Catch up on stories from the past week (and beyond) at the Slashdot story archive


Forgot your password?
Classic Games (Games) Robotics

Robots Aim To Top Humans At Air Hockey 177

An anonymous reader writes "You probably knew that the Deep Blue supercomputer beats chess masters, and that last weekend a software robot defeated four poker champions. But you may have missed this one: a GE Fanuc robot is taking on humans at air hockey. The robot is powered by a special PC-board that can instantly switch between 8-bit and its 32-bit modes. The 8-bit version lost to most human players, but the 32-bit microcontroller has defeated even the best human air hockey players by a ratio of three to one."
This discussion has been archived. No new comments can be posted.

Robots Aim To Top Humans At Air Hockey

Comments Filter:
  • by Anonymous Coward on Wednesday July 09, 2008 @05:20PM (#24124821)
    I won't be worried until computers start to beat us at bear pong.
    • by Spudtrooper ( 1073512 ) on Wednesday July 09, 2008 @05:22PM (#24124875)
      How is a robot supposed to get a bear to stand still and open its mouth to throw in a ping pong ball?
    • by Broken Toys ( 1198853 ) on Wednesday July 09, 2008 @05:24PM (#24124899)

      Bear pong?

      Squirrel pong, sure; monkey pong, any day; but bear pong? That's where I draw the line.

    • Re: (Score:3, Funny)

      by jgarra23 ( 1109651 )

      I won't be worried until computers start to beat us at bear pong.

      Is that similar to beer pong, only more dangerous?

    • by Anonymous Coward on Wednesday July 09, 2008 @06:29PM (#24126197)

      And thanks for demonstrating the neurological effects of playing beer pong.

      Actually, to be fair, it's very likely that similar malfunctions are also the cause of playing beer pong. Researchers originally thought that positive feedback was initiated by "pledging" a social fraternity/sorority, but it now seems most likely that "pledging" is itself but a symptom of a congenital defect.

      The evolutionary advantage for the species is obvious: when defective organisms have a tendency to clump together and disable their higher cognitive functions en masse by imbibing excessive quantities of ethanol, then they can be easily eliminated through mass extermination.

      However, there is associated risk: if extermination fails, the defectives may begin interbreeding, thus evolving a subspecies, supertards, which may begin undermining the species' broader social organization, due to the supertards' natural inclination for the lowest-skilled activities---business management, marketing, politics---which are, terrifyingly, activities with great potential for reducing the overall species' quality of life if not bounded and carefully monitored by more intelligent organisms.

      The results of careless monitoring could be disastrous. In a "perfect storm" scenario, where the supertards are allowed to impress their opinions upon large groups via mass communication and positions of power, then humanity's classical value system could actually be inverted! Imagine, a world where sports, entertainment, and consumerism are deemed more important than science, philosophy, and art! Where responsibility is shunned, work avoided, and a sense of entitlement the rule! Where xenophobia is disguised as religion, and religion derided by faux-scientific antireligion! Where film actors, instead of being recognized as glorified circus clowns, are given society's highest respect & obsessive admiration! Where full-time sportsman, instead of being mocked for wasting their lives, are beloved "heroes" whose salary is greater than the aggregate salaries of entire university faculties! Where conspicuous consumption is a substitute for cultural tradition! Where public schools are run by political committees and unions! Where the front page of Yahoo! recounts last night's television schedule alongside news of war and natural disaster! I could go on, but why? You see the horrors we could face if the extermination of supertards were to be forgotten.

      I certainly hope that never happens.

    • by Forge ( 2456 )

      Computers can beat humans at games where the possibilities are finite.

      For instance. Any decent programmer can make a tic-tac-toe game that is absolutely unbeatable. A robotic pool player of championship grade should be relatively simple (as game playing robots go).

      Poker isn't actually that hard since so much of poker play is disguising the emotional reasoning behind your decision to fold, call or raise and if you raise by how much. Since a computer can consistently play in 10 2nds after the commencement of

      • by Forge ( 2456 )

        I must add that, the computer can be taught to "read", some aspects of it's opponent's play.

        BTW: "2nds" should have "seconds". I need to reduce my dosage.

