ) on Thursday April 25, 2002 @09:00AM (#3408697)

    In related news today, the Brazilian contender for this year's Robot Soccer Cup was disqualified after testing positive for overclocking.

    • Chainsaw equivalent (Score:2, Interesting)

      by AtomicBomb ( 173897 )
      Two to three years ago, a team mounted a spinning blade in front of the robot. The ball bounced like a bullet whenver got in touch with the spinning blade. It upset many people. Not only because that is of little skill, but also may damage other people's robot... At the end, the design was banded for further matches.

      True story from a lecturer that I know, who is a veteran robocup participant.
      • the design was banded for further matches

        It was banded... and released? then found miles away in another country.... then much later found with its batteries drained and tangled in some electrical lines, apparently trying to recharge itself...

        sorry, but I had to

      • Re:Chainsaw equivalent (Score:2, Informative)

        by SnowZero ( 92219 )
        That would be the FU-Fighters [fu-fighters.de] 1999 team. It was a spinning 5mm thick aluminum plate, which is pretty large considering the robot itself was about 10cm x 12cm. They could kick the ball at up to 6m/s. They turned it down later in the competetion, but it was not banned (more to keep from getting penalties than other team's anger).

        The design lives on still in a toned down version on the current FU-Fighters team and others have copied it too. It's affectionately known as a "spinning blade of death" kicker.
        • That addition is there to help them win, which isn't the true aim of the competition. Having something spin doesn't require AI or self-balancing functions, it can just spin. Pretty soon it will just be a bunch of spinning blades going after a ball. Then we just have BattleBots + soccer ball. The true innovation will come from the humaniod tournaments.
    • ...But will appeal claiming that a processor they brought in Japan, whilst looking Identical to one brought in Britain, in fact used a different clock speed. Therefore they are not liable and it should retain it's bronze medal.

      Oops, sorry wrong sport, season and country..

    • Re:Disqualified (Score:3, Funny)

      by Slak ( 40625 )
      I'm waiting for the RoboHolligans contest.
  • I don't understand their goal to make those robot play human player by 2050... How can this be fair?

    The robot doesn't get tired, and doesn't feel pain when his lower legs hits a steel bar!

    Unless they plan to recreate pain and sleepiness...(And that we can trust them not to cheat (ya sure...!))
    • It isn't about setting up robots to replace human soccer players, it is about proving that robots can be programmed to independantly perform complex tasks. Currently any hichschool soccer team could probably beat the robocup winner. The idea is to advance robotics.
      • Probably? At least last year you could have put a dead guy as a goalie and he would have won. (Because at least he didn't score against himself. Robotic players sometimes get confused and aim for their own goal.)
    • The robot doesn't get tired

      well they kinde do, their power source runs out, engines get overheated

      and doesn't feel pain when his lower legs hits a steel bar

      True but i could mess their servo's, sensors, hydrolics(sp?) ect in the leg

      I also read about a project to build a robot to drive an F1 car agianst a real pilot. The robot should fit in the cars cocpit and use the normal controls of the car. no electronic interfaces alowed. sadly enough i cant seem to find the link now
    • Yeah, but by 2050 you won't be able to tell which ones are the robots and which ones are the humans!


      Soccer players will get mechanical legs, internal communication devices, pain filters and oxygen-producing nanomachines in their bloodstream. So what if the robot doesn't get tired or feel pain -- neither will the humans, and they'll effectively be telepathic as well.

    • Watch the new Nike (well, new as far as us football-loving fans in the States are concerned) Secret Tournament [nikefootball.com] (warning, Flash-only site) commercial(s). If a robot can pull moves like that off in the next 48 years, I'll be damn impressed. I know technology is advancing rapidly, but a machine that weighs the same as a player, has the mobility of a footballer and possesses an AI that matches the best players in the world is a long way off.

      Just watch guys like Thierry Henry, Luis Figo, David Beckham, Zinedane Zindane, etc...you just can't program talent like that. Not even by 2050, I would wager.
    • Because it's an enormously difficult task to do (as a robot) what you and I take for granted.

      Motion (walking, for example) involves all sorts of attitude shifts to maintain the centre of gravity in the correct place - it's not just putting one foot in front of the other. If you look at how athletes use their bodies to kill momentum and do quick turns, I think you'll agree that the slow-plodding robots are a long way off yet...

