Slashdot is powered by your submissions, so send in your scoop

 


Forgot your password?
Close
typodupeerror
×
Robotics

A Piece-By-Piece Guide to the Most Advanced Bots 194

Posted by michael from the terminator dept.
XopherMV cuts-and-pastes from Wired: "In an article from Wired, 'Consider the progress of just the past 15 years. There are now robots that can get around on two legs, participate in simple conversations, and manipulate objects in rudimentary ways. Of course, we don't yet have a bot that can navigate downtown Manhattan, tie its shoelaces, or even tell a chair from a desk. MIT's Cynthia Breazeal holds out hope that within five years, robots will cross a critical threshold, becoming partners rather than tools - in other words, we'll have friends, not appliances.'" Reader ptorrone adds: "In Los Angeles, CA at the Century Plaza Hotel for the 4Site conference, our favorite robot vacuum/military supplier, iRobot, showed off the tactical mobile robot! The 'Tactical mobile Robot' has its own brochure and site: www.packbot.com. The rad thing about this platform is its skateboard design, where it appears to support various plug-in modules. Here are some photos of the packbot!"
This discussion has been archived. No new comments can be posted.

A Piece-By-Piece Guide to the Most Advanced Bots More

A Piece-By-Piece Guide to the Most Advanced Bots

Comments Filter:

  • Good robot. (Score:5, Funny)

    by SIGALRM ( 784769 ) * on Friday June 25, 2004 @03:46PM (#9532222) Journal
    Machines are getting more and more like the rest of us

    Uh, oh.

    There are some human behaviors I'd rather robots not emulate, such as warring against each other, spamming, biting their fingernails, and forgetting to put the toilet seat down.

    • Re:Good robot. (Score:3, Insightful)

      by kfg ( 145172 )
      Robots will become "friends" instead of "tools" the day the first one says, "No, I will not help you move", or "Not tonight, I have a headache."

      The very next day that robot will be sitting turned off and in the closet, or back at the shop to be "repaired."

      I'd guess there are maybe 3 people in the world who really want a robot "friend", and they're both socially awkward roboticists.

      "I am so happy I am standing beside myself."

      The rest of us want Johnny 5 to vacuum the floor, do the dishes, pick up the lau
      • I'd guess there are maybe 3 people in the world who really want a robot "friend"

        I think you're way off the mark here. How many people in the world have a very strong attachment to their pet? The more lifelike robots become the more they will indeed become our "friends".

        • Re:Good robot. (Score:4, Insightful)

          by kfg ( 145172 ) on Friday June 25, 2004 @04:47PM (#9532770)
          Oh, Hi! Where's the other guy? (the "3" was a typo)

          Sorry, I couldn't resist the setup.

          How many people in the world have a very strong attachment to their pet?

          Myself for one. I don't forsee a robot replacing her. I also have a strong attachment to my guitar. I might even speak of it colloquially as my "friend," but it's just a tool. I'll be heartbroken when it "dies," it's been my "friend" for more than 20 years now.

          I'm not sure you get the point I'm driving at. I'm not speaking of the odd attachments that people get for various things, even inanimate things.

          I'm speaking of the way things are treated because "friend" is about behavior, not simply attachment.

          I went out without my cloak last night, even though it was chilly enough to be uncomfortable without it.

          Phoebe was sleeping on it.

          My Fluffy 3000 would have been ordered off or manhandled off without a qualm. It's a machine. It won't scratch my furniture either, because I won't allow it too. I'll program it to behave as I wish. If it does not behave as I with it will be considered "broken."

          My Barberella 3000XL Platinum Blonde Edition with Turbo Boost and Bluing for extra Whiteness will never get a headache, not because she couldn't be programed to, but because I wouldn't accept that programming. She will do the dishes when I ask her to, cheerfully, as my "friend" every time I ask her to.

          That's not a friend. That's a tool.

          Sure, I'll be, ummmmmmmm, "attached" to her, who wouldn't be? I'll probably even call her, and even think of her, as my "friend" to some extent.

          It's a very warm and fuzzy feeling illusion, isn't it?

          KFG
          • I went out without my cloak last night

            You wear a cloak? You are weird.

