Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
Science Technology

Learning Robots 125

Posted by michael from the maybe-not-such-a-good-idea dept.
carnun writes "The NewScientist is reporting on a new snakelike robot that uses genetic algorithms to change its motion pattern so that it can still function after sustaining damage." Roland Piquepaille sends in a report about another "learning" robot, named Adam, which is designed to seek out and feed from "flowers".
This discussion has been archived. No new comments can be posted.

Learning Robots More

Learning Robots

Comments Filter:

  • Aibo (Score:1, Funny)

    by fishybell ( 516991 )
    I've tried and tried, but I still can't teach my Aibo.

    • Re:Aibo (Score:2, Informative)

      by ejtttje ( 673126 )
      If you really want to teach your Aibo new tricks, try C++ ;)

      System SDK: OPEN-R [aibo.com]

      or a framework which builds on top of the SDK: Tekkotsu [tekkotsu.org]

      The goal of the Tekkotsu project is to eventually be able to train a robot like a dog.
      It's open-source, so you can try your hand at it if you think it should be easy ;)

  • Before they become impossible to stop! (Score:5, Funny)

    by tlacicer ( 515153 ) * on Thursday August 21, 2003 @09:20AM (#6754250)
    Again, I think it looks like it is time for some robot insurance [robotcombat.com]!

  • Worms (Score:4, Interesting)

    by rf0 ( 159958 ) <rghf@fsck.me.uk> on Thursday August 21, 2003 @09:21AM (#6754266) Homepage
    I wonder if they could extend this to create a worm type robot that if it got cut in two it could still carry on. Say a brain in each segment

    Rus
    • Or perhaps one which can grow a fully new brain in each segement no matter how many time you cut it.
    • What, a beowulf robot cluster? :-D

      (Sorry, it was obligatory)

    • Re:Worms (Score:4, Informative)

      by drc500free ( 472728 ) on Thursday August 21, 2003 @10:12AM (#6754709)
      Ah... there's my account ;-)

      anyway, this is already done with PolyBot:
      http://www2.parc.com/spl/projects/modrobots/polybo t/polybot.html [parc.com]

      each module is autonomous, and it can make legged as well as snake-like configurations. I assume that this worm i similar.

  • Very Worthwhile (Score:5, Interesting)

    by boogy nightmare ( 207669 ) on Thursday August 21, 2003 @09:24AM (#6754281) Homepage
    Damn Damn Damn, try as i might i cant find anytihng funny to write for this. I think the snake idea is inspired (imagine the fun aspects of a robo-whacking day hehehe)

    Imagine and earthquake scenario or anything along those lines (911) a van turns up and releases several hundred robotic snakes all able to sense heat, movement etcetc..

    Bless the Brits and their fabulous snakes :)
    see got a funny line in the end

    S
    • Imagine and earthquake scenario

      OK -- Imagine being immobilized under all that rubble and having a snakebot scare you half to death as it slithers into your crevice. No, it'd be much wiser to go with cockroach-bots. :)

      --

    • try as i might i cant find anytihng funny to write for this.

      You sure? What about this:

      "This thing must have been programmed in Python!" :^)

  • Self-healing robots (Score:5, Interesting)

    by rainstorm ( 237399 ) on Thursday August 21, 2003 @09:25AM (#6754299)
    Given that we will increasingly use robots to do the work that's too dangerous for humans to do, self-healing robots that can get the job done, damage or no, sound like a nice step forward.
    • Uh... self-healing? Can you imagine the trouble that would cause? Just think of what would happen when they become obsolete and you wish to destroy them... oops! They just heal themselves.

      Probably a better solution is to make them functional even with significant levels of damage, riddling them with redundant systems that take over where the main systems fail or get destroyed.

      • Re:Self-healing robots (Score:1)

        by Anonymous Coward
        Uh... self-healing? Can you imagine the trouble that would cause? Just think of what would happen when they become obsolete and you wish to destroy them... oops! They just heal themselves.

        Heh, that's what God must have been thinking.