      Machine vision is still in its' infancy. What you have is unsurpassed. What a 95% blind man has is unsurpassed by machines. Vision implies cognition, (without it, it's just a TV screen!) and this is Hard (capital H). Being able to recover depth, handle occlusion and parallax, make inferences from absolute and relative properties (size, circularity, colour, etc.), and generally 'see' is simply not possible yet in the general case.

      Temporal tracking is needed to tie each of those frames together, and make further inferences and aid cognition. The ball moves, after all... kicking it is actually solving a pretty complex tensor of vectors that are constantly changing...

      Prediction is necessary to make best use of the current tactical position, with allowances for what might happen next. If your defence has just got the ball, the forward might want to make a run towards the opponents goal... This sort of thing is 'common sense' to people, but really hard to get a computer to come up with. It's easy to hard-code some rules into the machine, but the real goal (pun intended!) is to get the machine to devise its' tactics from instant to instant.

      In short, although it's "just a game", it embodies a large cross-section of really hard problems in robotics. Frankly, my money's on the humans!

      Simon
      • These are the hardware issues, but do you know how complicated and cool the software issues are?

        To start with, soccer is a team game -- one of the most interesting features of this type of work is figuring out how to make these robots work together, and independently. This is where you get your 'selfish / communal' (sometimes referred to as 'capitalist / communist') programming models.

        Right now (if I remember correctly) the idea of rewarding the whole team for a goal -- the communal model -- is dominant, if individual players were all trying independantly for a goal-reward, then no one would pass, and the goalie would run across the field leaving the net open.

        But, if you're going to have star players, or different roles for different identical team members, then you are going to have to incorporate the selfish model to a certain degree inside the communal model. This type of programming is interesting even without the hardware issues.

    • The goal is to have a humanoid teams with similar strengths and weaknesses as a human team, but be able to beat the humans simply through intelligence (surpisingly difficult even with the low IQ of your average soccer player).

      An example of a two robot team that can win (or at worst tie) against any human team is the goalie is a large immobile robot that covers the entire goal (read brick wall). The other is a large scooper/cannon robot that is placed at the center of the field. At either the first half or second half it will get the kickoff, at which point it scoops up the ball a launches it at unstoppable speeds towards the opponent goal.
      This is not the goal of RoboCup.

      Hopefully one day we will have a team of physically inferior robots that can beat the human WC Champions. Until then we'll keep working.

      Also, if you though the competition was out of your grasp, think again. They have a simulation based leauge that uses an open source simulator found at http://sserver.sf.net, along with lick to example clients and client libs.
    • I'm on the University of Virginia team, and we're in the simulation league. We don't have physical robots. The result is we don't have to spend the effort on mechanical concerns and image recognition, and we get to devote more effort to the AI aspect of the competition. In the simulation league, the robots DO get tired, they do miss shots, and they have imperfect information. The idea is to remove all physical considerations from play and have them win on intellect alone. The robots being used in competition are no where near the level required to beat a world cup team, but I imagine that once they get close, these "humanizing" factors will be added to keep the match fair. At the current rate of development, I expect this to be well before 2050.

  • When I first read this, I could've sworn it read Robocop. I can only say I'm disappointed -- players being riddled with bullets from Robo's automatic pistal or impaled on that data spike would make things pretty interesting.

  • Ah bright future indeed... (Score:4, Funny)

    by gklinger ( 571901 ) on Thursday April 25, 2002 @09:02AM (#3408708)
    I dream of a day where we have robots to play soccer for us thus freeing up humans for more valuable endeavours like building pyramids out of Coke cans.
  • If you're going to build a robot, make it useful! (Hey! Bring me a beer!)

    I saw this on the local (Orlando) news last night. A guy at UF built a beer opening robot (ABOR) as part of a project/competition. Some amusing ideas. Here's a link to a story about it: Robots [sunone.com]
  • Our robots will be very unique this year, our fastest omni design yet. Just wait... :)
    • We have a new omni design as well, and it looks like the finalized robot (with all the junk on it) is going to be pretty fast. We'll have to watch out for the FU-Fighters, I hear they have an 8m/s (unconfirnmes) kicker they used at the German open. Of course kicking speed was not their problem in the past, but still... This year is going to be fun.

