Slashdot Mirror

← Back to Stories (view on slashdot.org)

Swiss Experimenter Breeds Swarm Intelligence

Posted by kdawson on from the what-hath-ai-wroght dept.

destinyland writes "Researchers simulated evolution with multiple generations of food-seeking robots in a new study of artificial swarm intelligence. 'Under some conditions, sophisticated communication evolved,' says one researcher. And in a more recent study, the swarms of bots didn't just evolve cooperative strategies — they also evolved the ability to deceive. ('Forget zombies,' joked one commenter. 'This is the real threat.') 'The study of artificial swarm intelligence provides insight into the nature of intelligence in general, and offers an interesting perspective on the nature of Darwinian selection, competition, and cooperation.' And there's also some cool video of the bots in action."

13 of 144 comments (clear)

  1. Of all the countries... by Kenja · · Score: 4, Funny

    Of all the Nations, I would never have thought it would be the Swiss who would start the robot apocalypse. I had Germany in my betting pull...

    --

    "Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
    1. Re:Of all the countries... by Starayo · · Score: 4, Funny

      Never trusted 'em, myself, what with their knives, and their cheeses.

      --
      Ezekiel 23:20
    2. Re:Of all the countries... by oldspewey · · Score: 3, Funny

      If history has taught us anything, it's that if you wait long enough, eventually the Germans will come to you.

      --
      If libertarians are so opposed to effective government, why don't they all move to Somalia?
    3. Re:Of all the countries... by commodoresloat · · Score: 3, Funny

      yeah but those clocks... you can set your watch by them!

  2. to counteract by Keruo · · Score: 5, Funny

    To counteract his theories about swarm-intelligence, I sent the researcher link to 4chan.

    --
    There are no atheists when recovering from tape backup.
    1. Re:to counteract by snarfies · · Score: 5, Funny

      Actually, not a bad way to poison a bot's intelligence. Its been done before, with hilarious results (well, if you like 4chan-style humor), with a chatbot called Bucket. It was designed to pick up the basics of the English language and conversation techniques from random internet users.

      Then 4chan found it.

      http://encyclopediadramatica.com/Bucket has the full story, along with quotes and screenshots.

  3. The ability to deceive? by Thanshin · · Score: 5, Funny

    they also evolved the ability to deceive.

    Obviously, once you've proved the entity has the ability to deceive, you must distrust any further results.

  4. Robotic Evolution by allknowingfrog · · Score: 3, Interesting

    Do I understand this correctly? On top of superhuman strength and intelligence, we're now making steps toward robot evolution? When robots rule the world, do you think they'll debate whether or not they actually evolved from primitive PCs?

    "You fool! We were created in our present form by the great nerd in the sky! Shun the non-believer!"

  5. i think this was covered already... by fuo · · Score: 3, Informative

    in this post: http://hardware.slashdot.org/article.pl?sid=09/08/19/185259

  6. Real hardware is more information rich by Weaselmancer · · Score: 3, Interesting

    Real hardware can hold more states than a purely digital system.

    I remember reading a paper (can't find it now though - darn it) about a guy who was doing neural net research with Xilinx chips. Same idea. Whenever an algorithm would do well he'd break it into "genomes" and pair them off with other successful programs.

    The board was a bank of Xilinx chips, the genomes were the programming files (basically 1s and 0s fed into the configuration matrix), and the goal was to get the thing to turn on and off when you would speak "on" and "off" into a microphone.

    It eventually started working. More interesting than that is what happened when he loaded the program into another board. It didn't work.

    It turns out the algorithm had evolved to take advantage of the analog properties of the specific chips in that particular board. The algorithm didn't see the board as a digital thing. It saw it as a collection of opamps, amplifiers, and other analog parts. Move the program to a board that is identical digitally, and it failed because the chips weren't analog exact. You wouldn't have seen that behavior in a purely digital simulation.

    --
    Weaselmancer
    rediculous.
    1. Re:Real hardware is more information rich by Chris+Burke · · Score: 4, Interesting

      It turns out the algorithm had evolved to take advantage of the analog properties of the specific chips in that particular board. The algorithm didn't see the board as a digital thing. It saw it as a collection of opamps, amplifiers, and other analog parts. Move the program to a board that is identical digitally, and it failed because the chips weren't analog exact. You wouldn't have seen that behavior in a purely digital simulation.

      Yeah, I remember that, but differently (or maybe it's a similar but different incident). What I recall is that he looked at the working design, and saw that it included a section that wasn't connected to anything else. Thinking this was just random waste, he removed it. Then it stopped working. Capacitive and inductive effects from the 'disconnected' section was affecting the main 'working' section and making a complicated analog circuit.

      In either case (and both are certainly possible outcomes), this outlines what is so awesome about Genetic Algorithms and the natural evolution that inspires them -- no preconceived notions about what the solution should look like. Whatever works, works, and that's literally all that matters. Us humans very often start with a picture in mind of what the answer "should" be, and it limits our thinking. On the other hand, a lot of times we have those preconceived notions like "this circuit should be digital not analog" for very good reasons, and we simply fail to notify the GA of that requirement. Which also makes GAs fun. :)

      --

      The enemies of Democracy are
  7. Re:Waste of time by jfruhlinger · · Score: 3, Insightful

    I imagine that there might be interesting results that come from putting objects into an environment where you don't control all the variables. I've heard of cases where the robots end up using features of their own hardware (which is generally cobbled together from off the shelf parts) that the researchers never anticipated.

  8. Re:Waste of time by thesandtiger · · Score: 3, Insightful

    Because intelligence isn't just a software thing. At least not in humans.

    I recall reading about field programmable gate arrays being used in an experiment with genetic algorithms. They wanted to force the FPGAs to evolve to tell the difference between two different frequency sounds. Eventually they wound up with chips that accomplished the task in a variety of ways - ways that worked but for no explicable reason, some of them being ways that took advantage of tiny differences in the individual (identical, at least from a manufacturing perspective) chips, and even that required slight differences in the room's environment. This was years ago.

    Simulations won't have those little idiosyncraces between individual units and thus might miss a huge component. Variation among individuals that is only in software misses the whole concept of variation between individuals that comes about from hardware, and also from the interaction between the two.

    --
    Since I can't tell them apart, I treat all ACs as the same person.