Forgot your password?
typodupeerror

SwarmOS Demonstrated at Idea Festival 142

Posted by ScuttleMonkey
from the welcoming-various-overlords dept.
PacoCheezdom writes "Intelligent Life has short summary of a demonstration by MIT professor James McLurkin of his new group-minded robots, which run an operating system called 'Swarm OS'. The robots are able to work together as a group not by communicating with all members of the group at once, but by talking only to their neighbors, and model other similar behaviors performed by bees and ants. "
This discussion has been archived. No new comments can be posted.

SwarmOS Demonstrated at Idea Festival

Comments Filter:
  • by arsheive (609065) on Monday September 17, 2007 @03:03PM (#20640885)
    I, for one, welcome the new swarming overlords nearest to me, so that they might welcome the rest.
  • My experience (Score:5, Interesting)

    by 2.7182 (819680) on Monday September 17, 2007 @03:06PM (#20640925)
    I worked in robotics for 3 years and there was a big fad of cooperative robotics. Now, closely related is this swarm stuff. But theoretically it is the same as having a robot with many parts (i.e. higher dimensional phase space). I never saw any real applications.
    • Re: (Score:2, Informative)

      by frission (676318)
      I didn't think it was a great book, but a lot of people seem to like the book "Prey" by Michael Crichton. It has a few lists of sample applications of swarms when used with nanobots, but military and medical applications were the focus...
    • Re: (Score:2, Interesting)

      by CaseCrash (1120869)
      One word: Collectors.

      I've always thought robot swarms would be good for stuff like landfill reclamation. Teach it to recognize something you want picked up and then set them loose. Tell each other when they've found something or when they need help moving it, etc.

      Might not be worth the ROI though.
      • ROI (Score:4, Insightful)

        by Joaz Banbeck (1105839) on Monday September 17, 2007 @03:16PM (#20641111)
        Bees and ants seem to be a good argument that it might be a good return on investment. So do search parties when looking for lost hikers.
      • Re: (Score:3, Interesting)

        by Torvaun (1040898)
        I seem to recall worry about declining bee populations and what that will do to the environment at large. Would these sorts of swarms eventually be able to replace bees for pollination purposes?
    • Re: (Score:3, Interesting)

      by JeanBaptiste (537955)
      Land Mines.

      I believe that's even been discussed here on /. before
      • by cloricus (691063)
        I've often wondered why land mines are cleared in such a stupid manor. Surely sending a swarm of robots over the effected area making as much noise and earth impacts as possible to set off the mines. Faster, you can be sure you've searched the whole area, and there is far lower risk of human injury. I know I consider my leg to be worth many thousands of dollars and I'd rather pay a robot to step on a mine than myself.
    • Re: (Score:3, Informative)

      by m0nstr42 (914269)

      I never saw any real applications.

      Adaptive Sampling and Prediction [princeton.edu] - Group of coordinated robots used in the field for ocean monitoring.

      There is also immense military interest. Research doesn't get done on a large scale without funding. Funding, generally speaking - at least in engineering, doesn't come without someone with some influence being convinced that there will be applications.

    • But theoretically it is the same as having a robot with many parts (i.e. higher dimensional phase space).

      No, it isn't.

      Swarm intelligence relies on emergence that arises from many simple agents that interact locally with each other (i.e. without a master controller), using minimal rules. These are the keypoints of this field: there isn't a single point of failure, you can ensure degradation of service gracefully, you can even perform self-repair, etc. It allows to solve large problems without having to imple

    • Re: (Score:3, Interesting)

      by JoeD (12073)

      No real applications?

      Forget about land mines, or rescue operations or other such high-minded things. Not that they aren't worthwhile, but they don't speak to most peoples' everyday life.

      How about self-driving cars?

      It seems tailor-made for that one.
  • Tried to RTFA and got this instead:

    "This Account Has Exceeded Its CPU Quota

    Please contact this site's webmaster.

    Wait a few minutes and use your browser's "Back" button or click here to try again.

    If you are the webmaster, your account may have gotten this error for one or more of the following reasons:

    * Your account has used more than its share of the cpu in the past 60 second sliding window.
    * Your account has too many concurrent processes running sim
  • by mac-diddy (569281) on Monday September 17, 2007 @03:10PM (#20640985)
    You can read more about this research and see some videos of the robots in action here [mit.edu].
  • What would really be a practical application of this? Name me one.
    • Practical application: self-laying mines. Think how annoying it would be to clear a path and then overnight see the 95% of the mines you missed on day one redeployed in near-randomness across your path back.