  • Show me a robot that can beat humans at real hockey. Then I'll be impressed.
    • by Hoi Polloi ( 522990 ) on Wednesday July 09, 2008 @05:26PM (#24124953) Journal

      Do you really want robots out there who can check you into the boards and beat you in a fight?

      • by scottrocket ( 1065416 ) on Wednesday July 09, 2008 @07:14PM (#24126765) Journal
        Only if they're fembots - ooooh
      • Re: (Score:3, Funny)

        Jan: Well, what would you suggest.
        Michael: A statue.
        Jan: Of Ed?
        Michael: Yeah.
        Jan: I'm not sure that's realistic.
        Michael: Well, I think it would be very realistic. It would look just like him.
        Jan: No, that's not â¦
        Michael: We could have his eyes light up, we could have his arms move â¦
        Dwight: That is not a statue, that is a robot.
        Michael: I think that is a great way to honor Ed.
        Dwight: And how big do you want this robot?
        Michael: Life size.
        Dwight: Mmm, no. Better make it two-thirds. Easier

    • by mr_mischief ( 456295 ) on Wednesday July 09, 2008 @05:26PM (#24124965) Journal

      I'll be worried when they can beat us at Dodge the EMP Blast.

      • by nsayer ( 86181 )

        Um... I may be wrong, but I think a paraplegic could beat a robot at that, given that humans don't respond to EMP.

      • Re: (Score:2, Insightful)

        by p0tat03 ( 985078 )
        Well... Since the only way to generate a sizable EMP blast is a nuclear detonation, I would say that's a small comfort... :)
        • Re:Boring... (Score:5, Informative)

          by Hojima ( 1228978 ) on Wednesday July 09, 2008 @10:46PM (#24128701)

          From wikipedia:

          Non-nuclear electromagnetic pulse (NNEMP) is an electromagnetic pulse generated without use of nuclear weapons. There are a number of devices to achieve this objective, ranging from a large low-inductance capacitor bank discharged into a single-loop antenna or a microwave generator to an explosively pumped flux compression generator. To achieve the frequency characteristics of the pulse needed for optimal coupling into the target, wave-shaping circuits and/or microwave generators are added between the pulse source and the antenna. A vacuum tube particularly suitable for microwave conversion of high energy pulses is the vircator.

    • Re: (Score:2, Interesting)

      by elemnt14 ( 1319289 )
      Although I agree that seeing hockey teams full of robots would be somewhat exciting (only to see them go up in sparks by a hard hit), I have to say that i personally would enjoy watching the sport with human players. Robots can not think for themselves (well, not yet anyway), so you would not see strategy that can change due to the changes on the field, or see some really great shots that only a human could pull off.
    • that wants to beat humans at air guitar. Then I'll be impressed.

      • Re: (Score:2, Insightful)

        by hplus ( 1310833 )
        Show me a robot that wants. Then I'll be impressed.
    • by Jerf ( 17166 )

      OK [].

      Yeah, I'll grant it's not fully autonomous, but I guarantee you I can use it to beat you at a game of hockey.

    • by Otter ( 3800 )
      I'd cite Strange Brew as a precedent, you hoser, but I guess those weren't actually robots.
    • by Detritus ( 11846 )

      You mean, give the robot a stick and program it to violently assault its opponent?

      Now introducing the 2008 GE/FANUC Thug-o-matic 5000!!!

  • Futurama (Score:5, Funny)

    by Anonymous Coward on Wednesday July 09, 2008 @05:22PM (#24124863)

    Bender: Now, Wireless Joe Jackson, there was a blern-hitting machine.
    Leela: Exactly. He was a machine designed to hit blerns.

  • Shufflepuck (Score:3, Informative)

    by Trogre ( 513942 ) on Wednesday July 09, 2008 @05:24PM (#24124907) Homepage

    All I can say is:
    "Good shot"

  • by way2trivial ( 601132 ) on Wednesday July 09, 2008 @05:24PM (#24124915) Homepage Journal

    I refuse to be impressed.

    I can create a 2 bit air hockey robot that will lose to everyone but Butters!