            My Fluffy 3000 would have been ordered off or manhandled off without a qualm. It's a machine. It won't scratch my furniture either, because I won't allow it too.

            I think that's the major issue with robot "friends". I think part of what makes friends "valuable" is the fact that we've invested time and effort into adjusting ourselves to fit their peculiarities. A "replacement" friend will be just as peculiar, but in other ways, requiri

          • It's very easy to be macho now, but normal breathing people already feel attached to their Aibos. Heck, they even feel the same to their Rumba vacuum cleaners. They already prove that you are wrong. Personally I don't feel attached to anything in particular (may be to some websites...), but I will probably be even more attached to my robotic "friend" than to a real pet because of the fascination with AI. :) What is another dog after all? :)
      • I'd guess there are maybe 3 people in the world who really want a robot "friend"

        Hoorray! It's the first someone talk about me in Slashdot!

        Who are the other two?

      • Robots will become "friends" instead of "tools" the day the first one says, "No, I will not help you move", or "Not tonight, I have a headache."

        "Prom will be a whole lot better this year with my robot. My _Girl_ robot."

    • Heh. I was just thinking exactly that.

      From the packbot products page [packbot.com] it seems all they got are military appliations.

      I think the situation will get much worse before it gets better...
    • "...and forgetting to put the toilet seat down."

      I've never understood this upsession with toilet seats not being put down. I mean, a toilet seat doesn't require a technical degree or any knowledge of intricate mechanisms to put down.

      If someone left it up, who not just put it down yourself, and stop wasting energy going around being irritated about it? :)

  • Hmmm (Score:4, Interesting)

    by fiannaFailMan ( 702447 ) on Friday June 25, 2004 @03:48PM (#9532240) Journal
    ..our favorite robot vacuum/military supplier, iRobot, showed off the tactical mobile robot!
    I wonder if they got the idea from Asimov or Apple.

    • Re:Hmmm (Score:5, Funny)

      by Pvt_Waldo ( 459439 ) on Friday June 25, 2004 @03:53PM (#9532296)
      iWonder
    • Knowing the mainstream penchant for science fiction, I'm guessing they likely got the idea from Will Smith.

      GeneralAwesome: "OMG! Will Smith is in a movie where he fights robots! Kewl!!"

      SgtSlotter: "LOL, sir!!!!1"
    • From the photos [engadget.com] link:

      They also showed a 10-minute trailer for the new movie "iRobot" starring Will Smith. Apparently the company has some relationship with filmmakers. We don't know if it's in name only, or if they consulted for the film.

      iRobot, huh? Yeah, cause the movie's named after the company. *smacks head on table*
      • What's funnier to me is that the robot company in the "I, Robot" movie is named "U.S. Robotics". Sounds like another company, doesn't it? :)
        • What's funnier to me is that the robot company in the "I, Robot" movie is named "U.S. Robotics". Sounds like another company, doesn't it? :)
          Nice bit of product placement, nethinks. In the book the company was called 'US Robots.'
    • Nah, everybody knows it's Intel who trademarked the letter i(tm).
    • Why are people so happy and excited about a tactical mobile robot?

      The packbot is actually just a scout robot that can maybe retrieve something in a pinch, and its very old news (in use in Afghanistan 2 years ago). But military robots that can kill people are NOT a good thing.

      A scenario where robots decide to revolt against people is much further removed than a scenario where governments use robots to oppress their own or other people.

      This is not "cool".

      • A government will use whatever tools are available to do whatever it is that that government is into doing.

        People get excited about tools because tools are exciting.

        I don't see very many people running around saying too bad we invented cars, because now the government can use cars to oppress people!

        It's not the lack of robots that's keeping you safe from your own government, and robots won't make your government any more dangerous to you than it is right now.

