Follow Slashdot blog updates by subscribing to our blog RSS feed

 



Forgot your password?
typodupeerror
×
Science Technology

Pheromone Robotics 109

An Anonymous Coward writes: "This is the official text I just came across: "The HRL Pheromone Robotics program aims to provide a robust, scalable approach for coordinating actions of large numbers of small scale robots to achieve large scale results in surveillance, reconnaissance, hazard detection, path finding, payload conveyance, and small-scale actuation." But it's the spooky image that grabbed *me*..." Here's some more on the pheromone-sniffing robots pictured, and some more information about making robots that hunt in packs. The page has not been updated for a while, but it's worth seeing.
This discussion has been archived. No new comments can be posted.

Pheromone Robotics

Comments Filter:
  • by Anonymous Coward
    I'd never be able to escape those robots on a bad gas day....
  • by HiredMan ( 5546 ) on Saturday January 19, 2002 @06:39PM (#2870117) Journal
    Ants are very simple creatures that working collectively in groups to accomplish fairly complicated tasks using mostly smell.

    Modeling behavior along these lines and allowing simple creatures to relay very simple state messages with each robot repeating it to others would allow behavior and information to be propagated and acted on even in hostile situations. (Only short range communication is possible for instance.)
    ie If the robots are searching for something and one finds the target it could alert the others around it and they could repeat the message and alter their behavior accordingly - if required. Eventually the alert would filter across all robots and reach "home" at which point a response could be propagated back to the successful creature the same way.

    If your creatures are too simple there are limitations, however. If you put certain acids on ants other ants will assume they're dead - the smell trigger - and carry them to "dead ant" pile even if they're struggling. The "un-dead" ant will be carried back to the dead ant pile repeatedly until the smell wears off.

    =tkk
  • This makes me wonder if robot hunting might become a new "sport". You know the classic scenario of many villains wanting to hunt humans because they're the only game that's difficult enough to bring down. Maybe we'll hear about a new kind of high-class robot safari? Heh, then we can all be evil-eccentrics without the guilt, or the evil...
  • by idiot900 ( 166952 ) on Saturday January 19, 2002 @06:51PM (#2870170)
    Imagine hacking these robots just by farting near a swarm of them ;)
  • by cybrpnk ( 94636 ) on Saturday January 19, 2002 @06:53PM (#2870178)
    Israel A. Wagner's home page about Ants, Robots and Computation is here [technion.ac.il] and it's a great and interesting compilation of data on this topic. Absolutely recommended.
  • Computational Beauty (Score:3, Informative)

    by clasher ( 2351 ) <bkeffer@thecomm a n d line.org> on Saturday January 19, 2002 @07:05PM (#2870216) Homepage
    For more information on the ability to accomplish complicated tasks with simple rules take a look at this book The Computational Beauty of Nature [mit.edu].

    Very informative book, lots of good explanations, diagrams, and the code for his software is available on the website. As a plus he seems to have written the book using free software which he acknowledges at the end of the book). His programs run under linux. He has some very well done graphics (even some dual-image stereograms) which were created with gunplot. I highly recommend this book.
  • I thought we already had pheromone-seeking robots. There called girls.
  • Watch out for those scent-tracking mechanical hounds.... Run, Montag, run!
  • From Count Zero: "They set a slamhound on Turner's trail in New Dehli, slotted it to his pheromones and the color of his hair. It caught up with him on a street called Chandni Chauk and came scrambling for his rented BMW through a forest of bare brown legs and pedicab tires. Its core was a kilogram of recrystallized hexogene and flaked TNT." Sleep sweet, everybody...
  • Oh no... more of "Fahrenheit 451" is coming true. Censorship, book-burning, government control, big-screen TV's, headphones, and now robots with a sense of smell that can be trained to hunt people down!

    Is Ray Bradbury psychic, or what? I mean, think about it: that book was written 50, 60 years ago, and it's still pertinent today. Just about the only thing that was off was the year the story took place-- 1990. But apparently, it was only off by about 15-20, because we could be living in that story in about 5-10 years, I'd say. *shudders* Really makes you think!

    BTW, if you haven't read the book yet, READ IT!!

  • It has nothing to do with the pheremone robots.
    HRL Laboratories has developed a unique technology, which we call PackHunter, for identifying cyberspace navigators with similar interests. The novelty comes from the use of "digital scents" left behind as trail markers as users move through the hyperlinked space. The properties and behavior of this scent can be tuned to allow a trail's visibility to decay in time, be reinforced through reuse, and to diffuse in cyberspace. The diffusion in cyberspace occurs through scent being distributed to neighboring links. The overlap between the diffusion-broadened trails can be used to identify people with similar interests without the requirement that they actually visit the same sites.

    Feedback results in improved collaborator discovery performance over time.

    There are many other potential applications, relating to both public and private hyperlinked systems. Examples are identifying users of large private databases with common interests such as genealogy or history researchers looking at similar sets of records, corporate R&D personnel investigating competitive analysis databases, and patent or litigation counsel researching large document data repositories. There are also opportunities in situations where knowledge of other users' past presence, frequency of presence, or proximity can be used in real time, such as in multiplayer on-line gaming.

