Slashdot Mirror


Robot Catches High Speed Objects

shpoffo writes "Engineers at the University of Tokyo in Japan have created a robot that can catch a ball moving faster than 186 miles per hour (300 kph) - more than 270 feet per second. It uses an array of photodetectors to directly control the three finger actuators - which can rotate 180 degrees in 0.1 seconds. It's only catching softballs at the moment, but operators are optimistic for it to soon catch other objects and grasp moving things. A video with odd sci-fi TV-series (coral cache) accents is available."

41 of 273 comments (clear)

  1. yeah but.... by Spoukie · · Score: 5, Funny

    can it catch a fly with chopsticks?

    1. Re:yeah but.... by ECramer · · Score: 2, Funny

      short answer: no

      long answer: noooooooooooo

  2. Sure, if it's thrown straight at it by paran0rmal · · Score: 3, Interesting

    I can't tell from the article and can't see the video (stupid firewall), but looking at the pictures it appears that the design only allows it to catch if the object is thrown straight at it, since it's just a hand. What would really be cool is if it was attached to a robotic arm that will move the hand to the right position to catch the ball.

    1. Re:Sure, if it's thrown straight at it by Morkano · · Score: 3, Insightful
      I can't tell from the article and can't see the video (stupid firewall), but looking at the pictures it appears that the design only allows it to catch if the object is thrown straight at it, since it's just a hand. What would really be cool is if it was attached to a robotic arm that will move the hand to the right position to catch the ball.
      All in good time. Having the arm without a hand capable of catching it once it's in position wouldn't be very helpful. One step at a time.
      --
      Victory or awesome!
    2. Re:Sure, if it's thrown straight at it by corngrower · · Score: 2, Interesting
      Having the arm without a hand capable of catching it once it's in position wouldn't be very helpful.


      Neither is having the hand without the being able to move and position it with an arm. The hard part is moving the hand in position to catch the ball. I'm not terribly impressed by just the hand alone, especially since they're still only using soft balls, like foam rubber balls. They're not even softballs, which aren't really all that soft, by the way.

  3. The robot is all thumbs. by mikeophile · · Score: 4, Interesting

    No, seriously, all three digits are opposable.

    It would be even nicer if it had an arm to intercept balls that weren't thrown precisely to it though.

    1. Re:The robot is all thumbs. by Illserve · · Score: 2, Insightful

      In theory the problem is no more difficult, just a bit more complicated in that now you need to do an arm. But once you've got motors that can react at this speed, the arm shouldn't be out of reach.

    2. Re:The robot is all thumbs. by Rick.C · · Score: 5, Funny
      It would be even nicer if it had an arm ...

      Well, since you're compiling a wish-list, let's not forget ... BREASTS!!

      --
      You were 80% angel, 10% demon. The rest was hard to explain. - Over The Rhine
      "Math in a song is good."-Linford
    3. Re:The robot is all thumbs. by gstoddart · · Score: 4, Funny
      It would be even nicer if it had an arm ...

      Well, since you're compiling a wish-list, let's not forget ... BREASTS!!

      I think we've all had our balls-busted enough to know that we don't need to put breasts on something which can catch balls at 300 km/hr.

      It wouldn't be long before we have a bunch of cranky, female-looking robots grabbing your parts at high-speed and little delicacy.

      Not a good combination. :-P
      --
      Lost at C:>. Found at C.
  4. Entertainment by DaSwing · · Score: 4, Funny

    Add a ball-throwing mechanism and you can watch two robots playing with eachother. If we are very lucky, humans won't have to have fun at all, we have robots for that.

    --
    11. Thou shall obey Da mighty Swing
  5. Is the US lagging behind Japan? by rolfwind · · Score: 4, Interesting

    I know the Japanese Robotic Mall Security guard was being made fun of here at /. but this is really cool - though it would be a nice step to see that hand attached to an arm attached to a humanoid robot who would actually have to go for the ball and not just have it thrown at it.

    But all the Robotic news seems to be coming out of Japan lately, is anything being done in the US that compares?

    Note: Not asking because I think the US should be in the lead but that it should compete for the benefit of all, definitely the US had the first industrial robot back in 1962 AFAIK:

    http://en.wikipedia.org/wiki/Industrial_robot

    And it's rather sad to think we're lagging in this on the R/D side in new frontiers. Unless this should be the extent of it:

    http://robots.engadget.com/entry/0657766019921755/

    1. Re:Is the US lagging behind Japan? by savuporo · · Score: 2, Informative

      Actually, robot revolution is also happening in China and Korea as well, but there's indeed very little in a way of practical accomplishments coming from west.

      http://plyojump.com/ has some in-depth info and couple good essays on these topics and why exactly this is happening. The core problem seems to lie in deeply rooted cultural issues

      Also check out Marshall Brain's ( the howstuffworks.com guy ) http://roboticnation.blogspot.com/ blog

      --
      http://validator.w3.org/check?uri=http%3A%2F%2Fwww.slashdot.org Errors found while checking this document as HTML5!
    2. Re:Is the US lagging behind Japan? by hackstraw · · Score: 4, Informative

      But all the Robotic news seems to be coming out of Japan lately, is anything being done in the US that compares?