      • Hey, you can always give them the ability to self-heal along with a fixed lifespan. (But Replicants have rights too! :)

        --

  • So this is how it starts (Score:3, Funny)

    by Timesprout ( 579035 ) on Thursday August 21, 2003 @09:26AM (#6754305)
    First of all its 'ahh look at the cute robot playing in the garden and learning how to survive on flowers'. Then its 'AHHHH please Mr. T1000 let me survive, please dont point that pulse rifle at me'.
    • Could someone explain to me how a comment that hasn't been rated can be "over-rated" (referring to Parent)? My brain hurts.
      • When your karma gets high enough you get a free +1 karma bonus that you can turn on or off with each post. You should use it when posting something on topic or particularly funny and turn it off when trolling or posting something off topic like this. Anyway, if you post using the bonus you've essentially modded yourself up. That means you can be modded down as overrated...the moderator is saying no, you shouldn't have used your karma bonus there.
      • It's very simple: Slashdot gives moderator points to retarded individuals who are, quite frankly, idiots.

        For example, the moderator who will most likely mod this comment down, ignoring the insightful and informative comments on this thread that should be modded up, is probably an idiot.
    • Dr. Ian Malcolm: Oooh! Ahhh! That's how it always starts. Then later there's running and screaming.
  • The serpentine spy...can be dropped out of helicopters to carry out reconnaissance missions

    I'm not surprised it needs to be resilient! What are the relative odds of the snake damaging itself on landing vs. someone managing to hit it with an AK-47?

  • Oblig. (Score:5, Funny)

    by Jonsey ( 593310 ) on Thursday August 21, 2003 @09:28AM (#6754327) Journal
    I for one welcome...

    Has anyone else noticed the large increase in the number of robot related stories here lately? Beats SCO anyway.... Waitaminnute! Robots beating SCO! Perfect!
    • Waitaminnute! Robots beating SCO! Perfect!

      I'm sorry, but it turns out we at SCO have identified our copyrighted code in your robots' neural programming. We are currently pursuing legal recognition of our rights to the software, but in the meantime we would like to extend an offer of $7,999 per robot brain in exchange for a license to continue functioning.

  • Mandatory (Score:5, Funny)

    by tlovie ( 603161 ) on Thursday August 21, 2003 @09:30AM (#6754343)
    I for one welcome our new snake-like robot overlords. :)

  • Snake Metaphor (Score:3, Funny)

    by ArmenTanzarian ( 210418 ) on Thursday August 21, 2003 @09:30AM (#6754345) Homepage Journal
    There's just something a little evil sounding about dropping snakes from the sky to use on your enemies. Especially in conjunction with another article with Adam and Eve references.

  • I mock the creators (Score:5, Funny)

    by L. VeGas ( 580015 ) on Thursday August 21, 2003 @09:31AM (#6754349) Homepage Journal
    Hey is that a new snakelike robot that uses genetic algorithms to change its motion pattern so that it can still function after sustaining damage in your pocket, or are you just happy to see me?

  • Whacking Day! (Score:5, Funny)

    by Goyuix ( 698012 ) on Thursday August 21, 2003 @09:33AM (#6754360) Homepage
    Obligatory Simpsons SONG:

    Oh Whacking Day
    Oh Whacking Day
    Our hallowed snake skull-cracking day.

  • Self-repairing robots have been around for a while (Score:5, Informative)

    by Anonymous Coward on Thursday August 21, 2003 @09:34AM (#6754372)
    A man by the name of Mark Tilden has been building 'unstoppable' robots for years out of regular components. He got his start building cheap, autonomous anti-land mine robots for the military that could have one leg blown off and still crawl around to find another.

    He also built $5 robots that crawled through mazes faster than anything MIT ever put together, pissing off the school's robotics department.

    Google for BEAM Robotics, and check out this interview:
    http://www.exhibitresearch.com/tilden/ [exhibitresearch.com]
    • Damn, that's a fascinating article. Unfortunately, it doesn't include schematics. :)
      • Google for BEAM robotics and you'll find lot's of links. There's even a company [solarbotics.com] that specializes in BEAM kits if you're interested. I find the concept interesting, but a bit overrated. The BEAM robots in question don't really heal themselves in the tradiitonal sense of the word. It's just that they're simple enough (and thus robust enough) to take a bit of a beating.
    • the robots which crawled thru the maze relied on air currents for navigation. basically a wind sensor with simple servo motors. the breeze blowing thru the maze allowed it to crawl thru.
      the mit one used vision sensing and had on board computation. totally different beasts.
      • So? Sounds like a good solution to the problem. In this case, the goal is to get to the end of the maze, not to see the maze.