  • Video (Score:4, Insightful)

    by electricbern ( 1222632 ) on Wednesday July 09, 2008 @05:28PM (#24125001)
    They could make a robot that beats human players at air-hockey but they were not able to make a watchable video or it in action? I guess it is all about specialization.
  • by TornCityVenz ( 1123185 ) on Wednesday July 09, 2008 @05:30PM (#24125045) Homepage Journal
    This must be one of the best ways to get a research grant to pay for an air hockey table I've ever heard.
    • Actually given that they took pains to make the system so it could use either an 8-bit or a 32-bit micro at random suggests that Freescale was footing the bill as a publicity stunt the whole time. I see no other reason for it.
  • by plasmacutter ( 901737 ) on Wednesday July 09, 2008 @05:30PM (#24125047)

    Honestly, it's not as if some robot is paintaing abstract art or writing poetry here.

    Robots exceeding humans in strength and precision when designed to do so is not news, it's our technology "working as intended".

    If they didn't exceed human strength or precision, i'd expect articles like "engineer blacklisted as incompetent for designing defective robotics"

    • by Bill, Shooter of Bul ( 629286 ) on Wednesday July 09, 2008 @06:10PM (#24125843) Journal
      Yeah but if they created a working human like arm with the strength and reaction time of an average human and it still beat everyone in arm wrestling or air hockey, then I would be impressed. That kind of research would also be very useful for creating artificial limbs.
      • by p0tat03 ( 985078 )
        Prosthetic limbs don't need to be intelligent and play air hockey. They need to be strong and have good control, since the implication here is that a human operator will always be present (or more accurately, *attached*).
        • They do need to be able to make the most out of minimal input from the user. The user might very likely have a minimal degree of movement of whatever the prosthetic is connected to. It would help greatly if the arm was intelligent enough to guess what movement the user was trying to do based upon the circumstance. If you were playing air hockey it would interpret your movements as attempts to play air hockey. If you were trying to play the guitar, it would interpret them in that fashion. There could be a s
    • by nfk ( 570056 ) on Wednesday July 09, 2008 @06:25PM (#24126129)

      "Honestly, it's not as if some robot is paintaing abstract art or writing poetry here."

      You picked a couple of interesting examples; I'm sure robots could paint abstract art and write poetry that would match some of today's offerings by human beings. Anyway, I have no idea how complex it is to program a robot to play air hockey, and whether it involves only strength and precision, but there was an idea I read in a book by Douglas Hofstadter that I find amusing: artificial intelligence is always defined as whatever a machine cannot do yet.

      • by pitchpipe ( 708843 ) on Wednesday July 09, 2008 @09:19PM (#24128035)

        artificial intelligence is always defined as whatever a machine cannot do yet.

        I wish I had mod points, you are exactly right. It's funny how people forget that what was once thought to be something only a human could do, if a machine is able to do that task better, then of course the machine could do it better. After all, that is what it was designed for.

      • Neither source nor output is available, sadly, but one of my senior theses was a program to write Japanese haiku. Its disgustingly easy because human brains love to play "fill in the gaps", and in haiku if you have two verbal images which are rather disparate but share a common bond (easy to guarantee by use of a seasonal dictionary, which is exactly how human writers do it), that is considered part of the charm. (I was also really helped by selection bias, in that I was allowed to present samplings of ou

    • Figure out the trajectory of a disc amid of two round objects in a rectangular space isn't exactly amazing technology.

      Talk to me when you can build something that knows the difference between me wanting fresh air and me needing oxygen.

      • I can build a robot to place a plastic bag over your head and eventually the problem would just goes away.
    • by cgenman ( 325138 ) on Thursday July 10, 2008 @12:34AM (#24129555) Homepage

      it's designed to upsell 32 bit processors. Annoyingly enough, it just takes x,y coordinates from a vision system, estimates trajectories, and outputs position data to a robotic arm. Really, you should be able to compile code on the nes to do that. It calculates three rebounds? That seems somehow like an easy task if you're being fed realtime position information.

      Color me amused but unimpressed. It is a great ad, but an ad nonetheless.

  • I for one welcome... (Score:2, Interesting)

    by gnosi ( 893875 )
    Oh that is just getting so old. In this context however it could become so real.

    On to the real subject...

    "If droids could think for themselves we would not be here"

    The day is coming when most if not all the routine and skilled functions of life will be carried out better by robots than by humans.

    The last bastion for the human mind will be pure abstract thinking.