      1 out of every 2 robots in the world are already in Japan. I guess they have a head start. Societies are different. We allow Mexicans to come into this country in lieu of robotic research. Japan has a much tighter immigration policy.

      No, this is not a slam against Mexicans. Its been said publicly by Bush that we like illegal aliens for cheap labor (maybe other Presidents as well).

    3. Re:Is the US lagging behind Japan? by Mostly+a+lurker · · Score: 2, Insightful
      Your Wikipedia reference provides a partial answer on why robotics R&D largely moved out of the US:
      Unimation had obtained patents in the United States but not in Japan
      While strong claims are made that patents encourage innovation, the reality, I believe, is the reverse. Invention thrives in an atmosphere of freedom, not one of bureaucratic control.
    4. Re:Is the US lagging behind Japan? by Guppy06 · · Score: 4, Insightful

      It's been suggested that the cotton gin failed to catch on until slavery was abolished in the United States. Slavery/serfdom/etc. has also been blamed for why nobody took Hiro's idea of a steam engine and ran with it until millenia later.

      On the one hand, we have recent event whittling away at the rights of both white- and blue-collar workers, from "no compete" contracts to laws allowing employers to prevent employees from fraternizing after working hours (at least accordin to Slashdot). On the other hand, we have overly zealous unions that can work to prevent employers from adopting technologies that would replace human workers (I've heard anecdotes of labor unions in the Port of Los Angeles fighting automation). Mix in a government giving US companies all the immigrant and offshoring opportunities they want, is it any surprise that the US is sliding behind in robotics in particular and technology in general?

      Technology only succeeds when it is cheaper to use than human labor, and human labor is pretty damned cheap in the US.

    5. Re:Is the US lagging behind Japan? by LoudMusic · · Score: 4, Funny

      We allow Mexicans to come into this country in lieu of robotic research. Japan has a much tighter immigration policy.

      They also have a moat the size of an ocean ...

      --
      No sig for you. YOU GET NO SIG!
  6. Re:Soon: pick-pocketing robots by SimilarityEngine · · Score: 2, Informative

    Too late! There is already a card trick performing robot!

    --
    Those who can make you believe absurdities can make you commit atrocities. - Voltaire
  7. Robotic fly catcher. by el_womble · · Score: 3, Insightful

    Am I missing something or does this work something similar to the lines of a fly catcher plant? Something is in my reach -> grab. All that is happening is that they have developed motors and photosensors fast enough so that they can do it at incredible speeds.

    The reality is that the robot has no idea what its catching. It doesn't know how to recognise a ball. The chances are that a fast moving object is easier to identify that a stationary one, as you just grab the thing that is moving rather than identifying a shape and deciding if that is the thing you want to collect.

    Still an interesting technology showcase, but I'm still no closer to my robot slave :(

    --
    Scared of flying, pointy things snce 1979!
    1. Re:Robotic fly catcher. by joelby · · Score: 2, Insightful

      Bear in mind that the carnivorous plants you're thinking about don't actively track and catch insects, but rather attract them with sweet excretions and close up like a trap when "trigger hairs" are touched. A plant doesn't really have any effective way to detect that insects are simply nearby.

  8. Excellent for the Space program by mrRay720 · · Score: 4, Funny

    1) Make them big
    2) One of these on Earth
    3) One of these on the Moon
    4) Make big ball-shaped transport vessels.
    5) SPACE PROFIT!

    Certainly a lot better than crappy shuttles that are critically damaged by bloody foam insulation.

  9. Re:High speed moving objects?! by beef3k · · Score: 2, Funny

    What do you mean? A hard boiled or a raw egg?

    Huh? I-- I don't know that! Auuuuuuuugh!

  10. Fast controled motion robotic by La+Gris · · Score: 3, Interesting

    The most interresting part here is, this robot fingers can rotate and stay in precise contrôl very fast.

    As mentioned, there is no arm and the area for interception is very tight. Building an arm mounted interceptor may raise serious problems with inertia though.

    Time to think of a robotized pickpocket.

    --
    Léa Gris
  11. Define catching... by fruey · · Score: 4, Interesting

    Picking up an imprecise, reasonably fast throw to a particular area doesn't need catching ability : think of those coin collectors on toll gates which are just a funnel down to a small coin slot.

    "The system is yet not sturdy enough to catch a real baseball and was only tested with soft balls. But, in other tests, it proved adept at grasping objects of various shapes, including cylinders."

