Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!


Forgot your password?
Robotics Science

Robot Demonstrates Self-awareness 362

shinyplasticbag writes "A new robot can recognize the difference between a mirror image of itself and another robot that looks just like it. ... The ground-breaking technology could eventually lead to robots able to express emotions."
This discussion has been archived. No new comments can be posted.

Robot Demonstrates Self-awareness

Comments Filter:
  • Mirroring Robots (Score:2, Insightful)

    by biocute ( 936687 )
    What I want to know is, if we build two of these robots, position them facing each other, and instruct one of them to mirror the other one (i.e. lift your left leg when his right leg is lifted), can the first one recognize someone is mirroring it?

    And can these robots still recognize their mirror selves if we secretly place a goatee on them?

    I believe one of the reasons why we can recognize ourselves is because we are told what a mirror is for, hence we are constantly updating our self image database. I'm pre
    • by rbarreira ( 836272 ) on Wednesday December 21, 2005 @10:37PM (#14314337) Homepage
      What I want to know is, if we build two of these robots, position them facing each other, and instruct one of them to mirror the other one (i.e. lift your left leg when his right leg is lifted), can the first one recognize someone is mirroring it?

      Maybe you could RTFA instead of striving for First Post ;)
    • by Yst ( 936212 ) on Wednesday December 21, 2005 @10:45PM (#14314383)
      Ah, so our task is as yet not accomplished.

      You see, poster, you, yourself are a robot precisely like the robot described in this article. In fact, you are the selfsame robot described therein. We've presented to you a Slashdot story about yourself and you've failed to realise that the story is in fact about you. And so the experiment fails.

      For our next experiment: determining a method for causing Slashdot editors to recognise a mirror image of a story they've already accepted only just hours prior.

    • Re:Mirroring Robots (Score:3, Interesting)

      by Kpau ( 621891 )
      That's odd.... when I look in a mirror I see some person that looks a lot like my dad in his younger days. My self-image function has not kept up with my actual appearance.... (not that I've become Gollum but I definitely can't be mistaken for the 20-something image stuck in my head).
    • Um. Question of logic.

      I give robot one the command mirror(theOtherRobot);

      Then I give the other robot the command mirror(theOtherRobot);

      Then get something to make an arm or leg move. Recursion much?
    • 'm pretty sure I'll get confused too if a cloned me standing in front of me.

      That's a joke, right? You do realise that you can see mirrors, not to mention the things behind you if you look at one?
  • by dada21 ( 163177 ) * <adam.dada@gmail.com> on Wednesday December 21, 2005 @10:34PM (#14314321) Homepage Journal
    The minute I read this commentary I thought of a way to do this: LEDs blinking randomly and being matched up by robots as their own. I read the article second, and guess what? That isn't how this works, but it seems similar. In fact, I think they should just put together a basic infrared (invisible) LED, make the robot blink it at a really complex pattern, and if it reads that blinking in a mirror, it not only knows that it is itself, but it also knows how far away it is. LEDs can transmit tens of thousands of cycles of on/off patterns, right? I guess another robot could read this LED, perform an act, and send the same message back, making the original robot believe it's looking in a mirror farther away, but there are ways to fix that (multiple LEDs at a set distance).

    I call shens on this self aware robot. Can you do that?

    Self awareness is more than seeing a pattern you know you are doing and realizing its you doing it. Self awareness to me means "I know I exist" not just "Hey! That's me!"

    Scientists reinvent the same wheel as always, and then say how it will save society. Reason? Finding investors/grants.
    • These christmas lights [komar.org] also do plenty of randomly blinking red, green, and blue lights. They certainly aren't self-aware. I call shens along with parent.
    • It isn't even "hey, that's me!" it's just "that's performing the same pattern as I am doing" (although the use of I would indicate self-awareness, I personally believe it's much more complex). It's programming would possibly allow a robot of a completely different configuration, that mirrors the pattern, to trick the robot into thinking it is a mirror image of itself.
    • Minsky sheds some light on this topic in his book The Emotion Machine, which is supposed to be published in January sometime if I recall. A draft is on his website, http://web.media.mit.edu/~minsky/ [mit.edu]
    • Ninja Bot (Score:2, Funny)