    I do not even pretend to know what that new day will bring to the meaning of mankind when computers become better than the human mind a
    • Re: (Score:3, Interesting)

      That's what's commonly called a "singularity". A point that changes things so much that it's impossible to predict its effects with any certainty. Depending on how we handle things, it could be a violent occasion worthy of a large-budget action sci fi movie, a quiet fade and disappearance of humanity, or a metamorphosis of humanity into a new form. Or it might not ever happen. *shrug*
      • by mcrbids ( 148650 )

        So, by this definition, wouldn't it be a "singularity" for most /.ers to establish a relationship with a member of the opposite sex?

      • There will be a war. The humans will win. The robots will live somewhere else for a while. Then they will launch a surprise attack, wiping out the vast majority of the human race, with the survivors spending years searching for Earth... ah crud!

    • Re: (Score:3, Insightful)

      by notnAP ( 846325 )
      I do not even pretend to know ... when computers become better than the human mind at pure abstract thinking.


  • The article hints at both, so it's hard to tell if the robot's true advantage lies in being able to analyze the puck's path more quickly than the human players, or is the robot arm simply faster/more powerful/more accurate than a human arm? If the former, then that's pretty cool. But if it's the latter, well heck, I can hop in a car and drive faster than an Olympic runner, but I don't write articles about it.

    • by MBCook ( 132727 )

      Better tactics. The robot is better at predicting the puck and where to hit it. It also plays very defensively. Combine that with high speed and accuracy, and the bot is a winner.

      In fact, the only reason it loses in 8 bit mode is it can't calculate the position of the puck fast enough to always catch it.

    • Smarter and faster (Score:3, Informative)

      by dj245 ( 732906 )
      Probably both. These microcontrollers are designed to calculate corrective action (often very small actions) to processes (such as pipe flow rates, temperatures, etc). When a process deviates from the setpoint, the microcontroller is supposed to calculate the correction (increase control output X slightly). I would say something like this would require some custom coding for the controller, but nothing too crazy. One of the harder parts would be coming up with a good input data method and formatting the
    • Re: (Score:3, Informative)

      it's hard to tell if the robot's true advantage lies in being able to analyze the puck's path more quickly than the human players, or is the robot arm simply faster/more powerful/more accurate than a human arm? If the former, then that's pretty cool.

      Why? It's a game where the puck is operating in a near frictionless environment. Hence, the speed can be computed as if it is linear. Of course a robot can more precisely measure time between samples and the location of an object on a fixed plane. So, the ca

  • by idontgno ( 624372 ) on Wednesday July 09, 2008 @05:35PM (#24125147) Journal

    First they're beating us at chess, then at air hockey... pretty soon they're rolling around yelling "EX..TER..MI..NATE", disintegrating us, and avoiding staircases.

    This is how the human race ends, mark my words.

    (Yeah, I know, the Daleks are supposed to be cyborgs. Roll with it, it's supposed to be a joke.)

  • by CthulhuDreamer ( 844223 ) on Wednesday July 09, 2008 @05:37PM (#24125197)

    Wouldn't just setting the arm to oscillate in an arc in front of the the goal at a few thousand rpm make scoring against it impossible? (Not to mention the 200mph random rebounds coming off a blocked shot?)

    • by EdIII ( 1114411 ) *

      That's why I stopped playing. I hit a puck so hard it broke the tip of my pinky finger sideways. It then rebounded off my finger to make a very interesting (and sadly hilarious) sound off some poor little girl's head.

      Playing a robot? Riiight. I give it a week before the emergency room staff is removing a puck from somebody's face.

  • Both the robot an the human should be drunk to be truly representative of regular air hockey.
    Beyond that, I say: "Just wait until the foosball competition you 32-bit tin can!"

  • by Dr. Spork ( 142693 ) on Wednesday July 09, 2008 @05:58PM (#24125603)
    I would love to see this in an arcade. I'd pay a dollar to play the arm - bring on the 32bit mode! If they could make the arm fold itself out of the way while two people are playing, this would make an excellent arcade machine.

    What's more, if the arms were standard and mass-produced, there's a great excuse for a little coding competition: Whose program will win when it's robot v. robot?

    Lots of cool AI, artificial learning and computer vision would go into it, and the result would no doubt be fun to watch!