      P.S. It was no fair not showing us your new robots when we visited :P (we didn't have ours yet). Are the new robots strong enough you can you stand on their covers like the 2000 robots?
  • So if they throw rolls of toilet paper onto the field at regular matches, what'll they throw when the robots are playing? Rolls of duct tape?
  • Has been able to win against the best chess player. So if I understand correctly, the logic involved to win a game isn't really the problem, it is more of a mechanical problem, isn't it? Recent video games are already able to beat really good video game player, and there are not even super-killer-incredibly-intelligent applications. So I think that 2050 is a good goal to try to achieve. By then, the mechanic involved in robot should have marginally improved and also processor power. My guess is that I should not even take that long. On the other side, looking a robot playing sports would not give me the same excitement has watching a true local team kick the ass of it's oponent. I'm currently following the Canadian-Boston series (I'm from Montreal), and the thrill is really to see those guys fight to win and put all there energy into it. Even if they lose, in the end I'll be proud of "my team". Would it be robots playing, I'm not sure I would be so much partisan. It would only be an enhanced Robot War :-) But, it is quite interesting stuff, and great for the advancement of science. We should see more of this in more field. maybe also organize Geek Olympics!
    • "So if I understand correctly, the logic involved to win a game isn't really the problem, it is more
      of a mechanical problem, isn't it?"

      Mechanical? Oh, there's far more to it than that. Designing good algorithms for vision and planning is not a trivial task, even if it does get easier with increased memory availability. How do you tell where the ball is, and discern the ball from a similarly colored spherical object on the sidelines? How do you identify your teammates? What motions should you use to respond to the ball headed towards you? A chess player is far easier to implement - the problem space is small and well-delineated (you have X many possible moves, with Y many possible responses, etc.)
    • Has been able to win against the best chess player. So if I understand correctly, the logic involved to win a game isn't really the problem, it is more of a mechanical problem, isn't it? Recent video games are already able to beat really good video game player, and there are not even super-killer-incredibly-intelligent applications.

      There are plenty of software problems. It turns out that chess is actually easy compared to the stuff we do everyday like walking. It's just that we have a lot of specialized wet-ware for the normal tasks, so we don't notice how difficult they are. Control and perception are major problems. Planning and coordination are also major problems. Chess is easier because things don't move while you are thinking and you don't have to pick up the pieces if you do it like Deep Blue did. The video games are usually easier for the computer than the real world because they have perfect information about what is going on in a convenient format for them. They almost always have a huge interface advantage as well. The humans attention is usually divided and forced to operate through a relatively clunky interface where the computer doesn't mind keeping track of 80 things at one time. The fact that the human ever wins at the hardest levels shows how stupid the computers are.
    • Video games are heavily hampered by their interface. Just because the simulation has the skill to beat you when you're using your thumbs doesn't mean it can beat you on a 3-D field.

      Anyway, it's easy to make an incredibly good video game team. All you have to do is have the players controlled by an omniscient observer with perfect information. No human could match that. When you make the players autonomous, with imperfect information, a limited field and range of view, and limit their communication with one another to the equivalent data bandwidth of soccer players yelling at each other during play and pointing with their arms (this is implemented in the soccer server) the challenge becomes much greater. Getting independent agents to function as a team when they have different information is not at all trivial.

  • Robocup (Score:1, Insightful)

    by Anonymous Coward
    This project is an 'all encompassing' project involving so many research areas (vision, AI, real-time, networking, embedded, hardware, radio comms, more....). It is a very and interesting useful project from an academic point of view because you can put new research into something practical.

    Research ideas are so often just theoritical, this is a chance to see how it works in a practical integrated system.
    • I've been working on the RoboCup team at my university for two years, and we're finally going to compete this summer. From experience, I can tell you that soccer is a VERY challenging problem. Putting a robot on the field is a huge accomplishment. Trust me - it IS fair to humans because try as we might, humans can't match the stupidity of robots.

      I'm not complaining about getting paid to go to Japan - Woohoo!

  • Video (Score:2, Interesting)

    by paranoidia ( 472028 )
    My university, Carnegie Mellon, competes in this competition. We usually do very well, I think second last year or the year before. But if anyone would like to see a video of the action, here's one here [cmu.edu]. Very cool stuff.