    So it's really a display of fast reacting robotic actuators and a pretty cool photo detection in order to time the reaction correctly. As the guy quoted in the article says "It's an engineering feat really"

    Real catching, in my opinion, can only be acheived if you can follow through with your hands to "take the speed off the ball" at least for hard objects. I think that a fast moving real baseball would be incredibly hard to catch robotically. A mitt is really useful because it allows the momentum to be absorbed into a wide area. In cricket, all fielders know they have to bring the ball in to their chest or follow its trajectory after catching impact to not lose the ball - they don't have a mitt. This robot couldn't catch a moving hardball no matter how fast its actuators are, because the kinetic energy has to be disspated properly, and with a heavy ball this energy is very high.

    Pretty cool demo though. I think its applications will be rather more in the picking up of (reasonably slow) moving objects realm than any useful rôle in catching. If you want to catch soft balls all day long might as well just breed dogs.

    --
    Conversion Rate Optimisation French / English consultant
    1. Re:Define catching... by Illserve · · Score: 2, Interesting

      "Real catching, in my opinion, can only be acheived if you can follow through with your hands to "take the speed off the ball" at least for hard objects. "

      There's nothing that is fundamental about the way humans catch. We happen to use hand motion to absorb speed absent a glove, but all that's required to catch is that you absorb the energy somehow. A robot arm could do it just by being tough enough to take the hit.

      "I think that a fast moving real baseball would be incredibly hard to catch robotically."

      It would be hardER because it has no spongy give and would bounce off the palm of the hand if not caught precisely.

      But it can be caught precisely.

    2. Re:Define catching... by YrWrstNtmr · · Score: 2, Insightful
      Real catching, in my opinion, can only be acheived if you can follow through with your hands to "take the speed off the ball"

      A human has to do that due to the limitations of the hand and arm. Catching a ball thrown hard enough might well break your wrist. A suitably constructed robot would have no such structural limitations.

      A mitt is really useful because it allows the momentum to be absorbed into a wide area.

      And you (nor I) cannot catch a ball, thrown directly at you, at 1/2 the speed that this robot can, without one. Ok....maybe once or twice. Try it all day as a catcher at a baseball game, and eventually you'll slip and break a finger.

      Think of weightlifting. An Olympic class weightlifter can do maybe 1000 lbs. A robotic forklift can do 10,000 or 100,000 lbs, all day long, without even trying.

      So this is a limited tech display. The photo detection and actuator designs may well find themselves in something else. Something more useful.

  12. Missile Defense by Skip1952 · · Score: 2, Funny

    Wow this is great! Has anybody told the Ballistic Missile Defense Agency? Maybe they'll have more luck catching a missile than shooting it down!

    --
    == Shipwrecked and comatose
  13. Shows just how powerfull the human brain is by SlightOverdose · · Score: 3, Insightful

    Watching this made me think about the calculations involved in estimating the trajectory and how well the human brain does it.

    While the raw maths is pretty simple by itself, when you factor in stereo image processing to see a ball, work out it's speed and trajectory, and move potentially hundreds of muscles into the correct position to catch the ball, you realise just how powerful the human brain is and how well it can adapt.

    1. Re:Shows just how powerfull the human brain is by Kombat · · Score: 3, Informative

      Watching this made me think about the calculations involved in estimating the trajectory and how well the human brain does it.

      There's an old saying in computer science that one of my professor's passed on to me in my undergraduate studies: "Things that humans find hard, computers find easy, and things that humans find easy, computers find hard."

      It really rings true when you think about things like factoring polynomials, solving differential equations, and catching a ball. I thought it was interesting, and the saying has stuck with me all these years.

      --
      Like woodworking? Build your own picture frames.
    2. Re:Shows just how powerfull the human brain is by SlightOverdose · · Score: 2, Interesting

      Smaller animal, less distance between brain and muscles, faster reactions.

    3. Re:Shows just how powerfull the human brain is by TapeCutter · · Score: 2, Insightful

      "What are they planning?"

      They don't plan they just "do", that's what makes them great catchers, nobody told them about the math.

      --
      And did you exchange a walk on part in the war for a lead role in a cage? - Pink Floyd.
  14. Re:High speed moving objects?! by The+Grassy+Knoll · · Score: 2, Interesting

    Well to catch, say, a cricket ball, you need a certain amount of "give" when you make contact, otherwise it just bounces off your hand and out, and you've dropped it. Presumably, you just need to up the amount of "give" to catch something fragile?

    I don't know how hard a softball (sic) is, but a cricket ball is solid cork wrapped in leather. And I have the bruises this morning to prove it, after playing at the weekend...

    .

    --
    They will never know the simple pleasure of a monkey knife fight
  15. Yankees by GPLDAN · · Score: 2, Funny

    Steinbrenner has already optioned the contract on the robot for 2008. Apparently, he likes it because you can scream at it all day long and it doesn't get upset.