        Many AI and robotics researchers seem to fall into the trap of modelling human cognition rather than designing an intelligent artifact. Both approaches have their place, but it's a shame when someone who's trying to design AI gets blinded by experience as a human being and tries to program an agent to make decisions the same way.

        That being said, computer vision is an important field
    • Yeah Tilden is the man! I remember once sawing a very nice documentary on Discovery Channel in which he stole the show. It's a farely old show, but nevertheless nice to see how Mark's building a robot from a old walkman in less than an hour. And it works! And good too!

      Too bad the folks from Discovery Channel have not visited him for the 2nd time when making the new show "Robosapiens" (although that show was mostly about humanoids, it could have had very well a reference to Tildens robots who dont have to b
    • I think the point of the article is that 'worse is better' applies to robots too =)

    • Re:Self-repairing robots have been around for a wh (Score:1, Funny)

      by Anonymous Coward
      In the article he claims the soldiers didn't like his ant-land mine robots, because they'd take away the soldier's jobs. You know, if my job description included getting my leg blown off by a land mine, I'd seek other employment.
    • From the article linked in post 6754372:

      "Believe me, no matter how smart we make our devices, we will never have to worry that our toaster is making plots against us. Unless, of course, it's being run by Microsoft."

      [/obligatory MS slam]

    • Nice article, but it appears that whoever wrote it did a rather lamenTABLE cellspacing=5 cellpadding=5 job of proofreading after running a search-and-replace.

  • WISOR (Score:5, Interesting)

    by JohnGrahamCumming ( 684871 ) * <slashdot@ j g c . o rg> on Thursday August 21, 2003 @09:35AM (#6754378) Homepage Journal
    If you find that interesting it's worth reading about a robot called WISOR [discover.com] that was built by a company called Honeybee Robotics [honeybeerobotics.com]. WISOR is uses for inspection and repair of high temperature and pressure steam pipes under the city of New York. It moves through the pipes like a very large inch worm.

    There's even a movie [wisor.net] (a really odd movie in fact) about it.

    John.

  • Pleasure Worm? (Score:5, Funny)

    by koniosis ( 657156 ) <koniosis&hotmail,com> on Thursday August 21, 2003 @09:36AM (#6754385)
    How long till they turn it into a sex toy?????
  • "The robot is going to lose. Not by much. But when the final score is tallied, flesh and blood is going to beat the damn monster."

    Not anymore buddy!

  • Haven't WE learned anything yet? (Score:5, Funny)

    by burgburgburg ( 574866 ) <splisken06.email@com> on Thursday August 21, 2003 @09:37AM (#6754396)
    Learning robots lead to robot overlords. Just last week, I caught my Roomba changing my long distance service. And my Aibo takes my car for weekends; never tells me where he's going, never pays for gas.

  • the concept's been around for a while (Score:4, Informative)

    by vida ( 695022 ) on Thursday August 21, 2003 @09:39AM (#6754412)
    the 'genes' part is new (and very cool) but the 'snakebot' as a concept has been around for a while. NASA announced something like it in OCT-00 nasa [nasa.gov] and this guys tried to put it in layman terms: here [howstuffworks.com]
  • The serpentine spy...can be dropped out of helicopters to carry out reconnaissance missions No wonder they made it to work when its damaged if they're throwing them out of planes!
  • "After a number of generations the amount of improvement finally tends to taper off, says Mahdavi, indicating that the GA has reached a performance plateau" and "Once the robot was mobile, the team disabled some of its segments to see if it could adapt to injury. Initially it was immobilised, says Bentley, but as the GA continued to try to improve the locomotion, it gradually worked out how to move again..."

    My god! It is the beginning of the Borg! "You will adapt to service us." or something. How long be

  • Practical Applications (Score:5, Funny)

    by LegendOfLink ( 574790 ) on Thursday August 21, 2003 @09:45AM (#6754464) Homepage
    Come on now, scientists, who really cares if a robot can sustain damage...why not create a robot that can "learn" to traverse from the TV room over to the kitchen and acquire some beers for its master.

    Now THAT would be freakin' cool.
    • For such a robot [or any other independent robot] to find many practical applications, it would need good visual pattern-recognition software to navigate independently, which is a very difficult objective due to the processing power needed, but quantum physics may help.