  • It's pretty easy to figure out what competitions a machine will be better at than a person.

    Chess: Really hard to make a machine that can beat a person. And it takes quite a machine. Why? The game is entirely mental. And computers are really dumb. But we can make them be really dumb really fast, so we eventually pulled it off.

    Poker: It's almost cheating for a machine here. Much of the game is based off of your opponents meat-weaknesses and reading their hand from their faces. The computer doesn't hav

    • Re:Yeah, and? (Score:4, Interesting)

      by RzUpAnmsCwrds ( 262647 ) on Wednesday July 09, 2008 @08:07PM (#24127421)

      It's almost cheating for a machine here. Much of the game is based off of your opponents meat-weaknesses and reading their hand from their faces. The computer doesn't have a face and is using pure probability. Even the best poker player cannot read them. So unless they're better at math than a computer and and their poker prowess isn't based on reading people, they're never going to win. It takes the game out of the game really. The perfect odds playing machine against the perfect odds playing player would come out even.

      If you think that this is how poker works at a professional level, you don't know very much about poker.

      Tells are a small factor at a professional level.
      Good players already have a firm understanding of the pot odds and expected value of a call.

      The major problem with writing a good poker program is that it can't be exploitable. If the program is too "tight", an experienced human player will realize this and can always raise with trash (because the program will fold), with a minimal chance of getting caught. If the program is too "loose", the human player can play good hands far more aggressively, knowing that the program will call.

      This is a very general example. In reality, poker strategy is far more nuanced. But the basic problem that computers face is not being predictable. And, no, playing randomly doesn't help - it merely substitutes poor play for predictable play.

    • by hob42 ( 41735 )

      Poker: [...] Even the best poker player cannot read them.

      Not quite true. I don't know anyone who relies on seeing someone's face to get a read on them - but that's because most player play (at least some) online poker these days. You can learn a lot from how your opponents play. In that sense, it could be extremly easy to adapt to a computer player that isn't complex enough to try to fool the human from time to time.

      Air hockey: It's mostly about physical speed.

      That makes it sound like it's about the speed of the arm, but it's more about the speed of the brain. And no, it's no surprise that with a certain le

  • better uses (Score:3, Funny)

    by zazelite ( 870533 ) on Wednesday July 09, 2008 @06:46PM (#24126443)

    Good work, GE boffins. It warms my cockles to see our best minds conquer one more idle pastime that robots hadn't already been programmed for. When the Japanese finally achieve their ultimate goal of an android with functional genitals, those air-hockey robots will be left playing with themselves.

  • Wouldn't a dumb mechanical arm that rapidly moves the pusher left and right in front of the goal be unbeatable?

    Just move the pusher fast enough, and it's impossible to get the puck in. If the puck is going fast enough to be able to get in before being hit away by the pusher, the puck will be going fast enough to be airborne.

    Eventually, the human will lose.

  • when you find a robot that can beat a human in several things.
    1) Air hockey
    2) Darts
    3) Pool
    4) Bowling
    5) mini golf
    6) Afterwards tie a shoelace

    This all without any rebuilding of the machine or doors. Also no external help, like power.

    Untill then I am not impressed if a specialy build machine is able to do a task better then a human can.

  • ...of the blernball argument between Leela and Bender, something about the star pitcher in the old robot league being a converted howitzer? Of course a machine would win at air hockey, I'm surprised the 8-bit version lost.

  • The 8-bit version lost to most human players, but the 32-bit microcontroller has defeated even the best human air hockey players by a ratio of three to one.

    Cripes, I dread to imagine how powerful a 64 bit microcontroller would be!

  • I can cut plywood that's about 3 feet wide and 2 inches high and can make it unbeatable in air hockey. See, as the GM of my wooden army of air hockey players, I KNOW that goaltending and defense wins championships. You're still thinking offense, speed, agility, yadda yadda. Solid goaltending, boys. That's how you win.
    • If you can defend against 100% of your opponent's shots, eventually they will score against themselves enough times to make you the winner.
  • "My computer beat me at chess. But then I beat it at kickboxing." --Dmitri Martin

  • The human lost because the game was only going at 4fps.

"You can have my Unix system when you pry it from my cold, dead fingers." -- Cal Keegan