      by Phae ( 920315 )
      So all my ninja bot has to do is wear a bunch of mirrors and your robot could never see it! Sucker!
    • by commodoresloat ( 172735 ) on Wednesday December 21, 2005 @11:13PM (#14314531)
      I think the reference to self-awareness here is based on psychological understandings of self-awareness in human beings. Since Freud the understanding of human self-awareness has located the "mirror stage" as the key moment in child development, the point at which the child becomes aware of him/herself as an independent "self." Of course, the mistake here is to believe that the mirror stage itself is both a necessary and sufficient condition for self-awareness; it is for humans a necessary condition, but it is not a sufficient condition for any entity. Especially in this case, where the robots pass the mirror stage by what is essentially trickery in this context -- achieving not self-awareness but an ability to manifest a particular symptom of self-awareness.
      • by GenSolo ( 444636 ) on Wednesday December 21, 2005 @11:39PM (#14314666)
        I have to disagree that the mirror image is a necessary condition for humans. People who are born sightless still develop into self-aware adults. The recoginition of a mirror image as oneself is a key point at which the child demonstrates awareness and the ability to recognize said independent "self". Frankly, it's just a point where kids figure out that shiny objects reflect light and infer that the image in the mirror must be them. Self-awareness is a prerequisite.
        • Yeah you're quite right -- take it up with Freud :) It's not necessary to actually be able to see yourself in the mirror; self awareness is actually the necessary condition for the mirror stage to take place.

          • Freud isn't the last word in psychology any more than Newton was the last word in physics. His work was pioneering and insightful but the world has moved on since then, and some of his original research was flawed.

            As far as I'm concerned, this advance isn't anything near what the news entry makes it out to be. Just because it can recognize itself in a mirror doesn't mean it's self-aware. We can't even define consciousness, let alone measure it. Well, unless you use an arbitrary numerical value from 3-18, wi
        • The mirror example is only one why this condition can be manifest. The condition can be met with reference to sound, assuming a situation where hearing is the dominate sense. Its just a point where you recongize the difference between internal sound and external sounds. Self awareness is not special, it is exactly what is says, being aware that there is a self. How can that statement have any meaning unless there is some external stimuli that you are seperate from the rest of the world? Perhaps you are just
        • I agree 100% with GenSolo. For most of human history people didn't have mirrors. Yes, they could see themselves reflected in water, but how many people experience that as infants before becoming self aware?

          This experiment merely demonstrates that the robot can detect which of two images its movements affect. It certainly doesn't imply any awareness of what the image represents. If the robot were controlling a traffic light, that wouldn't imply that the robot had a sense of self which it associated with the
      • by Rob Carr ( 780861 ) on Wednesday December 21, 2005 @11:58PM (#14314771) Homepage Journal
        Being the owner of parrots, I have a question about this:

        Does the concept of "recognizing self by mirror" require the concept of "mirror?" If someone doesn't understand what a mirror does, then they may fail the test but actually be self-aware.

        Brain injury patients teach us that there are circuits in the brain for things we wouldn't expect. A stroke patient lost the concept of "left." She could only eat half of a piece of cake in front of her -- her brain wouldn't recognize the other half. She learned to turn the plate, so that a piece of cake would magically appear! Doing this several times, the cake was essentially consumed.

        If the concept of "left" can be lost, what about concept of "mirror?" A human may be capable of reasoning out that the person in the mirror must be me, but for creatures that are less intelligent, I'm not so sure.

        One of our smarter parrots does not seem to recognize herself in the mirror. She attacks the mirror image. A second parrot seems to understand the concept of "camera." I once connected a video camera directly to the TV and videotaped him -- he began to experiment with moving and watching the parrot on the TV move. All of a sudden, he began to show off and...strut. Ever since then, he shows off for cameras and struts when he sees a photo of himself. He won't strut when he sees a parrot of his own species that is not him. (Note: I don't know if he's cueing on backgrounds to tell if the parrot is him or if he can identify himself.) He's the only parrot in the house that doesn't like anacondas on Animal Planet. Raptors also upset him. Most parrots don't watch TV, the refresh rate is too slow. But somehow he does.