      A year ago, New Scientist wrote about an algorithm that might allow future quantum computers to make a "Fourier transform" for pattern recognition. -If such quantum computers can ever become reality [with their massively parallel processing
  • ...SCO has found a new mascot, which is a robotic snake-thingy that will search and destroy all opponents.
  • The article doesnt say, but in abscense of photos I'd guess this is just more headwork.

    Good thing you didnt report on an unimportant article on New Scientist, you know, like this way to stop cancer. [newscientist.com]

  • Self-healing and redundancy a must for robots (Score:5, Interesting)

    by thepacketmaster ( 574632 ) on Thursday August 21, 2003 @09:50AM (#6754502) Homepage Journal
    While it is certainly natural for all living creatures to learn to cope with an injury, I think this is far more important for robots, since they don't have a survival instinct.

    Humans will go to great lengths to avoid getting injured (well, most sane ones). However, robots will just do what they are told. While they may be told to avoid any hazards, they just don't have that instinct that says I *really* don't want to get my limb chopped off today.

    So to compensate, all robots in hazardous or isolated situations should have this self-healing built in, as well as redundant limbs. A robot could be built with 2 legs, but why not make it 4 or 6 and have a couple to spare. The same goes for sensors. Only two are needed for stereoscopic vision, but 4 or 6 would be better.

    • ...not to mention that it's what allows them to run for Governor of California.

    • A robot could be built with 2 legs, but why not make it 4 or 6 and have a couple to spare.

      I just finished reading Philip K. Dick's "Do Androids Dream of Electric Sheep?" -- very different from the movie "Blade Runner", a bit darker and more depressing, but an excellent read.

      In it, at the end, the remaining 3 androids take a spider their human friend found, and asked, "Why does it have 8 legs? Don't you think it could get along with less? Let's find out." And they start snipping off the spider's l

  • Freakin' eh! I want one so I can win BattleBots [battlebots.com]. A robot that can keep killing after it's been damaged - ain't technology great?!
  • This article is unclear on the nature of the fitness measurement used by the GA. The following quote leads one to believe that the GA is running onboard the snake's processors (rather than in simulation):

    "Once the robot was mobile, the team disabled some of its segments to see if it could adapt to injury. Initially it was immobilised, says Bentley, but as the GA continued to try to improve the locomotion, it gradually worked out how to move again, albeit more awkwardly and with an ungainly, dragging gai

    • Re:Fitness Measurement for the GA? (Score:1, Informative)

      by Anonymous Coward
      inertial sensor with photonic sensor which allows it to orient with its target (light source). more motion in the direction of light source=better fitness.
    • This article is unclear on the nature of the fitness measurement used by the GA.

      No, it isn't:

      The GA tries them all out and awards them a fitness rating, depending on how far it makes the snake move.

      • ...and how does the snake know how far it moved? The fun thing about GAs is that they're very creative when it comes to solving the problem posed to them - so creative that they often find ways to "cheat." For example, an early GA experiment that tried to evolve "creatures" (composed of rectilinear solids with simple joints) that would move in their simulated environment. First, individuals evolved that took advantage of a conservation of momentum bug in the environment's physics package: they hit thems

  • Adam rots. (Score:2, Insightful)

    by Chess_the_cat ( 653159 )
    Adam is nowhere near a revolutionary robot. It was programmed to recharge itself. It 'learned' two facts: red walls don't recharge, green flowers do recharge. Wow. What is that, 3 lines of code within one IF loop? It moves around randomly and when it touches a wall its energy goes down. When it happens to touch a flower its energy goes up. Now that it knows that its learning is complete. It can't learn anything more. To me, a truly learning robot can learn anything if left alone long enough. Like
  • it's still no helper monkey.

  • Revolutionary? (Score:4, Insightful)

    by HolyChao ( 7909 ) on Thursday August 21, 2003 @10:15AM (#6754743) Homepage
    I suspect that the author of the article about Adam may have been a bit overzealous when she described the robot as "revolutionary."

    First, I have to give Professor Russell credit for some extremely clever names: Adam (ADAptive Mobile robot), and Eden (EDucational ENvironment).

