Forgot your password?
typodupeerror
Robotics Technology

Robot Catches High Speed Objects 273

Posted by Zonk
from the voom dept.
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."
This discussion has been archived. No new comments can be posted.

Robot Catches High Speed Objects

Comments Filter:
  • by Spoukie (775267) on Monday August 08, 2005 @06:31AM (#13268088)
    can it catch a fly with chopsticks?
    • by ECramer (905950)
      short answer: no

      long answer: noooooooooooo
    • Ah, beginner's luck [imdb.com].
    • In the video, the robotic hand is catching the ball with its fingertips, which to a human would be an incredibly difficult thing to do -- akin to catching a fly with chopsticks. A human would wait until the object being caught is somewhat within the opened hand before grasping and making the catch, which is probably more secure. However, I can certainly understand the need to catch the ball BEFORE it impacts the visual sensors in the palm of the robot hand.

      Also, the idea of putting the sensors in the hand i
  • by paran0rmal (799476) on Monday August 08, 2005 @06:34AM (#13268100)
    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.
    • The hand is fixed in place so yes for this prototype you have to 'throw' the ball close enough to the hand for it to catch it with it's fingers.I believe they want to use it as a demo of the speed and accuracy of the technology, it is quite impressive.

      We already have bowling robots, now we have a catching hand, just need to build the 'battathon 2000' and England may have a chance in the next test :)
    • 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.

      • 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.

  • by mikeophile (647318) on Monday August 08, 2005 @06:36AM (#13268103)
    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.

  • by DaSwing (902297) on Monday August 08, 2005 @06:37AM (#13268105)
    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.
  • by rolfwind (528248) on Monday August 08, 2005 @06:45AM (#13268130)
    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 [wikipedia.org]

    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/ [engadget.com]
    • 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/ [plyojump.com] has some in-depth info and couple good essays [plyojump.com] 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/ [blogspot.com] blog
    • by hackstraw (262471) * on Monday August 08, 2005 @07:30AM (#13268249)
      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).
      • Now that you put the inmigration problem to afloat, I want to state a quote when talking with some rand() friend about the inmigration problem, he said something like this:

        "the illegal Mexican to US inmigration problem is not a problem of Mexican government, for Mexico, after Petrolium, inmigrants is the second biggest source of income so it is a 'great buisness', the problem is in the USA and that it allows the inmigrants to go/work there. It is the USA government who needs to enforce its inmigration laws
      • by Guppy06 (410832) on Monday August 08, 2005 @09:42AM (#13268861)
        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.
        • 's why the ancient greeks, egyptians and chinese never had an industrial revolution. All the knowledge was there, but due to the cheap slavery available, there was never any need for it to be put together in a way that spawned the industrial age.

          Neccessity /is/ the mother of invention.
      • by LoudMusic (199347) on Monday August 08, 2005 @10:15AM (#13269078)
        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 ...
    • 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.
      • I am not strickly against patents and copyright, but I do feel they go entirely the wrong way. They shouldn't be getting extended but actually made shorter. Copyright maximium should be 25 years. Patent maximium should be around 5-7 years max for mechinical devices and 1-2 years max for information based devices.

    • Falling behind in (humanoid) robot technology would be a source of national shame. Haven't you ever watched anime or read manga?
  • by el_womble (779715) on Monday August 08, 2005 @06:50AM (#13268144) Homepage
    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 :(
    • Does your hand recognize a ball? Of course not, it's merely a tool used by your central control unit (brain) in order to catch what IT recognizes as a ball.

      Similarly, this is one small component of what will eventually be one hellaciously competent robotic assistant. Put two (or ten!) of these hands on the ends of 'Doc Oc' style semi-autonomous arms and watch the fur fly! I hope they're on our side.
    • The chances are that a fast moving object is easier to identify that a stationary one,

      I remember in IJCAI 2004 conference I attended to an invited where the person explained the difference in information between a still image and a moving image, IIRC, he showed first 1 still image, where as he said you have only pixels, and all you can attempt to do is a "edge detection" to recognize objects (playing with contrast/brightness/channels etc).