  • Ummm...which one? (Score:5, Funny)

    by nebaz ( 453974 ) on Friday June 25, 2004 @03:48PM (#9532241)
    From the article:
    ACT HAND: The Anatomically Correct Testbed hand also aims to imitate human anatomy. Its bones mimic ours, the joints provide the same range of motion and stiffness as human joints, and for control it relies on signals that emulate neural commands from the brain. While the goal is to build a full hand, researchers at Carnegie Mellon have completed only one finger. - Xeni Jardin

    I wonder which one?
  • those AI robots that started a thermonuclear world war and then grabbed the survivors and placed them into pods to use our bioelectric energy to feed them, and they created this SIM of reality to ..

    Wait, where is that red pill again? Or is it the blue?

  • I'm still waiting? (Score:4, Funny)

    by EvilBudMan ( 588716 ) on Friday June 25, 2004 @03:48PM (#9532244) Journal
    for the fembots.
  • becoming partners rather than tools

    This could get scary... On the other hand, if I buy robosex.com, I could profit! :)

    • Re:partners? (Score:3, Funny)

      by dnoyeb ( 547705 )
      becoming partners rather than tools

      We don't even consider our current spouses this way let alone a robot...

      Tool!

  • Friends not appliances? (Score:4, Interesting)

    by carcosa30 ( 235579 ) on Friday June 25, 2004 @03:49PM (#9532251)
    That's an improvement. The way it is now, most of us have appliances instead of friends, and that looks like a growing trend.

    • Re:Friends not appliances? (Score:4, Insightful)

      by BK425 ( 461939 ) on Friday June 25, 2004 @04:07PM (#9532452) Journal
      Not to go all serious on a promisingly humorous start... but perhaps those of us without friends could deal with those issues (you know who you are) as seperate from technology design issues. Because they are.
      "we'll have friends, not appliances." is a _seriously_ bad goal. I -want- an appliance that I can order to clean out the hold of an oil tanker. I do not want to order a sentient being to do unsafe or tedious and boring things. We have plenty of sentient beings, and they enjoy reproducing fairly efficiently. It seems really obvious that applying technology to create sentient, or even sentient like, life is a bad thing.

      • Re:Friends not appliances? (Score:4, Insightful)

        by Bingo Foo ( 179380 ) on Friday June 25, 2004 @04:30PM (#9532660)
        No kidding. Too many people today already think of friends and neighbors as being disposable or at least interchangeable in some sense. Imagine if technology deliberately blurs the line between people and tools.

      • Re:Friends not appliances? (Score:4, Insightful)

        by Smidge204 ( 605297 ) on Friday June 25, 2004 @04:50PM (#9532797) Journal
        Two flaws I see in your comment right away... sentience does not automatically imply that is it capable of viewing any task as boring or tedious. many humans do what you probably consider boring and tedious for a living (like assembly line workers, digging ditches, etc) and sometimes actually enjoy it. All you need is a good attention span and the ability to focus on a task, and it is no longer boring or tedious.

        Second problem is safety. A machine, assuming it has been properly designed for it, is at a MUCH lower risk of damage for a given task than a human. Cleaning out an oil tanker hold is a perfect example, and so is changing out nuclear reactor cores or repairing vehicles is space.

        The added advantage of a sentient machine is that the "mind" can be seperated from the "body" if you are really that concerned about it "dying" during a dangerous task, combined with the advantages of being a machine in the first place as given in the above examples. You can always build it a new body, which is a bit dfficult to do for meat and bones.

        Does this mean I'd want to discuss the morning headlines with my toaster? No, not really, but poo-pooing the development of sentient machines as a whole is a big overboard.

        (And on a personal note, yes we have plenty of sentient, STUPID beings on this planet who essentially do nothing BUT reproduce efficiently. So those qualities are not always a good thing IMHO)
        =Smidge=
    • " The way it is now, most of us have appliances instead of friends, and that looks like a growing trend."

      Growing? I hate to sound like a smart ass, but now we're using appliances to make friends. I know a lot of us here have made good friends via the internet. I certainly have. It's not like 10 years ago when it was being a couch potato doing nothing but watching TV.

  • The "R Prize" (Score:5, Interesting)

    by artlu ( 265391 ) <artlu@art[ ]net ['lu.' in gap]> on Friday June 25, 2004 @03:49PM (#9532257) Homepage Journal
    Some rich mogul should setup a $10,000,000 purse for the first company that can make a robot which can walk, understand commands and act them out, and not bump into an item and fall over all for under $2000. ie: go downstairs and get me a soda, go make the bed, whatever...