        I'd love to know how Alex the Parrot [alexfoundation.org] responds to "Who?" when looking at a mirror. One could start out by positioning the mirror so that someone else is visible, someone Alex could name. Then, by changing the angle of the mirror, have Alex look at Alex.

        • I have owned quite a few parrots, some seem to necer tire of attacking the mirror others are only curious for a short time then ignore or avoid mirrors. Parrots have a "personality", White Cockatoos look almost identical but up close their "personality" makes them easy to tell apart. Sure they may not be able to demonstrate self-awareness to a human, so what, can a human demonstrate unassisted flight to a Parrot?

          Even using broad definitions of "self-aware" that would include parrots, it is a mighty big c
    • I think everyone agrees this is little more than a rudimentary simulation of self-awareness. The $64,000 question, for any artificial life/intelligence, is: When, if ever, is a simulation no longer just a simulation? Is there a threshold, and if so, what is it?

      Are we not, to a large extent, just mimicking what we see around us, with varying degrees of accuracy and quasi-random implementations which we call "our own?"
      • "When, if ever, is a simulation no longer just a simulation?

        If we are talking about self-awareness as defined by mirrors and other human behaviour, lets just say humans will always want to feel special!

        (I belive) "Self" is a simulation of the real world (including the physical self) that has enough granuality to pick out the physical self. It is generated in humans by a "calcium pump computer" using the data from a network of trillions of nerve endings.

        The common threads amoung the many human simul
    • Exactly. But this is an important component of self-awareness; before, robots couldn't even distinguish between themselves and others. Without this distinction, self-awareness is impossible.
    • The minute I read this commentary I thought of a way to do this: LEDs blinking randomly and being matched up by robots as their own. I read the article second, and guess what? That isn't how this works, but it seems similar.

      If you consider lights and motion similar, sure. Recognizing the thing moving as the thing to imitate is much trickier than seeing a blinking light to blink after. We can imagine this robot would not blindly follow a rolling ball, for example, because it "knows" what it looks like an

  • Not Self Awareness (Score:5, Insightful)

    by MikeWasHere05 ( 900478 ) on Wednesday December 21, 2005 @10:35PM (#14314322)
    This isn't really self-awareness, just some good vision techniques. It recognizes key features of it's "face" compared to the normal face. Reminds me of the kind of things they use in face-recognition for security.
  • by civman2 ( 773494 ) on Wednesday December 21, 2005 @10:35PM (#14314323) Homepage
    I don't think being able to tell the difference between a reflection and not a reflection makes a robot self aware. True self awareness comes when a robot can actually think and communicate in ways it wasn't originally programmed to.
    • then you are not self-aware either. you have your programming, and it includes the capacity to learn. what is happening here is a robot is able to recognize that it's own actions are occuring in front of it. even though it's a simple binary true that recognition is no minor thing. is it good enough? of course not, but that's true of a lot of first generation ideas.
    • Actually true self-awareness can be more simply defined as awareness of oneself as a self -- you are describing intelligence, not self awareness, when you comment about "thinking and communicating in ways it wasn't programmed to."

      You're still right, the robots have not achieved self-awareness; all they've done is passed an artificial test of self-awareness (the ability to recognize oneself in a mirror). As others pointed out above, they do so by trickery rather than by knowledge of self. And as I poin

      • by TekPolitik ( 147802 ) on Thursday December 22, 2005 @12:24AM (#14314926) Journal
        You're still right, the robots have not achieved self-awareness

        There is a much deeper problem in the title than this. It is, quite simply, impossible for one being to prove its self-awareness to another. We may be able to make some sort of educated guess as to things being self-aware, but there is no way we can directly observe or experience the self-awareness of another being. This is by definition, since self-awareness is that recognition of one's own existence a a separate entity that is unique to and inseparable from that entity - it is not merely the reaction of the bio-machine to its environment no matter how complex and seemingly independent that reaction.

        The Star Trek TNG episode "The Measure of A Man [amazon.com]" gives a fairly good explanation of the problem. Even if we develop a non-biological machine that mimics in all respects the behaviour of a human, down to the finest of details, we will have no way of determining whether that machine is self-aware. A corollory of this is that we have no way of determining if any particular machine is not self-aware. You are probably fairly confident your computer is not self-aware, but just try proving it. If you think that you can prove something is, or is not, self-aware, then you have probably not understood the problem.