      After that he showed the next image in the collection and it showed
    • by joelby (800301)
      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.
  • by mrRay720 (874710) on Monday August 08, 2005 @06:53AM (#13268149)
    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.
  • Define catching... (Score:5, Interesting)

    by fruey (563914) on Monday August 08, 2005 @07:00AM (#13268172) Homepage Journal

    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.

    • by Illserve (56215)
      "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
    • 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 c

      • There's more to it than that really. I can catch a softball that's not thrown very hard with stiff hands. However, I still soften the catch, because it lessens the bounce of the ball off of my hand.

        The same technique is used by American football recievers. Soft hands, soft hands.
    • Man, I REALLY hate insidious comments like this.

      You're pretty coherent, offer a somewhat witty/smart comment, in a condescending, disparaging way.

      You complain about this not catching heavy thrown balls. You bitch about "I think its applications will be rather more in the picking up of (reasonably slow) moving objects realm than any useful rôle in catching.".

      Are you a geek at all? WTF are you doing here on this site?
      A normal nerd/geek/person who is interested in tech will immediatelt grasp that this te
  • Somewhat coincidentally, Japanese Motorcycle manufacturers have collectively agreed to limit motorcycle's max speed to 300 kph (186.411 mph) [wikipedia.org].

    Is there any chance such a contraption could be used to save some silly person's butt in case they decide to go that fast?

    • 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.
  • 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!
    • Damn you beat me to it!

      This was my first thought as well, clicked into the comments and searched for "missile." Cheers to the like-minded thought!

  • Robots will go to the ballpark to watch other robots playing baseball, while people sit at home playing computer games.

    But don't worry. The robots watching will be programmed to enjoy it.

  • by SlightOverdose (689181) on Monday August 08, 2005 @07:29AM (#13268248)
    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.
  • Yankees (Score:3, Funny)

    by GPLDAN (732269) on Monday August 08, 2005 @07:35AM (#13268264)
    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.
  • by Dunbal (464142)
    But the REAL question is, can it play football?

          What's up with all these Japanese "sports" robots anyway? I mean, I know their sports teams suck, but surely they can just do like the US and buy all the good foreign players (ducking...)
  • In this particular video it's certainly not going 186 mph. I think throwing a ball at 186 mph would be a bigger feat than this robot catching a slower ball. Kind of neat though.
  • Robocop 2 (Score:2, Interesting)

    by nherm (889807)

    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.

  • What some countries need are robotic fans that are programmed NOT to erupt in violent riots at the drop of a hat at every soccer game.

    (I say 'soccer for the benefit of the US readers, but I realize elsewhere in the world its called football.)
  • The future of tank's anti-missile defense. Robotic arm that sweeps grenades and missiles away...
  • Screw the robot... how do you launch a softball at 190mph? I believe that has a more useful application.
  • Just make a robotic batter and a robotic pitcher and we'll have everything we need for the first robotic blernball league!
  • That's a robot? (Score:3, Interesting)

    by Call Me Black Cloud (616282) on Monday August 08, 2005 @10:12AM (#13269059)

    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 [somethingawful.com]...don't bother me with this "hand robot" jibber jabber.
  • it is difficult conceive of ways that such a robot could be used today. "It's an engineering feat really

    Stealth [imdb.com]
  • I can't wait until there is an arm attached to the hand programed to catch softballs. There will be story about the first accident this arm caused when some intern ust happened to walk by the arm holding a softball and its photosensors noticed it. Bye bye hand...
  • Brilliant! I would like to thank the poster for using the coral cache link. This way we *all* get to see the video without crashing the server! (And no thinks to the "editors," who are too backwards to do it themselves, or god forbid - automate it)
  • wouldn't a bucket be a much simpler solution than the fingers? Fingers are good for being able to adapt to a wide variety of precision jobs - catching things at high speed seems like a specialized task better suited for a bucket.
  • So how long before they begin to be used in baseball games? The catcher's job is not a nice one, seems to be a good candidate for replacement by a robot.
  • If I was asked to build a device that could catch balls moving at high speed, I would want to call it Annette.

Say "twenty-three-skiddoo" to logout.

Working...