    That said, nothing in the article suggests there is anything remarkable about the robot. The most telling line in the article is "Adam was activated with a basic level of competence, which let him know to back off if he hit a wall, and to feed when he saw a flower." That's two very important abilities Adam didn't have to learn.

    It is certainly possible that Adam uses some revolutionary AI algorithm, and if so I would be very interested in it, but I have a hunch that Adam is just an exercise in building a basic robot with a basic learning algorithm and a clever naming scheme.
  • We've always wondered what's deep below the surface of the earth of given locations for mining, welling, etc. We're using sound waves so far but they can only go so far. Would it be possible to make a hollowed out worm/snake robot which moved the dirt infront of it to behind it, so in theory it could go anywhere underground until something went wrong, such as communication sever, too hard rock, too high temperature?

    Anyone want to make a billion bucks?

  • If I had to make a Terminator: (Score:3, Informative)

    by freality ( 324306 ) on Thursday August 21, 2003 @10:41AM (#6755044) Homepage Journal
    I've written about this elsewhere [freality.com], but here, for fun:

    The Robot: Honda [honda.com]

    "The functions of Honda's humanoid robot are defined as follows: An operational system that autonomously performs typical operations under known circumstances. If an extraordinary operation is required under unknown circumstances, the robot will be supported by an operator... [The P3, 1,600mm in height and 130kg in weight, features a computer unit, motor-drive system, battery and wireless apparatus inside the body section. This more sophisticated robot can achieve freer movement, go up and down stairs and push a vehicle.]

    [Future Development will focus on]:

    • Further dimensional and weight reduction.
    • Improved dynamic performance.
    • Improved operability.


    For items 2 and 3, it is extremely important that through the evolution of hardware we achieve physical autonomy by improving dynamic performance and adaptability to wider variations of working conditions. Also important is the pursuit of studies in artificial intelligence systems, which will provide the solution for improved autonomy."

    The Brains: CYC [cyc.com]

    "The Cyc product family is powered by an immense multi-contextual knowledge base and an efficient inference engine. The knowledge base is built upon a core of over 1,000,000 hand-entered assertions (or "rules") designed to capture a large portion of what we normally consider consensus knowledge about the world. For example, Cyc knows that trees are usually outdoors, that once people die they stop buying things, and that glasses of liquid should be carried rightside-up."

    And of course, lots of little other things, like targeting systems, healing systems (like this article), a CNS to link these higher-level functions to the motor control systems of the robot, um.... GUNS, MISSLES, etc..

    Yeah, maybe not such a good idea. Of course, if we truly believed it a bad idea, we'd work for treaties now against robotic warfare, before one of our county's governments builds these and the rest are "forced" to catch up.

    That is, if it hasn't started already. Clone wars!

    • "The Cyc product family is powered by an immense multi-contextual knowledge base and an efficient inference engine. The knowledge base is built upon a core of over 1,000,000 hand-entered assertions (or "rules") designed to capture a large portion of what we normally consider consensus knowledge about the world. For example, Cyc knows that trees are usually outdoors, that once people die they stop buying things, and that glasses of liquid should be carried rightside-up."

      I am a huge fan of AI, and geeky rob

  • T100 Technology (Score:4, Funny)

    by GoofyBoy ( 44399 ) on Thursday August 21, 2003 @10:52AM (#6755164) Journal
    Obviously this technology is going to be used to teach T100s to crawl with their hands in that slow manner after their legs get smashed up and they are on the verge of a total systems failure.

  • Building the "terminator" into robots is true AI (Score:4, Interesting)

    by adzoox ( 615327 ) on Thursday August 21, 2003 @10:53AM (#6755171) Journal
    This is essentially building "survival" into robots. Although fictitious, The Terminator's function was to complete it's mission, it's processing would route power or find power from other limbs, etc etc.

    I think that true AI will result from this "survival instinct" - because robots will eventually learn that in order to survive/continue they will need to be loved, to fix themselves (eat, be healthy), and to have shelter (come out of the rain)

    • I think that true AI will result from this "survival instinct" - because robots will eventually learn that in order to survive/continue they will need to be loved, to fix themselves (eat, be healthy), and to have shelter (come out of the rain)

      Why don't you export this artificial intelligence to the middle east? I don't know what kind of intelligence they're running on, but it sure sounds like they could use some of this!