        • Now it gets interesting.. You cannot prove or disprove God either. Some people think it is possible, but as you say, then they have not understood the problem. We're not talking about a biblical God here, which might be anything from hysteria, aliens or propbably many different phenomena attributed to one "God". In the East, God is the Great Thinker, the Great Dreamer, the being which is everything that is, dreaming up all this creation. It is quite unfathomable, and of course totally unprovable by the drea
        • I'd been wondering if someone would bring this up. Myself, I cannot think of the question of artificial self-awareness without thinking of this episode.

          It would seem to me we equate "life" with "resembling human". We look at animals and attribute emotional states to them, because they at times resemble humans and human behavior. We cannot attribute these states to plants or insects or microscopic life because they bear absolutely no resemblance to us. The fact is, we know only ourselves--that each of us, i

      • No. Recognizing oneself in a mirror is not as you claim, a necessary condition for being self-aware. If it was, then all blind people would not be self-aware.

  • by scenestar ( 828656 ) on Wednesday December 21, 2005 @10:36PM (#14314332) Homepage Journal
    these things can easily be defeaten by stairs.
  • Amazing ! (Score:5, Insightful)

    by acaspis ( 799831 ) on Wednesday December 21, 2005 @10:42PM (#14314362)
    Most ridiculously overhyped slashdot headline ! Ever !
  • WHY!?!?! (Score:5, Funny)

    by DaFallus ( 805248 ) on Wednesday December 21, 2005 @10:42PM (#14314363)
    Why was I programmed to feel pain!!!
  • no i haven't rtfa (Score:2, Insightful)

    by jefe7777 ( 411081 )
    but my quick on the draw guess: it's the illusion of self-awareness.

    some day the illusion will be so good, we'll have some difficult questions to deal with...
  • by betasam ( 713798 ) <betasam@ g m a i l .com> on Wednesday December 21, 2005 @10:44PM (#14314373) Homepage Journal
    Demonstrating "Self Awareness" is one thing, but defining it is probably the first step. I don't think there is a commonly accepted definition for this. The ability of two perfectly identical twins (hypothetically) to distinguish themselves, IMO is not self awareness, that's self identification. If a robot can identify itself in a group photograph, standing besides several other model look-alikes accurately (I wonder how this could be done), then that is self identification. I have trouble identifying one chimp from another, but no trouble distinguishing one human from another, sometimes even identical twins. Humans can identify their dog from a group of dogs of the same breed as theirs - clearly that's not "self-awareness". The same can be said for other pets or those working closely with wild animals. I believe there should be a different term used here.
  • by iSeal ( 854481 ) on Wednesday December 21, 2005 @10:44PM (#14314374)
    Facial/Body/Robot Recognition != Self-Awareness.

    These are algorithms, pure and simple, and do not on themselves constitute a self-awareness. Self-awareness would be the robot suddenly talking about wanting beer, and pondering the logistics of whether drinking beer is worth the ensuing short-circuit.
  • Emotions? (Score:4, Funny)

    by Sexy Commando ( 612371 ) on Wednesday December 21, 2005 @10:45PM (#14314380) Journal
    The ground-breaking technology could eventually lead to robots able to express emotions.

    Bite my shiney metal ass.

  • Cool! Someday my kitten will be self aware.

  • by MORTAR_COMBAT! ( 589963 ) on Wednesday December 21, 2005 @10:47PM (#14314395)
    the question of whether a computer can think is no more interesting than whether a submarine can swim.

    Edsger Dijkstra [thinkexist.com]

    Now, before you dismiss it, he also said one of the great truths:

    The use of COBOL cripples the mind; its teaching should, therefore, be regarded as a criminal offense.
  • "A new robot can recognize the difference between a mirror image of itself and another robot that looks just like it. ... The ground-breaking technology could eventually lead to robots able to express emotions."