      (Yes I have MOD points today...it's just more fun to talk.)

    • Re: (Score:2, Funny)

      by Xybre (527810)
      Simulated robotic orgies.
    • Re: (Score:2, Insightful)

      by darkfire5252 (760516)
      Swarm of UAVs for surveillance of hostile (and friendly?) countries. UAVs work together to accomplish goals such as "make sure there is a flyover of areas X Y and Z every 10 minutes", "keep a unit no less than 5 minutes away from this location", "keep 20 units in the airspace, but make sure each unit charges to at least 40% at all times."
      • Sounds like what my mom did by herself when I first moved alone. Fly-by seemingly at every 10 minutes (in my foolishness I only moved as far as across the street), kept a unit (younger siblings) no less than 5 minute away from my location at all times, made sure to load up my fridge to at least 40% at all times, and so on.

        Oh, and please no jokes like "yo momma's a swarm of nanobots" and such.
    • Re: (Score:3, Insightful)

      by Digital_Quartz (75366)
      An application of what, specifically? Machines that talk to each other and not to the whole group and do something useful? You mean, like Bittorrent? :)

      Seriously, though, this is some very cool research; the robots talk to each other via infrared, which is why they can only talk to their neighbors. But, with the infrared setup they're using, they can estimate direction and distance to each of their neighbors. You COULD do this with a bunch of robots talking bluetooth with GPS receivers, but it would be
    • Re:wha? (Score:5, Interesting)

      by lb746 (721699) on Monday September 17, 2007 @04:09PM (#20642047)
      Cars driving themselves.
      • or better yet, cars that work together to avoid gridlock, as in, all the cars within a mile or so of each other adjust speed and following distance and coordinate lane changes in advance of the obstruction. while overall speed may have to reduce, all the cars flow through the obstruction smoothly and with no fender benders.

        if a car breaks down, it transmits the "obstruction" signal so that approaching cars know to move around it. like a radio frequency hazard light that you can "see" for a couple of mile

    • by m0nstr42 (914269)
      ASAP [princeton.edu] program, where a group of coordinated robots was used to perform oceanographic measurements.
    • Nothing. Just like PC's, which have no practical application.
    • by Hatta (162192)
      I dunno, life? Every one of us is an intelligent network built from unintelligent components which mostly just interact with their neighbors.
    • Re:wha? (Score:5, Funny)

      by Hatta (162192) on Monday September 17, 2007 @05:55PM (#20643717) Journal
      I know I already replied, but I was just reminded of a quote. I forget whether it was Babbage or von Neumann or whoever, but he had just finished giving a talk about the computer. During the question and answer period a woman raises her hand to ask, "That's all very nice, but of what use is it?" To which he replies, "Madame, of what use is a newborn child?"

      I'd be glad if someone could tell me who said this or if it's apocryphal or whatever. I looked on google a bit with no luck.
      • I wasn't saying it wasn't without potential, like a newborn. I was just saying that this technology isn't as practical or Earthshaking as something that could brew me a decent pot of coffee in 3 minutes flat. And another thing, why are they working on this when I still haven't gotten my damned flying car!
    • Re:wha? (Score:5, Interesting)

      by ChrisA90278 (905188) on Monday September 17, 2007 @09:11PM (#20646031)
      practical applicationS: Airplans flying and not crashing into one another. Same for cars.

      More practical. How about Earthmoving equipment or coal mining.

      Some exotic ideas. Military robots that gather intelligence. You
      drop thousands of these on the enemy's side and they look out to see what is going on and report back via "the grape vine". There would be tens of tousands of communications paths, far to many to jam. They also watch out for each other and communicate warnings like "hide, someone is coming." Sensor could be very primitive, perhaps just a microphone or a cellphone-like camera, but by working together they can use triangulation to locate moving targets.

      They don't have to be robots. What about a self configuring network? Each node only sees a few other nodes but they all talk about what they've seen and the word gets around that there is a printer on the second floor available for anyone who is a member of the graphic arts department to use.

    • by smchris (464899)
      What would really be a practical application of this? Name me one.

      Replicators. You never watched Stargate?
    • by nurb432 (527695)
      Traffic Control ( intelligent cars ).

      There is one for you.
  • James McLurkin (Score:5, Informative)

    by Digital_Quartz (75366) on Monday September 17, 2007 @03:13PM (#20641031) Homepage
    I saw Mr. McLurkin give his presentation here in Ottawa. Fascinating stuff. Each component of the swarm is very dumb, with very little storage. If you want to store a location for future reference, it's very easy; park a robot there.