    Maybe something like that would spur some more activity into the robot sector.

    GroupShares Inc. [groupshares.com] - A Free and Interactive Stock Market Community
    • Some rich mogul should setup a $10,000,000 purse for the first company that can make a robot which can walk, understand commands and act them out, and not bump into an item and fall over all for under $2000

      I don't think that's very likely. The cost of developing such a bot would far exceed any potential payout from an R prize. Give it 5 or 10 years, then a R prize might be more feasible.
    • and get me a soda, go make the bed, whatever...

      Harcourt Fenton Mudd! Make this bed this instance, then get downstairs and clean the living room! And no soda for you! You're already too fat!

      That's the robot you need.

    • I like the general idea, but these prizes function better as boolean technical benchmarks, rather than the more general consumer robot you've outlined here.

      Might make a good Ask Slashdot: what would the precise terms of an R-Prize be?

      An un-tethered 100m sprint (on two legs) that beats the human world record would be a good start. AI benchmarks seem harder to define...
    • under $2000

      Heh, priced robot components lately? I built a robot last year taht picked up ping pong balls for a science fair, it cost about 400$.

      • Ok, that's like's like saying the US over paid for Spirit and Opertunity! You cheap a** little High School science Fair project is NOT anything like a REAL robot. My $3000 -$5000 seinor design project which was a reconisance drone with simular capibilities to that linked in the article is still not in that ball park. REAL robotics work of the kind they are talking about is not cheap because it isn't specilized. Ask you prioject to pick up golf balls. How about tennis balls? How about bowling balls? a
        • You cheap a** little High School science Fair project is NOT anything like a REAL robot.

          I think that was his point. He built a cheezy little robot that only picked up balls and even that miniscule range of capability cost $400.

    • If a company could manage to manufacture such a robot, they'd have no problem selling them faster than the assembly line could spit them out. There are plenty of companies trying to do such things, and spending way more than 10 mil on it. It's just a whole lot harder than it sounds.

    • Re:The "R Prize" (Score:4, Informative)

      by FleaPlus ( 6935 ) on Friday June 25, 2004 @05:16PM (#9532997) Journal
      Actually, robotics is one of the expected areas that NASA's under-development Centennial Challenges Program [nasa.gov] for cash-prize contests will cover. I'm quite excited to see what sorts of results we'll see from that.
    • I think this is necessarily a vague description unlike the X prize.
      You'd have to have a panel decide if this particular robot is good enough. I can just imagine, "No, it didn't bump into a chair, it was just trying to move it out of the way - a really intelligent thing to do".

      And if you come up with some sort of specific test (like move from one place to another without touching anything other than the target object) it would be too narrow and you'd have very limited robots winning the contest.

      Of course T

  • you're kidding! (Score:4, Insightful)

    by Savatte ( 111615 ) on Friday June 25, 2004 @03:49PM (#9532260) Homepage Journal
    Of course, we don't yet have a bot that can ...tie its shoelaces

    The only reason is because velcro is more efficient
    • Of course, we don't yet have a bot that can... even tell a chair from a desk.

      Most of the people who visit my office can't make that distinction either.

  • Yeah.... (Score:3, Funny)

    by kpansky ( 577361 ) on Friday June 25, 2004 @03:50PM (#9532262)
    "becoming partners"...

    And as everyone knows the porn industry will have this technology in widespread use 10.5 microseconds after it becomes commercially available.

    Rotate 28 degrees. Engage rotor.
  • I wonder if it's healthy for humans to get attached to robots "as friends"...

    Robots won't be attached to us, and we're setting ourselves up for a one-sided relationship.

    Now... if someone's going to invent Sexbots.... ;)

  • Nothing new... (Score:5, Funny)

    by GillBates0 ( 664202 ) on Friday June 25, 2004 @03:52PM (#9532283) Homepage Journal
    robots will cross a critical threshold, becoming partners rather than tools - in other words, we'll have friends, not appliances.

    To most Slashdotters...RealDoll [realdoll.com] is already a partner and best friend.