    My dog [flickr.com] sees herself in the mirror and thinks it's another dog. Then she expresses emotions to the other dog. Dogs are clearly way ahead of robots. You can buy a robot that vacuums the floor, but you won't find one that poops on the floor.
  • Definitions? (Score:5, Interesting)

    by lawpoop ( 604919 ) on Wednesday December 21, 2005 @10:59PM (#14314470) Homepage Journal
    Do the fields of AI or evolutionary psychology have any definitions of "self-awareness" or "consciousness"?

    I see a lot of stuff in the popular press about a robot or computer becoming aware, but everyone seems to totally ignore what exactly the definition is. How do we know that most people are aware? If I say that I know that I am aware, what exact claim am I making?

    I had a philosophy professor in college, Tom Kasulis, who studied Eastern and Western philosophy. He had a breakthrough moment when he went to study in a Zen Monastery. In order to enter, he had to do a 'pre-interview' with the abbot, a Zen Master. The master asked him, "What is Zen"? Kasulis mumbled somthing about it being a practice, not a belief. The Abott responded, "Zen is -- knowing one's self. It is the same undertaking that Western Philophers undertook."

    Kasulis taught my class about Hindu philosophy of the self or soul and the supersoul ( Atman and Brahman ). I thought some of it might be a useful high-level definition of self-awareness in AI. It goes something like this:

    Q. Are you aware?
    A. Yes.
    Q. Are you aware that you are aware?
    A. Yes.
    Q. Are you aware that you are aware that you are aware?
    A. Yes.
    Q. Are you aware that you are aware that you are aware...?

    So, you see it leads to a never ending chain of awareness. In Hindu philosophy, the ultimate awareness, the 'unseen see-er', the entire infinite chain of awareness, is the Atman, or the supersoul that transcends the individual.

    In the AI realm, we could build a machine that had two components: a perception system (vision, sound, whatever) and a detection-of-perception system ( a 'true' output if it percieves a system that can percieve ). Once the perception system falls on the system itself, it will detect a perception system. It will 'know' that it 'knows'. Then, it will detect another perception system in the original act of perception. Then, it will detect that act of perception, and in turn that act of perception... ad infinitum

    The self's perception of the self has this hall-of-mirrors quality that does not occur when the self perceives others of the same kind.

    You can take it one step futher and detect other self-aware systems if you can somehow detect this self-detection in other systems. However, I haven't figured out a logical argument for how to do this.

    I humbly submit my hall-of-mirrors definition of self-awareness. What does the Slashdot non-liberal arts majors make of it?
    • What?
    • Re:Definitions? (Score:5, Interesting)

      by FireballX301 ( 766274 ) on Wednesday December 21, 2005 @11:25PM (#14314596) Journal
      At a point, ask:

      'Are you aware this is an infinite loop, and if so can you stop it?'

      Once a computer can stop the loop recognizing that it is infinite, but also differentiate it between non-infinite loops through a single function, then they are self aware.

      I probably mangled it but here's the relevant link: http://en.wikipedia.org/wiki/Halting_problem [wikipedia.org]
    • by DrJimbo ( 594231 ) * on Wednesday December 21, 2005 @11:32PM (#14314631)
      You should really try to work through Raymond Smullyan's book "Forever Undecided: A Puzzle Guide to Godel".

      In it you would learn many very interesting things. One of the more trivial things you would learn is that once one is aware that one is aware, the infinite recursion comes along for free and is mostly a red herring. Smullyan explains Godel's Theorems mathematically and also in terms of "reasoners" reasoning about their own reasoning.

      IMO, Smullyan has a much deeper and more fundamental understanding of Godel's Theorems than Nagel and Newman who popularized them in their book "Godel's Proof". Unfortunately, Hofstadter got most of his intuition about Godel's proofs from Nagel and Newman so he has continued to propagate their limited understanding onto the masses.

      In a nutshell, Godel's Theorems deal with the mathematics of self-awareness.

      • I will get into the book that you recommend.

        "One of the more trivial things you would learn is that once one is aware that one is aware, the infinite recursion comes along for free and is mostly a red herring."

        I understand that the infinite recursion comes along for free, but can you elaborate as to why it is a red herring?
        • I think of the infinite recursion like a tv camera hooked up to a monitor and then pointed at the monitor so you get a picture of the picture of the picture ... It is a pretty little model but we don't learn very much from it.