    All the robots have a sound system, though; the first thing Mr. McLurkin did during his presentation was to have a single robot request that 6 other robots follow it, and the swarm picked and allocated 6 robots, and they all went off in a chain, singing "Hi-ho, hi-ho, it's off to work we go".

    Check out James McLurkin's website for some presentations and videos:

    http://people.csail.mit.edu/jamesm/ [mit.edu]
  • ...of an obligatorily /.-ted article here [networkmirror.com].
  • Boids (Score:5, Interesting)

    by Joaz Banbeck (1105839) on Monday September 17, 2007 @03:14PM (#20641061)
    Boids was a program written to try to simulate the flocking behavior of birds. It was written by Craig Reynolds

    Reynolds gave his boids 3 rules:

    1 Don't crowd too close to other boids
    2 Try to go the same direction as other boids near you
    3 Try to be in the average position of your local neighbors.

    With just those three simple rules, the boids arranged themselves in a flock. Much to Reynolds surprise, without any more rules than that, the flock exhibited other emergent behavior, such as a flock that split up to go around an obstacle would rejoin.

    More at: http://www.red3d.com/cwr/boids/ [red3d.com]
    • by Speare (84249)
      Sounds like Rule 4 is "don't hit obstacles" unless you rewrite Rule 1 as "don't crowd too close to anything."
    • Re: (Score:1, Interesting)

      by Anonymous Coward
      This is a little multiagent java applet I worked up a few years ago, inspired by stuff like Boids.

      http://www.erik-rasmussen.com/multiagent/ [erik-rasmussen.com]

      For what it's worth...
    • Re:Boids (Score:4, Interesting)

      by m0nstr42 (914269) on Monday September 17, 2007 @05:24PM (#20643257) Homepage Journal
      One of the seminal analytic papers in this area is

      Tamás Vicsek, András Czirók, Eshel Ben-Jacob, and Inon Cohen ``Novel type of phase transition in a system of self-driven particles'' Phys. Rev. Lett. 75 1226 (1995)

      Another great paper:

      Couzin, I.D., Krause, J., James, R., Ruxton, G.D. & Franks, N.R. (2002) Collective memory and spatial sorting in animal groups [princeton.edu] Journal of Theoretical Biology 218, 1-11.

      In the above, a phenomenon called "collective memory" was exhibited in a model similar to Reynolds'. Individual members of the group have no explicit memory, but the group as a whole exhibits behavior that differs depending on the previous state of the group - in effect a "group memory".

      Also, a shameless plug for my own software/API designed for similar simulations: glSwarm [sourceforge.net]. Admittedly in a very early state of development, but functional enough to play with.
  • by Anonymous Coward on Monday September 17, 2007 @03:17PM (#20641113)
    Robot-1: I heard from Robot-2 that Robot-3 got promoted because she slept with the boss after the Christmas party last year.

    Robot-4: I knew something was going on. Robot-3 doesn't even have opposing digits, how can she be qualified for the ball in bucket tests?
  • Awesome.... (Score:3, Funny)

    by that IT girl (864406) on Monday September 17, 2007 @03:18PM (#20641135) Journal
    With all the advancements and buzz about smarter-than-man AI, and now they're excited about robots as smart as BEES AND ANTS.
    • Eowyn: I am no man.

    • Or alternately as smart as the neurons in the human brain. It wouldn't surprise me in the least to see this technique applied to nanobots to create an artificial brain as good as a real brain at storing, retrieving and making decisions based on some very simple rules and typical sensory input.

    • by Woy (606550)
      Clearly you've never faced ants.

  • Was there and... (Score:1, Insightful)

    by Anonymous Coward
    I was there, saw the demonstration, and wondered why this was being done on physical robots rather than on virtual robots. I guess its more impressive to see the little cars roaming around with their blinky lights.

    The part of the presentation I didn't agree with was the myths about robots taking over. I think that robots alone won't take over, but once we supply them with the true ability to learn like the human brain learns, we will be dealing with something other than a robot, and its intelligence will
    • by m0nstr42 (914269)

      I was there, saw the demonstration, and wondered why this was being done on physical robots rather than on virtual robots. I guess its more impressive to see the little cars roaming around with their blinky lights.