    HRL Laboratories is actively seeking commercialization partners, primarily with a view to licensing the technology, but also with the option for more active participation. If you are interested in further discussion please contact Dave Payton at payton@hrl.com [mailto] or Mike Daily at daily@hrl.com [mailto].

    Interesting stuff, but nothing to do with the original subject.
  • by Incongruity ( 70416 ) on Saturday January 19, 2002 @08:45PM (#2870520)
    The first link mentioned in the story/writeup is not about pheromone sniffing robots persay. If you read the article, the whole idea is called "Pheromone Robotics" because of the similarity to ants and other, similar pheromone using species that the collaborative, distributed system of problem solving utilizing large numbers of independent and relatively simple robots. The robots use "virtual pheromones" to communicate (again this is an illusion to the system of pheromonic communication used by ants etc.

    Here's a section from the article that explains basically what I just tried to explain.

    Borrowing techniques used by ants and termites, our robots exhibit emergent collaboration. Inspired by the chemical markers used by these insects for communication and coordination, we exploit the notion of a "virtual pheromone," implemented using simple beacons and directional sensors mounted on each robot. Virtual pheromones facilitate simple communication and coordination and require little on-board processing.

    I don't mean to be flame bating or anything, I just thought the writeup was a bit confusing/misleading...that or I'm just an idiot and didn't understand what they submitter meant.



  • Ugh..Here we go again...

    The HRL Pheromone *DING* Robotics program *DING* aims to provide a robust *DING* , scalable *DING* approach for coordinating actions of large numbers of small scale robots *DING* to achieve large scale results in surveillance *DING* , reconnaissance *DING* , hazard detection *DING* , path finding *DING* , payload *DING* conveyance *DING* , and small-scale actuation *DING* *DING* *DING* . We intend to accomplish this by developing innovative *DING* concepts for coordinating *DING* , and interacting *DING* with, a large
    collective *DING* of tiny robots *DING* . Borrowing techniques used by ants and termites *DING* , our robots exhibit emergent *DING* collaboration *DING* . Inspired *DING* by the chemical markers *DING* used by these insects for communication *DING* and coordination *DING* , we exploit *DING* the notion of a "virtual *DING* pheromone," *DING*
    implemented *DING* using simple beacons *DING* and directional sensors *DING* mounted on each robot. Virtual *DING* pheromones *DING* facilitate *DING* simple communication *DING* and coordination *DING* and require little on-board *DING* processing. Our approach is applicable to future robots with much smaller form factors (e.g., to dust-particle size) (hah, yeah right-- *DING* )and is scaleable *DING* to large, heterogeneous *DING* groups of robots.

    We plan to provide robustness *DING* by requiring no explicit *DING* maps or models of the environment, and no explicit knowledge "explicit knowledge? What, the robots watch porn movies? *DING* of robot location. Collections of robots will be able to perform complex tasks *DING* such as leading the way through a building to a hidden intruder *DING* or locating critical choke points. *DING* This is possible because the
    robot collective *DING* will become a computing grid *DING* embedded *DING* within
    the environment *DING* while acting as a physical embodiment *DING* of the user interface What the FUCK are you talking about? *DING* . Over the past decades, the literature on path planning and terrain analysis *DING* has dealt primarily with algorithms *DING* operating on an internal map containing terrain
    features. Our approach externalizes *DING* the map, spreading it across a collection *DING* of simple processors *DING* , each of which determines the terrain features in its locality *DING* . The terrain processing algorithms *DING* of interest are then spread over the population of simple processors *DING* , allowing such global *DING* quantities *DING* as shortest routes, blocked routes, and contingency *DING* plans to be computed by the population.

    The user interface *DING* to this distributed robot collective *DING* *DING*
    *DING*
    is itself distributed *DING* . Instead of communicating with each robot individually, the entire collective will work cooperatively *DING* to provide a unified *DING* display *DING* embedded *DING* in the environment *DING* . For example, robots that have dispersed themselves throughout a building will be able to guide a user toward an intruder by synchronizing *DING* to collectively blink
    in a marquee-style *DING* pattern to highlight the shortest path to the intruder. Through the use of augmented *DING* reality *DING* , robots will be able to present more complex displays *DING* . Users wearing a see-through *DING* head-mounted *DING* display and a head-mounted *DING* camera that detects and tracks infrared *DING* beacons emanating *DING* from the robots will
    be able to see a small amount of information superimposed *DING* over each robot. Each robot will, in effect, be
    a pixel *DING* that paints *DING* information upon its local environment. The combination of this
    world-embedded *DING* interface *DING* with our world-embedded *DING* computation means that the results of complex *DING* distributed *DING* computations *DING* can
    be mapped *DING* directly onto the world with no intermediate *DING* representations *DING*
    required.

    I think I broke my dinger.

  • Basically its a ton of cameras.

