News: A robot that demostrates self-awareness

Discussion in 'Intelligence & Machines' started by identityless, Dec 27, 2005.

Thread Status:
Not open for further replies.
  1. identityless Registered Senior Member


    Robot Demonstrates Self Awareness

    Tracy Staedter, Discovery News | December 23 2005

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

    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.

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

    Under development by Junichi Takeno and a team of researchers at Meiji University in Japan, the robot represents a big step toward developing self-aware robots and in understanding and modeling human self-consciousness.

    "In humans, consciousness is basically a state in which the behavior of the self and another is understood," said Takeno.

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

    To mimic this dynamic, a robot needs a common area in its neural network that is able to process information on both cognition and behavior.

    Takeno and his colleagues built the robot with blue, red or green LEDs connected to artificial neurons in the region that light up when different information is being processed, based on the robot's behavior.

    "The innovative part is the independent nodes in the hierarchical levels that can be linked and activated," said Thomas Bock of the Technical University of Munich in Germany.

    For example, two red diodes illuminate when the robot is performing behavior it considers its own, two green bulbs light up when the robot acknowledges behavior being performed by the other.

    One blue LED flashes when the robot is both recognizing behavior in another robot and imitating it.

    Imitation, said Takeno, is an act that requires both seeing a behavior in another and instantly transferring it to oneself and is the best evidence of consciousness.

    In one experiment, a robot representing the "self" was paired with an identical robot representing the "other."

    When the self robot moved forward, stopped or backed up, the other robot did the same. The pattern of neurons firing and the subsequent flashes of blue light indicated that the self robot understood that the other robot was imitating its behavior.

    In another experiment, the researchers placed the self robot in front of a mirror.

    In this case, the self robot and the reflection (something it could interpret as another robot) moved forward and back at the same time. Although the blue lights fired, they did so less frequently than in other experiments.

    In fact, 70 percent of the time, the robot understood that the mirror image was itself. Takeno's goal is to reach 100 percent in the coming year.
  2. Google AdSense Guest Advertisement

    to hide all adverts.
  3. android nothing human inside Registered Senior Member

    In other news, today I developed a robot that will smell its own finger after pulling it out of its ass.
  4. Google AdSense Guest Advertisement

    to hide all adverts.
  5. kazbadan Registered Senior Member

    Amazing news! Do you think that this can be considered self awareness? Do u think that is some kind of self conscience? Maybe in a bug level?
  6. Google AdSense Guest Advertisement

    to hide all adverts.
  7. Qorl Guest

    We all are, in a way robots. I am Citroen C 4.
    Last edited by a moderator: Jan 10, 2006
  8. Anomalous Banned Banned

    Nope its a trick , a marketing gimmick i guess.

    All the robot has to do to reconnize itself from a mirror is to simply reflect specific pulses of waves, now how does that result into awarness ? anyways face recognition was created long time back.

    Now I did not read the news, I hope I am wrong, I am looking forward to something like shown in I ROBOT.
  9. RoyLennigan Registered Senior Member

    awareness is anything that relays stored information (or stimuli) from the past to present information, and uses that to manipulate the world. it doesn't matter if we consider it 'alive' or not.
  10. EmptyForceOfChi Banned Banned


    well am i missing something here, would somebody explain to me how that thing is conscious and has self awareness,

    i did read it but still does that classify as consciousness?

    seriously i dont get it, i understand what was said, but do not understand how that classes as conscious,

    is your home security alarm system conscious?.

  11. Anomalous Banned Banned

    Should have urge to prapogate and must have an ego.
  12. Qorl Guest

    Is on avatar your picture?
  13. river-wind Valued Senior Member

    Without having any real detailed information about how the system works, it does sound to me like the robot is just designed to pass the "recognize mirror image as self" test that animal behaviorists use to determine if individuals are self-aware.

    As a programmer, it would be easy enough to include a couple IF statements into an image recognition SW to use the order and timing of the blinking lights they are using for feedback as a way to identify an image as "self".

    There'd be no awareness there, only a sub clause in a logical algorithm. I'd need to see this test passed w/o hard-coded self-identification routines included before I'd call it really aware.
  14. Spectrum Registered Senior Member

    Nice try!
  15. daktaklakpak God is irrelevant! Registered Senior Member

  16. Pete It's not rocket surgery Registered Senior Member

    Hmmm.... What about your own hard-coded self-identification routines? Do they imply that you are not really aware?
  17. weed_eater_guy It ain't broke, don't fix it! Registered Senior Member

    why not let it code itself? humans start with inate learning, and absorb from there. we;d just need to give the starting points (for a human, that would be the desire for food, breathing, fear of fire, etc etc.), and let the artificial mind go it from there.
  18. Hipparchia Registered Senior Member

    I think you have to consider that the researchers are using the words 'self aware' in a very specific, constrained way. It is not the same thing as you mean by self aware. They are certainly not claiming consciousness for this robot. They have, as I understand it, mimiced the kind of circuitry in humans that relates to self awareness. It's as if they have taken one piece of the puzzle and put it in place. We still can't see what the picture is.
  19. Pete It's not rocket surgery Registered Senior Member

    I think that there are those who certainly would claim consciousness for it.

    What is consciousness, anyway? How do you tell if something is conscious or not?
  20. Hipparchia Registered Senior Member

    You are saying the researchers are claiming consciousness? That was definitely not my impression. If someone other than the researchers whose project it is claim consciousness, that is really irrelevant.
  21. Pete It's not rocket surgery Registered Senior Member

    Doyou think? If a researcher cloned an animal then claimed the clone was not conscious in order to use it for inethical practices, do you think that claims of consciousness by others would be relevant?
  22. Hipparchia Registered Senior Member

    Inflated, disconnected, irrelevant analogy. Stop changing the subject (and the subjective).
  23. Pete It's not rocket surgery Registered Senior Member

    The best threads are those with meandering subjects, I think.
Thread Status:
Not open for further replies.

Share This Page