Forgot your password?
typodupeerror
This discussion has been archived. No new comments can be posted.

In Robot Soccer, US Team RoMeLa Dominates Robocup 2011

Comments Filter:
  • by Anonymous Coward

    Hong, Lee, Han, Nguyen, Song, Orekhov, Hopkins, Pesek, Lee, McGill, Nunez, Kapadia, Donnellan, Thakur

    The Chinese team won the Middle Size League, btw.

  • You may now begin the regular, tedious argument about an American site using American English. Please reply to this comment to continue the discussion on this topic, I'm sure none of the points have ever been made before and original insights will be heard.
    • Ok - let me start. How the hell can you call a game where ball spends more time in the players hands as football.
      In football, there should be a penalty any time someone(except the goalkeeper) touches the ball with his hands when the ball is in play.

      • by roguer (760556)

        I honestly don't know.

        But riddle me this: How can you call a game where no one rubs their hind legs together to make a chirping noise "Cricket"? After all, sports are all about their names, right?

        Or maybe this: If the purity of "football" is in the name, why are you allowed to touch the ball with head, chest, rump, knee, etc.? If hands are off-limits because of the name of the game, then why aren't other body parts?

        Or maybe let's just call the whole conversation ridiculous and be done with it.

        • Even more ridiculous....the English came up with the word soccer. It was a play on "association" in "association football". When the game came over here, we already had American football, so we used the other word they had for it.

          Not ridiculous...did anyone else watch that US women's world cup match today? What I am about to say is shocking...

          It was as exciting a sporting event as I have ever watched. Seriously.
      • by artor3 (1344997)

        This website is neither about slashes nor dots! I am outraged and will bring this up at every single opportunity!

        Signed,
        Every European to ever use the internet

      • How the hell can you call a game where ball spends more time in the players hands as football.

        Like this: "Football." Pretty easy, eh? I'll bet even you can do it.

      • The ball is advanced down the field by foot. Using your definition above, soccer should be renamed to kickball.

        Seriously, we've had this argument, you must be aware of its reply by now. Like e4-e5 in chess.

  • Did anyone else watch the video [youtube.com]? Is it really that hard to make robots that can walk decently?

    It seems like from a mechanical standpoint, it wouldn't be too hard to make something that mimics the muscular structure of the body......it's not like human muscles are particularly strong, or human nerves fast transmitting, or human sensors high precision. I'm having trouble understanding what the challenge is in building a robot that works reasonably well (or at least not dreadfully slow).
    • by Smauler (915644) on Sunday July 10, 2011 @02:25PM (#36712978)

      Our sensors _are_ pretty high precision, and very well integrated with our brain. They're also integrated well with each other. The three _big_ ones that are used in football would be sight, equilibrioception (balance), and proprioception (limb awareness), IMO (with touch and hearing playing lesser parts). Those 3 alone are very hard to replicate well in robotics, and combine into a complete package.

      • by m4ktub (2333996)

        I don't think we really know how we think and act. Also, our sensors are hardly high precision.

        Robocup results are anthropomorphic by design but the people involved quickly realize they have a bunch of wires that break and boards that burn in their hands; not very human of the robots. In the end - in Robocup they say 2050 - we will not have a replica of human perception. My guess is we will have a cyborg with her own way of perception and that perception may not be high-precision at all. Our is not and wor

    • by sbates (1832606)

      You have to think about what you do when you walk. It's very rare that any two of your steps are precisely the same. You are constantly adjusting the length of the stride, the roll of the foot, the vertical position of your toes, the angle at which your knees bend, etc. You don't think about it consciously, but if you tried you might find you have a hard time walking smoothly :)

      Like Smauler says, we have not only awareness of these parts independently but also in relation to each other and to the ground.

      • So what you are saying is, it's not the hardware that is the roadblock for better soccer-playing robots, it's the software? That's kind of cool.
        • by KDR_11k (778916)

          Many leagues use standardized robots, there are even completely software-based leagues (AR league, for example). It's a competition of software skills, not really much about electronics.

    • by vlm (69642) on Sunday July 10, 2011 @02:59PM (#36713212)

      Did anyone else watch the video [youtube.com]? Is it really that hard to make robots that can walk decently?

        It seems like from a mechanical standpoint, it wouldn't be too hard to make something that mimics the muscular structure of the body......it's not like human muscles are particularly strong, or human nerves fast transmitting, or human sensors high precision. I'm having trouble understanding what the challenge is in building a robot that works reasonably well (or at least not dreadfully slow).