  • Priscilla, queen of nightmarish robot designs. (Score:5, Interesting)

    by Remus Shepherd ( 32833 ) <remus@panix.com> on Thursday April 25, 2002 @09:12AM (#3408784) Homepage
    Here are some pictures of Priscilla. [chalmers.se] That robot is scary looking. I wouldn't want to meet it (her?) on a soccer field or anywhere else.

    Robots should be cute. Otherwise they remind us of the whole taking-over-the-world scenario.
    • I wouldn't want to meet it (her?) on a soccer field or anywhere else.

      That's what alcohol is for.

    • NO! (Score:1)

      by flikx ( 191915 )

      Robots should not be cute. Look at the Abio, it's a joke!

      Robots should be complex, filled with pinch-points and aluminum cross-pieces; and with big stickers stickers labels 'DANGER'.

    • You should have a look at the Aibo (four legged) leage.
      They're extremely cute and I was surprised how well
      they play.

      The next season will have new rules. The game will be
      played four on four (how fitting) instead of three on three,
      the playing field will be enlarged, and the next generation
      players are allowed to use wireless communication.
    • Robots should be cute. Otherwise they remind us of the whole taking-over-the-world scenario.

      I tend to think cute robots would have a much better chance of taking over the world:

      unsuspecting human: "Aww, look at that cute robot teddy bear! It's even got a toy laser gun in it's paw!"
      evil robot teddy bear: "Will you be my friend?"
      unsuspecting human: "aww, of course I will you cute.."
      BRRZZZAP!!!
      evil robot teddy bear: "stupid human"
  • ... I've been dutifully building a robot soccer (football) spectator. I'm just putting the finishing touches on the riot subroutine now...
  • The genius of today's great footballers (Zenidine Zidance, Luis Figo, Rivaldo et al) is their incredible creativity and flair for doing the unexpected. (I'm not offtopic, read on a bit). Often they choose the improbable course of action, which, because it is unexpected by the opposition, yields results.

    I will be interested to see whether these robots are able to be programmed with the same creative impulses that a professional footballer posseses, or whether the style of play will remain formulaic and based on high-percentage tactics. It'd certainly suck if all they did was lob the ball forward and try and get a head on it *cough*englishfootball*cough*, but just imagine how pissed off you'd be if you got nutmeged (ball through the legs) by a robot!

    D'you rekcon they will eventually manage bicycle/scissor kicks? Just be sure to avoid getting landed on *wince*
    • ....if you got nutmeged (ball through the legs) by a robot!

      That brings up an interesting point. Is anybody building a Robo-cup for protection against such an event?

      Would a robot specifically programmed for this move be referred to as a rack server?
  • I visited this thing back in '99 when it was held in Stockholm.

    Cool stuff! (I liked the Sony Aibo compo, especially.. they're so cute.. )

    Definetly more interesting than robotwars,
    but a little more violence wouldn't hurt. ;-)
    (Nasty tackles, anyone? )

    Go Team Sweden!

  • Favorites and team info (Score:5, Informative)

    by SnowZero ( 92219 ) on Thursday April 25, 2002 @09:30AM (#3408902)
    (Note: I'm sitting in a RoboCup lab right now, so IMNSHO:)

    I don't think the favorite is going to be Iran this year, but more likely the Phillips professional team, which won the German Open [robocup-german-open.de] this year. That said, I wish people would realize there are 4 leagues, not just the middle size league, with different robots and different favorites in each. In the Sony Legged league, UNSW [unsw.edu.au] has dominated, though we [cmu.edu] came in second :) There are a lot of strong teams in the league though so we'll have to see...

    In the small size, I'd say the favorites are last year's winner LuckyStar II [np.edu.sg] from Singapore, and Big Red [cornell.edu] from Cornell University. FU-Fighters [fu-berlin.de] is also a pretty strong team. Our team (CMU) hopes to do a lot better this year in the small size league. We won in '97 and '98, but haven't done too well since then.

    I don't know to much about the simulation league so I won't bother to comment. Finally, a personal plug: See a video from the vision system of a Sony legged robot here [cmu.edu]. It'll give you more respect for how hard a problem this is :) It sure did that for me, even though I've been programming them for several years.

