Slashdot Mirror
Robots Aim To Top Humans At Air Hockey
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."
I won't be worried until computers start to beat us at bear pong.
Show me a robot that can beat humans at real hockey. Then I'll be impressed.
I read the article, and it didn't mention how physically strong the robot was. I bet even the best human players would have a hard time stopping a puck traveling in excess of 250 MPH.
Bender: Now, Wireless Joe Jackson, there was a blern-hitting machine.
Leela: Exactly. He was a machine designed to hit blerns.
I for one welcome our new Air Hockey dominating overlords!
All I can say is:
"Good shot"
"Nine times out of ten, starting a fire is not the best way to solve the problem." - my wife
I refuse to be impressed.
I can create a 2 bit air hockey robot that will lose to everyone but Butters!
every day http://en.wikipedia.org/wiki/Special:Random
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.
alias possession='chmod 666 satan && ls
This must be one of the best ways to get a research grant to pay for an air hockey table I've ever heard.
I Need someone to rebuild a Digitech Digital Delay pedal for me....for me...for me...for me.
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"
VLC FOR MAC IS DYING! IF YOU DEVELOP, PLEASE SAVE IT!!
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 at pure abstract thinking.
--
It is all in the sig. The rest is just window dressing
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.
A post a day keeps productivity at bay.
And the video they post is like watching a slideshow!
I'd like to congratulate the genius who chose to shoot fast-action footage on an unmounted low-quality camera. It reminds me of some UFO footage I've seen.
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.)
Welcome to the Panopticon. Used to be a prison, now it's your home.
I'm not impressed. Despite years of playing supposedly hand-eye-coordination improving video games, I'm still better equipped at writing an algorithm to play air hockey than I am at actually doing it.
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?)
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!"
Get puck position Get puck position Get puck vector Repeat
Eat sleep die
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 input sensor data, since this is a slightly odd application for ths controller.
as an aside, the automation and control business is still a growing market, and they can never find enough engineers. Many of these jobs involve high travel if you're into that sort of thing.
Even those who arrange and design shrubberies are under considerable economic stress at this period in history.
Air hockey is only the start to robots domination of our world!
that wants to beat humans at air guitar. Then I'll be impressed.
"Kill 'em all and let Root sort 'em out"
I for one welcome our new air-hockey playing robotic overlords.
(There, somebody said it.)
That's all the robots need...
-- I really need to bleed off some of this
That's a great idea. I am picking my masters in mechatronics thesis. Does anybody have any similar ideas.
G
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!
Anyone have the time to make one out of an inkjet printer and a webcam?
This explains why I could always win when I played the computer on my Nintendo, but always lost when I played my Pentium desktop.
The real battleground will be 16-bit, I guess. Warm up that old Sega Genesis.
One might ask the same about birds. What ARE birds? We just don't know.
I challenge our new "Robot Air Hockey Overlords" to a duel! I am yet to be defeated at a game of air hockey on a regulation size table.
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 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.
Air hockey: It's mostly about physical speed. [sarcasm]Shockingly, machines are faster than people.[/sarcasm]
Facial Recognition: We win, and I'd wager we will for a while. Machines still get fooled by magazine covers. Next up, multiple cameras for 3D recognition! Foiled by a mannequin head or some random person paid to pose for the cameras.
Sex: I'm pretty sure we're still better at it. Sure, you can get some machines to give you an orgasm, but I don't think there are very many people that wouldn't rather go for a roll in the hay with a real person.
Question everything
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.
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.
What what? In the butt.
Then, the world.
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.
Don't fight for your country, if your country does not fight for you.
Guitar Hero! :-)
Build a robot that plays Guitar Hero (yes, by actually watching the TV and physically manipulating the guitar). You'll get practice in machine vision, compensating for the variable delays in the screen-to-sensor-to-actuator-to-guitar links, and to finance the project, you can sell saved games with 100% perfect on every song
Work out a novel locomotion technique
We've seen wheeled, tracked, and legged robots. Flying robots and swimming robots are coming along. And then there was the snake-bot. But there are a number of other locomotion techniques in nature that haven't been reduced to practice yet, as far as I know. Elastic jumping, like a Flea uses, would be one. Or maybe brachiation, like the tree-dwelling primates. I've never seen a robot that burrows through the ground, but that'd probably be a useful tool, actually.
http://en.wikipedia.org/wiki/Terrestrial_locomotion
http://en.wikipedia.org/wiki/Robot_locomotion
...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!
and I will spank that robotic ASS!
Love,
The Foosball Wizard
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.
That's me!
Machines are cold and calculating. Humans have the advantage of chaos and stupidity which will occasionally help them win. Now only when government contractors develop a machine with armour and machine guns to mimic this same idea { lasers a plus } will this be the end of us feeble humans...
my UID is Prime. It makes me special.
All you have to do is remove the energy souce of the computer and you can beat it every time.
Seriously, though, there isn't much difference between this and letting a computer fly us to the moon. Give a computer and a human a confined set of parameters and rules and the computer can, with the right programming, consistantly perform at a higher level. Add any unforseen elements to the situation and the human can learn and adjust. Computers just can't do that as they are limited by their creators, and I don't see them being able to do that any time in the near future. For example, I wonder what would happen if something was added to the Air Hockey table that sped up or slowed down the puck in certain sections (i.e. spilt cola or oil).
What is cool is the advancement in video recognition.
David
I suspect there are another 32 bits hidden away and the robot will strike out with 64 bits of pucking power if provoked.
I doubt the robots would have had anything left to beat after the grizzly was done. Or do you claim the robot would be faster?
I think the real question is whether a robot can beat a grizzly at beating a human.
Shachar
"My computer beat me at chess. But then I beat it at kickboxing." --Dmitri Martin
I object to that article, and to the next reply.
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 output that showed the program at its best, and readers would invariably only remember the haiku that they thought was quirkily amazing rather than the ones which were merely nonsense.)
The best one, and we're working across a few years of my deteriorating memory and a language gap here, came out something like:
Late spring morning,
Flower petals sprinkling from sakura,
A flock of pink cranes.
People who read that go "Wow! The computer knew that sakura blossoms and crane both fly, and that using the cranes as a metaphor for the sakura would combine gracefulness with aesthetic sensibilities!" The computer knew no such thing -- it picked 3 nouns from a list of "approved words for traditional haiku which deal with $RANDOM_SEASON", then did a bit of sentence-pattern plug-and-chug to stitch them together. Its the human reading the poem who paints the mental picture that makes it all work.
Abstract art is similar: given that art critics will write stories about the deep meaning in pain dribbled onto a piece of paper from a cheese grater, it is not difficult to make the CheezeGratezor2009. All the hard work gets done by the art critic, not the painter.
Help poke pirates in the eyepatch, arr.
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
i like this
...we're still better at Bulletball(TM).
The human lost because the game was only going at 4fps.
Robot AI has come a long way since the toaster!
Its too bad that they cant invent a robot that can take more than 2 FPS on a video. Who shows off an invention or design with that crappy of a video?
you insensitive clod...
"Kill 'em all and let Root sort 'em out"
yeah, it's called 'me'.
composition | performance | education | music
After seeing what missile systems are capable of I fail to be impressed by new tracking systems like this.
The only stable state is the one in which all men are equal before the
Its not "Robots Aim To Top Humans At Air Hockey" it should be "Freaky researcher wants to make Robots Aim To Top Humans At Air Hockey"