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."

Robotic fly catcher.

[el_womble]

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 :(

Re:The robot is all thumbs.

[Illserve]

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.

Shows just how powerfull the human brain is

[SlightOverdose]

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.

Re:Is the US lagging behind Japan?

[Mostly a lurker]

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.

Re:Idiot Land-speed Record

[isorox]

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.

Re:Sure, if it's thrown straight at it

[Morkano]

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.

Re:Robotic fly catcher.

[joelby]

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.

Re:Define catching...

[YrWrstNtmr]

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.

Re:Is the US lagging behind Japan?

[Guppy06]

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.

Re:Shows just how powerfull the human brain is

[TapeCutter]

"What are they planning?"

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