  • Cool... (Score:3, Interesting)

    by CyberDruid ( 201684 ) on Thursday April 25, 2002 @09:32AM (#3408913) Homepage
    ...I do my AI Masters Thesis for that guy (Peter) and some friends of mine have been working on Priscilla. He has an enormous talent for getting publicity on everything he does. The smaller robot, Elvis, has been on national TV and on posters on public transportation here in Gothenburg, among other things. Everytime he starts on a new project, he manages to make the press interested and write an article about it. Perhaps more scientists should look into PR?
  • do videos of these robots playing exist? this sounds pretty cool. id like to see how agile they actually are!
    • yeah...this page [science-arts.org] (taken from the main story) has some videos...however, they don't appear to be from the "humanoid" division, because all the players look like little boxes...
    • You can see movies of our Cornell "box-like" robots from the last 3 years at http://robocup.mae.cornell.edu [cornell.edu] While they are boxes, our robots use omni directional drive, which means we can move in any direction at any time. Makes for much more effecient movement, and allows us to dribble and pass, soemthing no other team in the f180 size does. As for the humaniods, Honda has a bunch of photos of the Aismo and associated robots they have built walking up subway stairs and kicking soccer balls, but most of those videos are quite staged.
  • How does one compete in this tournament? It looks like all the teams have identical equipment: do the companies (like Sony) sponsor them?
    • I'm not positive of this anymore, but while I was going to school (couple of years ago), we played around with the Robocup in our AI class. It was very interesting and very difficult. At the time, there was a downloadable environment that you could play with to get the behavior of your little robots correct. It implemented a field and the rules and you could download teams, and then play around with them. I also believe that they used the software for some of the competitions so others, like us without the unlimited budget, could also play. Here's a link to the soccer server. [sourceforge.net]
    • How does one compete in this tournament? It looks like all the teams have identical equipment: do the companies (like Sony) sponsor them?

      There are several different leagues that one can enter. There is a simulator league, small-size league, middle-size league, Sony legged league, a humanoid league (new for this year), and a couple rescue leagues.

      The simulator league has no hardware. The software is downloadable from sourceforge. This is the easiest league to get started in since there isn't a lot of money involved and you can even enter remotely. Keep in mind that a lot of researchers are working hard on this problem, so most of the teams are really good. The Sony legged league is run by Sony. Sony provides a lot of support. You have to make a proposal to Sony to get into this league. A committee of researchers and Sony personel decide which teams to allow in. Everyone uses the Sony hardware in this league. The small-size and middle-size leagues have hardware built by the teams. It usually costs at least $10,000 for all the hardware needed for a small-size team. Middle-size teams run from $3,000-$40,000 per robot (4 on 4 competition). See www.robocup.org [robocup.org] for more details. Registration is already over for this year, but there will be another competition next year (in Italy, I believe).
  • Improvements are continually being made but, as Professor Nordin warned, "you don't want to give too much freedom to the robots as they will go crazy.

    "You want the robots to have the ability to learn some of the things, but not do completely unexpected things."

    Finally, it seems like someone has watched enough sci fi flicks to get the idea that autonomous machines are scary.

    I read about advances in AI theory and think "Sheesh, haven't these guys ever heard of Skynet? HAL? Maximilian?" I read about artificial wombs and wonder if Aldous Huxley was ever required reading...

    Even the Simpsons had it right:
    "Itchy and Scratchy Land: the amusement park of the future where nothing can possi-blye go wrong. Er, possi_bly_ go wrong. Heh, that's the first thing that's ever gone wrong."

    Frink - "You've got to listen to me. Elementary chaos theory tells us that all robots will eventually turn against their masters and run amok in an orgy of blood and kicking and the biting with the metal teeth and the hurting and shoving."
  • I'm just wondering if the fans at the Robo-cup will riot like in regular soccer.
    *News Flash*
    Rioting robots caused a great deal of destruction at the IBM headquarters today, destroying servers and singing "We Are the Champions". Police were called in to restore order after several fires and much looting took place.
    Hmm...I wonder if M$ has a team in the Robocup...imagine the possibilities.
  • I was at the RoboCup98 in paris, it will be interesting to see how things have changed. The match that I saw involved a few brick looking robots moving around in a random manner. It was the first time that I saw the Sony Dogs... Do the robots now wear boots?
    • I was at the RoboCup98 in paris, it will be interesting to see how things have changed. The match that I saw involved a few brick looking robots moving around in a random manner. It was the first time that I saw the Sony Dogs... Do the robots now wear boots?