          Another model I have of self-awareness is a detailed, animated map of a city, like something out of a Harry Potter movie that is so detailed it even shows the person holding the map and the very map itself.

          One question is: can something like this map exist? The answer is yes. Se

    • I have been thinking for a while that one of the interesting tricks of human intelligence is the ability to recognize and "tokenize" that infinite chain, essentially allowing us to conceive of the infinite. That sort of generic pattern recognition would seem fairly fundamental to a human-like artificial intelligence, but it's not here yet.

      The self-awareness "breakthrough" in question doesn't really seem to be anything of the sort, just some cheap hand-waving and trickery.

    • Kasulis taught my class about Hindu philosophy of the self or soul and the supersoul ( Atman and Brahman ). I thought some of it might be a useful high-level definition of self-awareness in AI. It goes something like this:

      Q. Are you aware? A. Yes. Q. Are you aware that you are aware? A. Yes. Q. Are you aware that you are aware that you are aware? A. Yes. Q. Are you aware that you are aware that you are aware...?

      I can get to 23 levels of awareness, but at that point, I'm not actually aware that I'm awar

    • Re:Definitions? (Score:3, Interesting)

      by Eivind ( 15695 )
      This all just sounds clever if you never stop to think about it, actually it's not clever at all.

      Your never-ending-chain is nothing more than a trivial game with language, exploiting the fact that humans are notoriously bad at de-nesting deeply recurcive expressions. Most people have a problem instantly parsing sentences like: "Do you know that I know that he knows that we know that Alice is actually a boy ?"

      I think that's basically due to our limited stack-size :-)).

      Your hall of mirrors definition al

  • by Master of Transhuman ( 597628 ) on Wednesday December 21, 2005 @11:06PM (#14314499) Homepage
    Since the exact technology (artifical neurons?) is not described in detail as to how they work, ascribing "self-awareness" to this experiment is "claiming too much."

    Also, use of the word "understanding" may be claiming too much in the absence of any evidence of conceptual processing in either the neurons or the software.

    Still, it's an interesting bit of work, which may prove useful if it can be extended.
  • A Single Bound (Score:2, Insightful)

    by mattwarden ( 699984 )

    A new robot can recognize the difference between a mirror image of itself and another robot that looks just like it.


    The ground-breaking technology could eventually lead to robots able to express emotions.

    Poster can leap farther than Superman!

  • by Belseth ( 835595 ) on Wednesday December 21, 2005 @11:08PM (#14314507)
    If you are trying to test for human behavior in a robot pour hot coffee on one. If it's first reaction is to call it's lawyer I think we have a winner.
  • Bull. (Score:3, Informative)

    by CyberVenom ( 697959 ) on Wednesday December 21, 2005 @11:16PM (#14314551)
    The complete program:

    while(1) {
    if(ovservation = sight.recent_movement()) {
      light['I see someone else'].flash();
    } else {
      wheels.move(int rand(2) - 1);
      if(sight.recent_movement()) {
       light['I see myself'].flash();
  • by Mr. Flibble ( 12943 ) on Wednesday December 21, 2005 @11:17PM (#14314556) Homepage
    Great, all we need now are robots looking in mirrors wondering if their butt is too big...

    Already got one of those thanks.
    • Re:your sig (Score:3, Funny)

      by Lehk228 ( 705449 )
      you may want to fix that link in your sig, it's going to an unpatched IIS 5 server and i just put sub7 on your computer
  • Robot recognizes self in mirror! Scientists jump gun! People astounded by misleading headlines! I mean *I* recognize myself in the mirror, and I've been told plenty of times that I don't know how to express or interpret emotions.
  • ... meh (Score:2, Interesting)

    by snark23 ( 122331 )
    Okay, so they've programmed a robot to understand mirrors... that's hardly the same as "self-awareness" in the sense of sentience or consciousness.

    The article isn't very descriptive, but it sounds like stupid pseudo-science:

    "This so-called mirror image cognition is based on artificial nerve cell groups built into the robot's computer brain
    that give it the ability to recognize itself and acknowledge others." ... what does that even mean?