      As someone who has done both (virtual and real groups), doing things with real robots tends to open up a whole can of worms in terms of practical issues. This is true in a great variety of engineering fields... start with a simulation to get the major kinks out, move to the real thing and reali

    • by grahamd0 (1129971)

      ...its intelligence will quickly surpass a human's. Someone, somewhere, will give it (or a version of it) the means to replicate and improve upon itself, and eventually it will emerge from that as an unstoppable being....

      That's a common viewpoint, but I believe it stems more from human arrogance and fear than from logic or fact.

      What qualification would make one intelligence "better" than another? What can a machine intelligence possibly learn that an organic intelligence could not?

      • by skelly33 (891182)
        What can a machine intelligence possibly learn that an organic intelligence could not?

        Machine intelligence can use brute force to find answers that humans can not. Hence brute force encryption cracking, or perhaps subtler tasks like gene folding. Possibly more important than what answers machines can come to faster than us is the question of what questions can a machine postulate to itself for resolution? What is the answer to life, the Universe, and everything!?

        I figure when AI reaches the point that
    • by skelly33 (891182)
      I've pondered this topic a bit over the years. I still think it's a long shot. Real long.

      Consider the film "Batteries Not Included" which featured miniature robotic machines that were able to reproduce. They did so by harvesting raw matierials that they commandeered from their immediate environment, and then put to work their on-board fabrication tools (welding, cutting, fastening, etc.).

      That may work for Hollywood, but if you consider the great variety of both materials and tools required to fabricate
  • by fahrbot-bot (874524) on Monday September 17, 2007 @03:27PM (#20641339)
    "Intelligent Life has short summary of a demonstration by MIT professor James McLurkin of his new group-minded robots, which run an operating system called 'Swarm OS'.

    Professor James McLurkin now goes by the designation "1 of 12".

  • This isn't actually new technology. Swarm has been an active research technology for some time, in robots and distributed systems.
  • SlashSwarm (Score:3, Funny)

    by UltraAyla (828879) on Monday September 17, 2007 @03:28PM (#20641351) Homepage

    I for one welcome the new swarming overlords nearest...oh - I've just received word from the swarm that someone already posted this. Ok how about:

    In Soviet Russia, bots swarm...oh - that too? Ok, how about just a simple "Profit?"

    I think this swarm thing will take some getting used to

  • by Anonymous Coward
    From TFA : "...James McLurkin, a PhD student at MIT Computer Science and Artificial Intelligence Laboratory..."

    He's a student, not a professor. Way to read the article, Mr. submitter.
  • The Berserkers are coming...
  • Robots (Score:5, Funny)

    by slobarnuts (666254) on Monday September 17, 2007 @03:40PM (#20641513) Homepage
    ... Guided by a rumor mill. Bot 1 to Bot 2: Were going left. Bot 2 to Bot 3: Were going left. Bot 3 to Bot 4: Were going left. Bot 4 to Bot 5: purple monkey dishwasher.
  • This topic isn't new (Score:1, Interesting)

    by Anonymous Coward
  • Come on....

    We start off with dumb near mindless swarm bots. And then we find ourselves waging war with a super-evolved sentient robotic hive species!

    Have we learned NOTHING from our hours of sitting on our couch watching sci-fi without end as we munch on Oreos and beer?
  • So if the hurd isn't out yet, the herd is?
  • Swarm racer (Score:3, Interesting)

    by Cochonou (576531) on Monday September 17, 2007 @03:49PM (#20641691) Homepage
    Swarming and flocking behavior also inspired a freeware game called Swarm Racer [lexaloffle.com], in which you get to control a swarm of micro-racing robots. For Windows and Mac OS X.
  • Do they run Linux?
  • I'm pretty sure this is how the Borg started.
  • Wow! (Score:2, Funny)

    by Bobb Sledd (307434)
    Can you imagine a bee or wolf cluster of these?

    I'll be here all week.

  • by mveloso (325617) on Monday September 17, 2007 @04:44PM (#20642605)
    How are humans and bees/ants/swarms different?

    When you put lots of humans together, they get dumber.
    • Its not that. As a group the individual is still stressed and people still want their individuality (or have been brainwashed into thinking that via the media). The bees are selfless and work for the greater good of the hive. Humans as a group still at the individual level work for themselves.
  • Now try to build those on a molecular level and we're in the Diamond Age !
  • Just for the record, McLurkin is a graduate student, not a professor at the good ol mit
  • Do not feed them natural oil!

Assembly language experience is [important] for the maturity and understanding of how computers work that it provides. -- D. Gries

Working...