      The robots now look much slicker. They also perform a lot better. The teams no longer look random at all. They are certainly capable of scoring. Last year saw many scores of around 10-1. The robots still go barefoot.
  • Picture this, you're attending your teams playoffs and the judge makes a white-cane call. You voice your opinion and Miss Priscilla stands up 2 rows behind you, abrasively questioning your judgement! Time for the better part of valor??
  • There's a decent article [bbc.co.uk] on this linked from BBC News' front page.
  • Neat idea, but I think fundamentally flawed in that these robots are programmed by geeks. What the hell do they know about football? Have you seen those videos? All those damned Aibo's running after the ball... none of them hang back in defence or make a move for the box to wait for a cross in from the left.

    They've got no width, their midfield is sorely lacking, defence is a shambles and the strikers have no pace.. Its like watching Scotland play.

    Matt.
  • For some pictures of the RoboCup 2001 competition, see http://www.robot-news.com/robocup_2001_images/ [robot-news.com]

  • By 2050 I'll be way too old to play... I was hoping to buy a couple of these things to make up the numbers next time we're a few short for 5 a side :)

  • The Only US University to Qualify (Score:3, Informative)

    by RJ11 ( 17321 ) <serge@guanotronic.com> on Thursday April 25, 2002 @11:24AM (#3409646) Homepage
    I'm on the University of Virginia team [virginia.edu], and we're one of two teams to qualify representing the US for the simulation league (which doesn't use real robots, and is thus a lot more fast paced). The other team being AT&T Research Labs.

    We're actually in the process of looking for sponsors so that we can get to go to Japan for the competition.....
    • I'm on the University of Virginia team, and we're one of two teams to qualify representing the US for the simulation league (which doesn't use real robots, and is thus a lot more fast paced). The other team being AT&T Research Labs.

      Just a small clarification. The parent is referring to the simulator league. There are also several US teams entering in other leagues. For example, Carnegie Mellon University is entering in the small-size league and the Sony legged league.
  • Comment removed based on user account deletion
  • Elvis, which is the predecessor of Priscilla and the first and most famous robot from the lab was built by two friends of mine.

    Marcus [tallhamn.com] and Manne [chalmers.se]
  • I want an open source soccer league, so when someone scores the announcer screams

    GPLLLLLLLLLLLLLLLLL!
  • UNSW (Uni of New South Wales, Aust). Always is. They have won every game they have competed in, with an average lead of 30 goals (no joke).

    The difference is, they've seen the limitations of the dogs and kludged appropriately for the environment, while the other teams have used very generalised AI algortihms, that while very clever, are beyond the dog's processing power and give them no competitive advantage.

    They used this technique in 2000, published the results, and no one learned and they won again in 2001. I'll back them again, even if the AI lecturer in charge is a bit of a tool.
    • UNSW (Uni of New South Wales, Aust). Always is. They have won every game they have competed in, with an average lead of 30 goals (no joke).

      Actually, UNSW lost games to both Carnegie Mellon University and LRP (Paris) their first year. Also, they have never won a game by more than 14 goals and the games were all close their first year. I'd say the difference is that UNSW spends a lot of time tuning there systems for the task at hand. Many of the other universities spend more time doing basic research, which won't make you play better soccer this year, but might a few years down the road. If you measure success in terms of published papers, then UNSW is behind many of the other universities. That being said, their system is impressive. Hopefully, this year we (I'm from Carnegie Mellon University) can give them a bit more of a challenge. The gap certainly closed between 2000 and 2001. It should be exciting to see what happens this year.
  • "While the rest of the world is watching the soccer world championships in Korea and Japan this summer"

    No, the rest of the world is watching Football and (occasionnally) American Football, Americans are the one watching Soccer and Football ;).

    BTW, I am not a big Football fan so when my American boss talks about Football with somebody else I realize that he knows more about it than me, which always makes me laugh.

Slashdot Top Deals

I THINK THEY SHOULD CONTINUE the policy of not giving a Nobel Prize for paneling. -- Jack Handley, The New Mexican, 1988.

Close