Slashdot Mirror


Researchers Using AI To Build Robotic Bees

An anonymous reader writes "British researchers at the Universities of Sussex and Sheffield are developing a computer model of a bee's brain that they hope can help scientists better understand the brains of more-complex animals, such as humans, and perhaps power artificial intelligence systems for bee-like robots. Called 'Green Brain,' the project is trying to advance the science of AI beyond systems that just follow a predetermined set of rules, and into an area where AI systems can actually act autonomously and respond to sensory signals."

29 of 44 comments (clear)

  1. Promising... by raydobbs · · Score: 2

    ...every good project has to start somewhere - and it will be interesting to see what this kind of AI modeling will accomplish. Perhaps we can learn more about bees, and how to keep them doing their busy work throughout our world without mass murdering them. ...that being said... the day they crack the secrets of modelling the human female's brain... there is where the real money will be made.

    1. Re:Promising... by TheLink · · Score: 2

      To me it seems that they should figure out how the single celled stuff (like amoebae and neutrophils) think before they go on to more complex stuff.

      From what I see they seem smarter than most people (including many scientists) assume:
      https://www.youtube.com/watch?v=I_xh-bkiv_c
      https://www.youtube.com/watch?v=pvOz4V699gk&feature=related
      http://www.brianjford.com/a-08-12-infocus_cell-intelligence.pdf

      Have our AIs reached the level of intelligence of an Euglypha amoeba, which builds a pretty decent shell for itself: http://starcentral.mbl.edu/microscope/portal.php?pagetitle=assetfactsheet&imageid=26590

      It's quite an elaborate shell - with holes in the front and back. The number of "teeth" in the shell apparently is not determined strictly genetically either see 3) in:
      http://what-when-how.com/molecular-biology/maternal-genetic-effects-molecular-biology/
      Note that it builds a new similar shell when reproducing.

      It may be that a single neuron is actually not that stupid and it's because you need redundancy and the ability to control a large creature/"machine" that you have to have many of them and a multicellular body.

      --
    2. Re:Promising... by LifesABeach · · Score: 1

      With 2 daughters and a wife, I've lived in that femail group think mode. It's chilling.

  2. Curiosity. by Ostracus · · Score: 2

    A certain Mars Rover comes to mind.

    --
    Shai Schticks:"You don't make peace with friends, you make peace with enemies"
  3. Bee Brain by busyqth · · Score: 5, Funny

    for (x in recognize_nearby_objects())
    {
    if (x.type == FLOWER) {
    nuzzle_flower(x);
    }
    else if (x.type == HUMAN) {
    sting(x);
    }
    else if (x.type == SMOKE) {
    sleep(1);
    }
    else {
    buzz();
    }
    }

    1. Re:Bee Brain by pitchpipe · · Score: 3, Funny

      // The following section is essentially complete. Someone
      // just needs to flesh out a few of the functions
      // (probably just take an intern an afternoon)

      for (x in recognize_nearby_objects())
      {
      if (x.type == FLOWER) {
      nuzzle_flower(x);
      }
      else if (x.type == HUMAN) {
      sting(x);
      }
      else if (x.type == SMOKE) {
      sleep(1);
      }
      else {
      buzz();
      }
      }

      --
      Look where all this talking got us, baby.
    2. Re:Bee Brain by MatrixCubed · · Score: 1
      ...
      sting(x);
      die();
      ...

      FTFY

  4. These post titles really are sensationlist lately by NinjaTekNeeks · · Score: 1

    "British researchers at the Universities of Sussex and Sheffield are developing a computer model of a bee’s brain that they hope can help scientists better understand the brains of more-complex animals, such as humans, and perhaps power artificial intelligence systems for bee-like robots."

    Perhaps bee-like robots. Or robots that function as bees do, where they perform mundane functions over and over for the good of society.

  5. Re:These post titles really are sensationlist late by TommyTumult · · Score: 1

    Or to produce dogs with bees in their mouths so when they bark they shoot bees at you

  6. Scale this up by teaserX · · Score: 3, Insightful

    These don't have to be limited to just RoboBees. The algorithm could be used for more than just pollination. Think about it. Build anything of the appropriate size to autonomously go out and collect $RESOURCE, return with a load, refuel itself and go back out. Some cursory self-defense, like hazard evasion, would be nice. Throw in some networked communication to help with discovery of sources and you have a very efficient way to accumulate stuff.

    --
    We really need your help
    http://www.gofundme.com/help-sherry
    1. Re:Scale this up by wierd_w · · Score: 3, Interesting

      Logistically, if the swarm could not manufacture new units, and or, collect and repair damaged/errant units, the system has serious vulnerabilities.

      take for instance, the human greed factor.

      If there is a huge swarm of autonomous robots out scouring riverbed sandbars for teensy gold nuggets, or some other discrete but scattered and valuable resource, how long do you think it would be before unscrupulous people tried to trick the bees into dropping the cargo off at a "new" dropoff point?

      Where there is profit, there will always be dirty dealing and crime. Look at the internet for instance, with something seemingly as harmless as email. Then along came the spammer.

      Autocollecting robot swarms would be a smorgasboard for whitecollar criminals.

    2. Re:Scale this up by teaserX · · Score: 1

      Autocollecting robot swarms would be a smorgasboard for whitecollar criminals.

      That's why we're also working on the escort model: Flying RoboShark with frickin laser beams on thier heads.

      --
      We really need your help
      http://www.gofundme.com/help-sherry
    3. Re:Scale this up by Peristaltic · · Score: 1

      The algorithm could be used for more than just pollination. Think about it. Build anything of the appropriate size to autonomously go out and collect $RESOURCE, return with a load, refuel itself and go back out. Some cursory self-defense, like hazard evasion, would be nice. Throw in some networked communication to help with discovery of sources and you have a very efficient way to accumulate stuff.