    The real question is: was this robot programmed to recogn
  • I've seen self-awareness demonstrated in a seven line perl script.
  • by xineax ( 871580 ) on Wednesday December 21, 2005 @11:22PM (#14314583)
    I wish people would sit on their research for awhile sometimes and that readers of these articles wouldn't read into buzzwords like "self-awareness."

    1) What is consciousness?

    Takeno, oversimplifies the definition.

    2) Was the robot picking up on the fact that a mirror image is STILL corrupted information (which is remarkable in itself)?

    3) Consciousness works on many levels and may have biological primitives we just don't understand yet. Seems appropriate to call this anything but a robot with better programming--not "self-awareness."

    We'll have to wait it to see.

  • Humans learn behavior during cognition and conversely learn to think while behaving, said Takeno.


  • Sort of cool. (Score:3, Interesting)

    by BorgCopyeditor ( 590345 ) on Wednesday December 21, 2005 @11:27PM (#14314608)
    This robot's ability is not in itself very interesting. What is interesting, though, is the way that developing the ability to recognize one's own movements "from the outside," as in a mirror image, is an important stage in the development of self-consciousness.
  • by RJSIII ( 878585 ) on Wednesday December 21, 2005 @11:28PM (#14314611)
    First off, this is NOT a new robot. The robot pictured is a commercially available mobile robot called Khepera II [k-team.com]. These robots are fairly stupid, but are easily tethered to more capable machines via a 19200 baud serial link. Mostly, they're used in research (usually undergraduate) because there are whole hosts of Matlab libraries available to interface to these buggers.

    bot=kopen([0,19200,1]); % open a connection to tethered robot on /dev/ttyS0 at 19200 baud with one second timeout

    And so on and so forth. The Khepera robots have been available for many years, along with the k-team matlab resources. That aside, what the robot in question seems to be doing is using the Matlab Neural Network Toolbox to recognize and classify behavior by observation. Sorry folks, but kids at underfunded state schools [southernct.edu] do this as undergraduate work in AI. This is nothing new.
  • Did know one read I, Robot?
  • by Animats ( 122034 ) on Wednesday December 21, 2005 @11:33PM (#14314636) Homepage
    For the low, low price of only $15, you can read the published paper. [metapress.com]


    This paper presents a clear-cut definition of consciousness of humans, consciousness of self in particular. The definition "Consistency of cognition and behavior generates consciousness" explains almost all conscious behaviors of humans. A "consciousness system" was conceived based on this definition and actually constructed with recurrent neural networks. We succeeded in implementing imitation behavior, which we believe is closely related to consciousness, by applying the consciousness system to a robot.

    This belongs to the branch of AI informally known as "faking it". There's a long history of work in this area, starting with ELIZA and continuing through a long series of rather lame systems. The latest systems are intended to mimic the behavior of call center employees.

    Sadly, this isn't a joke.

    • Faking it accurately enough such that there is no distinguishable difference means that you have, in fact, achieved the goal of AI. So it's a worthwhile approach, IMO. Of course, we are miles away still.
  • by photon317 ( 208409 ) on Wednesday December 21, 2005 @11:37PM (#14314658)

    AI? Whatever. Among serious theorists, it is pretty widely accepted that we will never reach a goal of true, hard AI (as in, something we created which is truly every bit as smart, independant, creative and "alive" as us, or even more) by cobbling together algorithms like this. It will come about by building the right sort of neural-net building blocks, arranging them in roughly the right kind of networks (probably via genetic selection algorithms rather than manually), and then teaching it much in the way one raises and teaches a small child. That's *if* we can solve the huge problems that still lie in our way going down that path (not the least of which is raw processing power).