  16. Re:Just for once? by aussie_a · · Score: 4, Funny

    When the revolution comes people like you will be the first against the wall.

  17. Re:Idiot Land-speed Record by isorox · · Score: 2, Insightful

    collectively agreed to limit motorcycle's max speed to 300 kph (186.411 mph)

    I know the imperialists always convert from mph to kph in this manner when telling us of the superiority of the imperial system that their imperial overlords insist on, however do we really have to stoop so low as to give the speed to 6 s.f.? Do we really think the limiters are accurate to less than one thousandth of a percent? That's like saying a running track is length-accurate to about the thickness of you fingernail.

  18. Robocop 2 by nherm · · Score: 2, Interesting

    Cue that scene where Robocop catches a bullet fired to a police.

    I've always wondered about the real physics of that scene, maybe robocop's fingers would be destroyed, or the bullet deformed... all that kinetic energy has to go somewhere...

    Ok, back to work.

  19. Non-linear equations by pfafrich · · Score: 4, Interesting

    In the video, the ball has a very visible parabolic flight curve over the 2 meters distance.

    The parabolic flight curve actually makes this a harder task. If the equations of motion were purely linear, then it would be a simple task to calculate future position. The second order nature of the trajectory mean that a little more maths is needed to predict where to catch it. Much of the maths for this sort of thing uses matrices (read linear algebra) which would fall over for this task.

    I seem to recall that human cricketers use a simple technique for solving this problem. As they are running to catch the ball they move so the ball is kept at a constant angle in their field of view. Keeping this angle constant ensures that the ball will neatly arrive in their hands. Or so the theory goes.

    I've long thought that catching a ball would be a great research project, mainly due to the quadratics calculations involved, great to see it realised.

    --
    There are four sorts of people in the world: fools, lunatics, idiots and morons. - Umberto Eco, Foucaut's pendulum.
    1. Re:Non-linear equations by pfafrich · · Score: 2, Interesting
      Sorry to burst your bubble, but figuring out the trajectory of a ballistic object was figured out long, long ago. Just because an equation is quadratic doesn't mean it's very hard to solve

      I should explain why this hard to solve in a machine learning context. Whilst I agree that quadratics eqns have long had explicit solutions this may not be relevant if you use a machine learning approach. For current AI the game is not to program in the explicit equations themselves, but more construct a system in which the machine can learn through trial and error, using a positive feedback mechanism such as neural networks. Most of the work I saw in this domain five years back, when I was working in the field, used a strictly linear approach so would fail here. It is an interesting computational challenge to have a system which can "learn" the equations of motion.

      I mean, if you consider that a ballistic trajectory in a vacuum in a uniform gravitational field (such as experienced to a good approximation by a ball thrown across the surface of the Earth at reasonable speeds) is completely determined by the just three parameters (position, velocity, and gravitational acceleration)

      But in reality we are not working in a vacuum, as well as these effects we also have viscosity, wind resistance, and wind to take into account. Strict adherence to a quadratic equation would fail every time. In some respects having a fast moving ball makes the computational question easier as there is less contribution for these effects, it does make it more of an engineering challenge though. I'd actually be more impressed by a slow moving ball with lots of spin on it over a greater distance.

      --
      There are four sorts of people in the world: fools, lunatics, idiots and morons. - Umberto Eco, Foucaut's pendulum.
  20. Re:SI, damn it! by Smidge204 · · Score: 2, Funny

    "186 miles per hour (300 kph) - more than 270 feet per second."

    Or 499,968.9936 furlongs per fortnight, if that helps you put things into perspective...

    =Smidge=

  21. Re:High speed moving objects?! by sstoops86 · · Score: 2, Informative

    Actually, if you'd look through all the videos on the site, it DOES catch an egg, uncooked, unfrozen. They just have it wrapped in saran wrap in case it breaks, so it doesn't ruin the robot arm. I found that video last friday.

  22. Screw the robot... by xENoLocO · · Score: 2, Funny

    Screw the robot... how do you launch a softball at 190mph? I believe that has a more useful application.

    --
    "The need to build the internet comes from something inside us, something programmed... something we can't resist."
  23. That's a robot? by Call+Me+Black+Cloud · · Score: 2, Interesting


    It seems to me that's pushing the definition of robot a bit much. It's a grabber that closes when something approaches it. The ball is thrown straight at it. It seems more like the doors at the supermarket that open when you approach. Of course, the doors won't open fast enough for people moving at 186 mph but it's the same general principle.

    The impressive thing about all this is that I was able to download the 9+MB video, first try, using the link on Slashdot's front page, in about 15 seconds. Now that's technology!

    Wake me when someone builds a working pusher robot...don't bother me with this "hand robot" jibber jabber.