      If they're going to include these behaviors, they ought to model Weaver ants instead.

  7. It'll never happen. by dohzer · · Score: 1

    Shows like Here Comes Honey Boo Boo make me realise we will just never understand the human brain.

    1. Re:It'll never happen. by jd2112 · · Score: 1

      Shows like Here Comes Honey Boo Boo make me realise we will just never understand the human brain.

      Shows like Here Comes Honey Boo Boo make me think that the (average) human brain isn't that complicated after all.

      --
      Any insufficiently advanced magic is indistinguishable from technology.
  8. Tonight on SyFy... by Zephyn · · Score: 2

    Irwin Allen and James Cameron proudly present:

    THE SWARMINATOR!

  9. Obligatory Simpsons by TheSpoom · · Score: 1

    Homer: Bart, you’re coming home.

    Bart: I want to stay here with Mr. Burns.

    Burns: I suggest you leave immediately.

    Homer: Or what? You’ll release the dogs, or the bees, or the dogs with bees in their mouths and when they bark they shoot bees at you? Well, go ahead—do your worst!

    --
    It's better to vote for what you want and not get it than to vote for what you don't want and get it.
    - E. Debs
    1. Re:Obligatory Simpsons by wierd_w · · Score: 1

      Burns: Release the robotic Richard Simmons.

  10. I, for one, welcome, our new by Sneftel · · Score: 1

    emphasis on fidelity over complexity in neural simulation.

    --
    The opinions stated herein do not necessarily represent those of anybody at all. Deal with it.
  11. Excellent! by PRMan · · Score: 4, Insightful

    Maybe these ones will be resistant to Monsanto products...

    --
    Peter predicted that you would "deliberately forget" creation 2000 years ago...
  12. The problem with programming a brain.. by andydread · · Score: 3, Interesting

    may possibly be the approach many of these very smart researchers use. Perhaps the focus should be on developing some kind of artifical nevous system with the abitlity to learn on its own rather than trying to program for the dynamics of real world interaction. Perhaps the folks over at Boston Dynamics may be on to something? Not sure what its learning/memory capabilites are but it sure seems to behave like it has some kind of nervous system.

    1. Re:The problem with programming a brain.. by phantomfive · · Score: 1

      It looks like they are actually trying to simulate a bee's brain at the neuron level (the article is light on details). This is the latest trend in strong AI, to simulate a brain at the neuron level. There are a lot of problems and difficulties involved, and inevitably the emulations are only crude approximations of real neurons that the researches hope is good enough. But if it works, the brain should have some learning capability.

      --
      "First they came for the slanderers and i said nothing."
    2. Re:The problem with programming a brain.. by phantomfive · · Score: 1

      Apparently brain-emulation technology is to the point where emulating an entire bee brain in real time is feasible

      It's not. They are emulating a simplification of a bee's brain. Everyone else doing brain modeling is simplifying things as well. Do the simplifications make a difference? This is a question no one actually knows.

      --
      "First they came for the slanderers and i said nothing."
  13. Why not simulate the world too? by OGmofo · · Score: 1

    Why go through the trouble of building an actual physical bee, when there are awesome 3d world and physics models that you could drop the bee brain into and it would have no idea the world was simulated. Seems like that would bee a lot easier debug. *cringe*

  14. Re:anonymous reader uses AI to share news by wierd_w · · Score: 1

    Natural system software incorporates rules that have builtin support for uncertainty.

    Ever wondered why it takes so goddamn much processing power to fold a model of a protein? (They don't call brownian motion a "random walk" for no reason you know.)

    The nervous system of that bee is fudementally influenced by biochemical interactions at thousands of locations, each incorporating a degree of randomness into the system. Instead of treating the randomness as noise, the design utilizes the randomness as an asset.

    This inherent incorporation of randomness would make artifical nervous systems based on it abhorrently difficult to reliably and consistently program. Rather than programming, it would be training, and the robots would naturally develop naughty habbits, just like their biological counterparts do.

    A really sophisticated one would be a health and safety nightmare.

  15. Monthy Python - Eric the Half a Bee by Master+Moose · · Score: 2

    Is this a wretched demibee,
    Half asleep upon my knee
    Some freak from a menagerie?
    NO! It's Eric the half-a-bee!

    --
    . . .gone when the morning comes
  16. Dalek Bees! by jd2112 · · Score: 1

    I hear them now! Oh no, the horror! ..... POLLINATE! POLLINATE!

    --
    Any insufficiently advanced magic is indistinguishable from technology.
  17. Release the hounds! by the_humeister · · Score: 1

    But did they also make robot dogs as a robotic bee launching platform when they bark???

  18. Industrial Apiculture by handy_vandal · · Score: 1

    "The bees are fine," said the beekeeper.

    While visiting a farmer's market this summer, I asked a beekeeper, "How are the bees?"

    I was concerned that he had not understood my full message, so I amplified: "Nationally, I mean ... globally ... Colony Collapse Disorder ...?"

    "There is no 'Colony Collapse Disorder'," he assured me. "This is an industry bugaboo, a distraction from the real problem, which is industrial-scale beekeeping.

    "Oh, there are bees with mites, and diseases. But the real problem is industrial-scale beekeepers who move their colonies twice a year. When you keep your bees in Minnesota for a few months, then move them south for the winter -- move them next to industrial zones, toxic waste dumps -- then what can you expect?"

    I don't know beekeeping, but this guy clearly does: the jar bears his name, his product is widely sold at grocery stores around town (Minneapolis/Saint Paul), and he had the absolute serene confidence of a man who has seen the future, knows the score, and will faithfully answer any question you care to ask.

    --
    -kgj