  • impressive? (Score:2, Insightful)

    by trans_err ( 606306 )
    I'm not sure how impressive this really is... maybe i'm missing something, but the algorithm simply learns from it's "mistakes" (ie. if i move this segment and this segment i move this way) and records these mistakes... this is not unlike the basic learning algorithms in some AI's (ie. in the beginning the program starts with a limited amount of knowledge.. a set strategey and learns everytime it makes a move which puts it in a negative situation).. .

    or maybe im just bitter.

  • More about "Adam in Eden" (Score:4, Informative)

    by rpiquepa ( 644694 ) on Thursday August 21, 2003 @11:36AM (#6755776) Homepage

    I read all the comments about this story.

    First, if you want a direct access to my report, click here [weblogs.com].

    Then, even if I agree that's the code behind and the robot itself don't look *very complex*, I think the idea of a robot recharging its batteries from pseudo-flowers is pretty refreshing -- if I might say so.

    And, finally, you need to read what Andy Russell, Professor at Monash University in Australia, says on his homepage [monash.edu.au]: "For me this is a new area of research and so there are no publications as yet."

    A last note: the small videos available on his site are really fun to watch.

  • Biological robots. . . (Score:5, Funny)

    by Fantastic Lad ( 198284 ) on Thursday August 21, 2003 @12:06PM (#6756138)
    The muscles in the human body are triggered by electrical signals, right?

    So then it should theoretically be possible to wire a human body so that it can be remote controllable. --I mean, even in the dorky public access sciences, they have rats which can be directed around laboratory floors with radio control units.

    Heck, does the body even have to be 'alive'? --We already have coma victims kept going by machine. Why not, through brain manipulation, fire all the right signals to make the body walk and breathe. And talk. Why not? --All that speech stuff is programmed in there already. --Look at Bush; he's just a reaction machine; no soul inside. Not even an Intel chip. (Though he's not a robot; he's just another boring psycho.)

    But hey, many Slashdotters would argue that there are no such things as 'souls' in the first place, which would mean that all humans are just big robots running rogue. Why not simply direct some of those brains and bodies by remote control? Again, public arena science has experimental jet pilots directing their planes with mind-reading helmets. --And the nice thing about electrical impulses is that, as any engineer can tell you, they're a two-way street. (Though somewhat more complicated in biological form, but nonetheless entirely manipulable.)

    According to my ever-so-bountiful sources, there are about 1 million of these human robots being used right now on our humble little planet. --It's even possible to simulate an aura, making them difficult to detect even by those who are sensitive to such things. (Not that aruas exist, of course. To suggest such a thing would be foolish.)

    Now sure, this may all sound like rather much higher tech than even a well equipped Shadow Government could pull together. And last I heard, human agencies weren't at the level of being able to put a human robot into action, but then things have been moving pretty quick of late. --For instance, I'd be interested to know which particular group is responsible for the lastest bunch of crop circles up in Canada. --The ones which have burnt/blown cavities [cropcirclenews.com] in the cereal nodes which look as though they were put too long in a microwave.

    Human agencies? Maybe. It's tough to say. Things are playing so fast and loose these days, it's nearly a full time job just keeping up!


    -FL

  • snakelike robot that uses genetic algorithms to change its motion pattern so that it can still function after sustaining damage

    ...So in other words, after a shotgun blast, it will keep coming after you unlike a real snake.

    I wonder how development of directed energy weapons is coming?

  • I, for one, welcome our new robotic snake masters...
  • Thinking, evolving, self-healing robots. Hmmmmmmmmmmmm... can't see that going wrong. http://www.terminator3.com
  • How about the snake-like robot splits into two autonomous parts when it sees an advantage to do so. It gets to its (supposedly military) objective, decides it would be useful to recce two perimeters... off they go. They could always meet up and reconnect later.
  • and with this, SOON, we will be living in pink sacs of goo and wired into a virtual world once the machines have found out they cant be stopped by us.. ok, sorry, I had to crack a lame Matrix joke in there some time.. anyways, this seems cool, but like I've said before...why? why make something that cant be stopped and can learn? and why they keep pushing artificial intelligence is beyond me, I can understand limited artificial intelligence, where they learn to an extent, but are "blocked" from learning h

Slashdot Top Deals

Whoever dies with the most toys wins.

Close