    Use visual recognition to detect stuff like troop movements....
    Or just use cameras+ human watching + set coordinates already.

    Picture vietnam movies, with the guy radioing for a mortar strike.

    Now picture no one in harm's way, but the cameras and coordinates for mortar strikes are at Mr. God's hands.

    Later: Camera + visual recognition = Missle Guidence system

    Later: Camera + High powered AA guns + some elementary physics = anti aircraft guns

    But here's the kicker... If you network ALL the cameras, so you know information everywhere, then you can calculate things better...

    Its like automagic driven cars, the more networked, the more you see around JOE BOB in his big ol truck... Because of networking alerts you to whats around it... The more you know.
  • ...The U.S. have sent them after President Jiang Zemin already, look out!
  • BEAM Robotics (Score:2, Interesting)

    by mgandhi2 ( 455480 )
    The idea for the pack hunter sounds like a basic neural network with BEAM robotics. You can get a fairly good idea what BEAM(Biological, Electronic, Aesthetic, and Mechanical) is all about at http://www.solarbotics.net .
    Basically, the philosophy of BEAM is that all robotics can be made from imitating the form of nature, and all can be made from the same basic components. You start by replicating single cell organisms and insects, and eventually progress to neural networks. The cool thing about BEAM robots is that they're entirely automated. You don't have to program their behavior, they works by "instinct."
    If you want to make your own BEAM robots, just read some of the tutorials on http://www.solarbotics.net . Just don't be tempted to start with a complex robot. The idea behind BEAM robotics is to start simple, and work to complex. All you will need to start is a basic understanding of electronics and some cheap electronic components, which can usually be found at RadioShack(or by tearing apart old household appliances.)
  • ... helping the US be more of an automated imperialist. This may be clever, but even if it is, it makes me sad that in a country with so many problems, some of our greatest minds are used to create smarter tools to kill and opress.
  • The insect/pheromone analog functioned more as a metaphor than anything. The underlying engineering seemed to be a rehash of the old digital/analogue information 'theory'. Nothing new but old sci-fi allusions.
  • This is fairly standard technology for "game AI". I could give references, but don't have time right now.

    The "pheromone" business is no big deal. That's how creatures too dumb to make maps mark their world. The territory is the map.

    • This is fairly standard technology for "game AI".

      I disagree. Presuming your talking about real-time strategy games, most of those seems to generate a path when asked to go somewhere, and stick to it, even if that path should become blocked. This is a natural consequence of using the A* or similar pathfinding algorithms. The pheronome approach is a much superior approach, as it allows traversal of unknown territory, something the A* doesn't really handle, since it assumes perfect knowledge of the world, and allows for intelligent handling of changing landscapes and crowded areas, something almost all RTS games handles in a suboptimal fashion, to say the least.

      I could give references, but don't have time right now.

      Hope you can find time to post the references. I love reading about this kind of stuff.
      • The classic game with a "pheronome" approach was SimAnt, which explicitly worked that way. There are other games that have a similar system internally, but don't make the trails visible to the player.

        If you combine trail-making behavior with flocking [red3d.com] and related field-based behaviors, you can get results that look semi-intelligent, even though the underlying algorithms are quite dumb. The field-type behaviors result in reasonable low-level movement in the presence of obstacles, while the trail-making system provides map-like information from successful movement. You can do a halfway reasonable battle simulation like that. It will look good from a distance, at least.

  • Can you imagine a cluster of these babies!?

    I never thought that would actually come up seriously.
  • Quote "But it's the spooky image that grabbed *me*..."

    Yeah, a picture of little robots is real spooky. I bet this guy's shadow gives him a heart attack.
  • I am aware of this project quite a long time, since I'm working on a similar project called "Swarm-Bots" [web site www.swarm-bots.org [swarm-bots.org]]. According to me their use of the term "pheromone" is not more than a catchy adjective to label their work. The research, as displayed on their web site, does not take many ideas from the ethological studies of ant colonies. For instance the robots communicate directly with each other, NOT through the environment, which is what ants use pheromone for. To me, it is merely an integration of the dynamic programming technique with mobile robots coupled with VR display interface. For those new to the subject, there is a new approach, called "swarm intelligence" that aims to create intelligent systems from a group of distributed simple agents. An excellent description of this approach is available in the "Swarm Intelligence: From Natural to Artificial Systems By Eric Bonabeau, Marco Dorigo, and Guy Theraulaz" [santafe.edu] . In this approach, the agents communicate through the environment, called stigmergy, to achieve group level tasks. There is no centralized control, yet the whole system is very scalable and robust. I hope to report some news on the progress of the Swarm-Bots soon.
  • .. what those little shoebox-sized black robots in
    Star Wars were doing.. Now I know: checking up on Stormtrooper B.O.!
  • are both good, but they both smell. Or osmething? the paohs thing about teh open sarcs

    asource opened source???
  • So you know, the HRL webpage has been updated.

"It is easier to fight for principles than to live up to them." -- Alfred Adler

Working...