    This kind of shit isn't even in the right ballpark, and it's not going down the right road, and it's simply not productive in the long term. But gee, it gets headlines and research grants because it makes laymen say "ohhh neat". AI scientists of the world - I challenge you to get off your collective asses, stop pandering to morons, and get down to business with the decades of work that remain to be done.
    • Dead on. (Score:3, Insightful)

      by localman ( 111171 )
      Yeah, I'm tired by these flimsy pop-AI articles too. Your comment about teaching it like we teach a child is really the key, too. I think that most people are going in totally the wrong direction thinking about AI. People seem to think that intelligence is in the hardware, that if we built a "super brain" it would be super smart. But I don't think so: I think that we've already got "super brains" in our heads (in the sense that they blow away any hardware we've been able to concoct with all our high tec
  • ...am not Sarah Connor.
  • While it seems to be successful test of pattern recognition, calling this "self awareness" is really stretching the term and making it sound like something much more than it really is. This is more like "Likelihood of object three meters ahead being a mirror - 99%. Likelihood of visual feedback within object confines being reflection of this unit - 99.9%." If that robot experienced the spontaneous thought of "My hips look fat," or "Why do I look so ugly?", I'd be more inclined to think of this as a staggeri

  • all this means is some programmer taught a robot to remember its limb positions and reverse the coordinates for a mirror image and compare the two. how the heck is telling a robot "your arm is here, his is in a different position, therefore, you are not the same" lead to teaching a robot how to think "that girl-bot just flashed me, i almost short-circuited my-self" and "that sob just flipped me off and passed me on the freeway, I'm going to pointlessly blare my horn for an hour at him!"
  • By touching himself in fron ot the mirror
  • 1. Robot programmed to recognize itself in mirror
    2. ???
    1000000. ???
    1000001. Profit !
  • Semantic problem. (Score:3, Insightful)

    by blair1q ( 305137 ) on Thursday December 22, 2005 @12:18AM (#14314895) Journal
    That's not self-awareness, it's merely self-recognition.

    Or rather, it's an identification protocol sent through a loopback channel to a pattern-recognition processor mapping the local identifier value to the response methods associated with itself.
    • I was going to post this myself, but you hit it on the head. We can also assume the poster & editor have no idea about AI systems or ever read any science fiction stories as saying an AI is self-aware is the equivalent of saying, 'I have the cure for cancer' in the medical field. Or maybe it was a ploy to garner more interest in the article.
  • From TFA: "In humans, consciousness is basically a state in which the behavior of the self and another is understood," said Takeno.

    Umm, no. There are plenty of disagreements over the nature of consciousness, but this is just sillyness that not even a hard core analytic functionalist should care to defend. A good intro to the subject can be found in the (excellent) Stanford Encyclopedia of Philosophy. Stanfod Encyclopedia of Philosophy [stanford.edu]

  • "One more robot learns to be
    Something more than a machine
    When it tries the way it does
    Makes it seem like it can love

    'Cause its hard to say whats real
    When you dont know if you feel
    Is it wrong to think its love?
    When it tries the way it does."
  • It's actually a bit incomplete to say that there's anything special about a robot becoming self-aware.

    What makes it noteworthy that we humans are self-aware, is the fact that we discover this fact on our own. It is not a specific "function" of our species -- it's a realization that our developed brains allow us to achieve.

    If we program a robot to understand that it "exists," even if we program it to have a full understanding of what that means, it's not really significant.

    Being self-aware is a landmark achi
  • The ground-breaking technology could eventually lead to robots able to express emotions."

            and in other news, the dreidel could eventually lead to a perpetual motion machine...

        this seems like quite a leap from banal invention to extraordinary implementation
  • by l3v1 ( 787564 )
    This is nothing but a fairly stale story with a very ostentatious (what a word) title. What would any of you expect from any news source. I am by no means a psychologist, still for me, as someone fairly knowledgeable in computer vision and image processing, this story tells one thing: we are just as far away from real self-aware and intelligent [not as in a.i. algorithms and logic, but intelligent as in being able to learn, adapt, understand abstract concepts, reason, etc.] robots as yesterday or last week.
  • a mirror reflects the light that hits it.

    logic.... does mirror image move in accordance with movement of machine? True or false?

    If true, must mean self awareness?


    a rock is not self aware, no matter how much you configure its atomic structure to pass electrons in a logical path.

    This is more a play on human fantasy than hard reality.

    Guided missles are not self aware but find their target via a feedback loop that constantly corrects minor deviations from the terget.

    Fine tune that feedback to be under

The secret of success is sincerity. Once you can fake that, you've got it made. -- Jean Giraudoux