      The devil is in the details. There's lots of muscles involved. Newbie mistake #1 is thinking you can build a walking mechanism using a really simplistic count of leg joints. Like trying to get away with about 4 servos per leg. You really do need a nearly fully articulated body including arms and spine, even if its cost is incredible compared to just two articulated legs. While walking to refill my water glass I felt my sore elbow moving as I dynamically balanced walking down the hall, and theoretically I wasn't using my elbow. Newbie mistake #2 is trying to use a single canned routine. Walk around some time and try to straighten or slump your back, it has an effect on gait. Even if you're not paying attention, your gait is pretty dynamic, and newbs can't program dynamic gait very well. Newbie mistake #3 is applying human male standards of beauty to something inhuman. To me, a reasonably well shaped 20s female human just coincidentally happens to have a "decent walk" that I would admire as she walks by. Other people, live and let live, their idea of living is Really liking the 4-legged gait of a sheep, or the 2 legged gait of a 'roo, etc. I'm sure to a robot, a similar robot would seem smooth and graceful, and if we don't like it, the robot's opinion would probably be to shrug shoulders and grunt "eh". Newbie mistake #4 is not emulating or handling the shock adsorption of soft tissue, both semi-statically and also dynamically. Not just female swaying as per above #3 or whatever, but the cushion of the spine and feet (and shoes!)

      • by Sir_Lewk (967686)

        "Newbie mistake #3 is applying human male standards of beauty to something inhuman"

        It's not a matter of beauty, it's a matter of function. These things take minutes to cover mere meters.

        • by vlm (69642)

          "Newbie mistake #3 is applying human male standards of beauty to something inhuman"

          It's not a matter of beauty, it's a matter of function. These things take minutes to cover mere meters.

          The two are sometimes (often?) the same, looking at spots in the giant solution space of how far outside of static stability you're willing to leap in order to walk...

          One local maximum seems to be human bipedal, give them some wide hips to store more batteries and the android would inevitably have a human female gait that we would think is hot and graceful and would inevitably (pendulum effects on the legs, dynamic stability of a spinal column, etc) be about as fast as a human female.

          Another local maximum i

    • by vlm (69642)

      it wouldn't be too hard to make something that mimics the muscular structure of the body......it's not like human muscles are particularly strong

      No, its impossible at this time to even come close to human muscle as an engineering material IF you include strength to weight ratios of the entire system (heavy batteries), power to weight ratios, peak vs sustained power output, long term durability, total energy use / efficiency, etc.

      People have been trying, and failing, to build artificial limbs for centuries for trauma victims, and not only are the artificial limbs not better than the original, but they generally don't even come close to the real thing

      • ok, point taken, but look at the movie; all it would take is a goalie robot that can move within three seconds to a position where it can block the goal (and we are talking a two meter space here), and the team with that goalie would win. Is that really so hard? I mean, let's be honest, those robots were kind of pathetic.
    • That's last year's video. This year's video is linked from the summary. I haven't watched it yet, I'm just pointing out that you are being critical of the wrong thing.
      • oh, ok, good point, but this year's video isn't any better!
        • Sadly too true. But they're bigger!
        • The leading robot (CHARLI) at least is a quite significant improvement over last year's video. Sure it's not running, but the precision and recognition of the ball are very noticeably improved. We shouldn't expect it to happen overnight, it's an extremely complex process. Baby steps, baby steps...
    • by xtieburn (906792)

      For a good analog try play QWOP.

      http://www.foddy.net/Athletics.html [foddy.net]

  • Winning 2 divisions in 1 league out of 5 is NOT a sweep. A sweep would be winning all the leagues. 1 out of 5 isn't even close. Congratulations on the wins in the humanoid league.

    For those that are curious, the other 4 leagues are simulation (focusing on team play and low barrier to entry), small size robot (hardware/software combined, wheeled robots), middle size robot (hardware/software combined, wheeled robots), and standard platform league (software only using real humanoid robots).
  • for this endeavor. I have little doubt that the problem they're solving is hard. But is this progress?

    Anyone trying an evolutionary layered approach where the control code is evolved?

    Seriously, it looks like my Alzheimer-wracked mother trying to play soccer, except that, unlike her, it continues to pursue the ball. I hope the DoD's killer robots are more nimble than this: otherwise our Android Corps will be the laughingstock of the next big war.

  • by formfeed (703859) on Sunday July 10, 2011 @06:35PM (#36714960)

    U.S. Team RoMeLa has swept Robocup 2011, winning first place in both the kid size and teen size divisions.

    And at the same time, the US women's soccer team advanced to the Semi final.
    I don't like where this is going, Sarah Connor::

    The US still sucks, except for robots and women.

  • This is very interesting work and the robots are very impressive... but shouldn't full-sized be at least... adult human sized? It seems rare to see projects with fully 6-foot-tall humanoids, I know it's a much greater challenge... but isn't that exactly why it should be done?

An Ada exception is when a routine gets in trouble and says 'Beam me up, Scotty'.

Working...