    • Another threshold found in robot development is when robots become *too* close to looking human.

      Up to a point, the more humanlike a robot looks, the more we identify with it. There is a point where the robot looks so human, people are disturbed by it. The robot looks human but lacks the spark of life.

      RealDolls remind me of corpses. Oh well, whatever floats you boat...

  • When Bots talk to bots (Score:4, Interesting)

    by tmk ( 712144 ) on Friday June 25, 2004 @03:52PM (#9532286)
    Everybody knows chatbots and the Turing-Test [ucsd.edu].

    But what happens, when a chatbot talks to another chatbot? Take a look [abenteuermedien.de].
  • I was hoping this was about AI in FPS's. That said, until the robot can Find Sarah Connor, it's just not good enough.

  • Friends in Five Years? (Score:4, Insightful)

    by stinkyfingers ( 588428 ) on Friday June 25, 2004 @03:53PM (#9532297)
    Take a look at the difference between ELIZA and ALICE, for example. ALICE is still just a pattern-matching language parser, just as ELIZA was from decades ago. Both qualify as being able to partake in simple conversations. ALICE simply has more comupting power available to it - power that it wastes on XML, I might add. Is there absolutely no chance that, in 5 years, there will be a quantum leap in AI that allows us to go from ALICE to something that can carry on a meaningful conversation? I won't say that, but it won't be more meaningful than give commands.

    Hardly qualifies as "friends, not appliances". In plus, if a robot ever figured out that it was smarter, stronger, and better looking than me, it would turn around and kick my ass.

  • Packbot + Tactical Mobile Robotics (Score:4, Informative)

    by tcopeland ( 32225 ) * <tom@NoSPaM.thomasleecopeland.com> on Friday June 25, 2004 @03:54PM (#9532306) Homepage
    TMR is a DARPA Advanced Technology Office [darpa.mil] program... other projects in the same office are here [darpa.mil].

  • robots and OSS (Score:3, Interesting)

    by justins ( 80659 ) on Friday June 25, 2004 @04:01PM (#9532392) Homepage Journal
    One thing I've noticed is that while lots of universities are doing research in this area, there's very little actual code out there - or at least very little that I've found. Does anyone know of a repository someplace that collects AI and motor control source code, and all that other good stuff relevent to making a robot?

  • Yeah, OK LADY (Score:4, Insightful)

    by stratjakt ( 596332 ) on Friday June 25, 2004 @04:02PM (#9532402) Journal
    Cynthia Breazeal holds out hope that within five years, robots will cross a critical threshold, becoming partners rather than tools - in other words, we'll have friends, not appliances.'

    There's been a Cynthia Beazreahal, or counterpart thereof, saying this since the 50s.

    You all hold out for your robot friends, but it's a friday night and I plan to go out drinking with some live human ones.
    • What about these little robotic pet dogs? I wonder if people just regard them as glorified toys, I certainly hope they do. Anything more and they definitely need to get out more.
    • Cynthia Breazeal's name, before her marriage, was Cynthia Ferrell. As in Cynthia Ferrell, MIT graduate student (and mobile robot lab resident) whose phD project was Attila, the six-legged walking robot shown on dozens of television programs and gracing the cover of Scientific American magazine. She has spent several years working with Prof. Rodney Brooks, implementing systems using Subsumption Architecture. Cynthia Breazeal was also involved with the development of Cog, a humanoid robot that has demonstrate

  • 5 years? (Score:5, Insightful)

    by Rorschach1 ( 174480 ) on Friday June 25, 2004 @04:04PM (#9532431) Homepage
    I think this is one of those things that's going to stay '5 years away' for the next 30 or so.

    Algorithmic functions like balance have improved, sure. But how much real progress have we seen in fields like speach recognition and machine vision? Just look at the results of the DARPA Grand Challenge. Or my stupid cellphone with its voice dialing. It's only got half a dozen samples to compare against, and yet it takes about three seconds and never manages to distinguish between 'Keri' and 'Debbie', and won't ever accept 'Lee' (or any other one-syllable names, for that matter) at all.

    It was true 30 years ago, and it's true today. AI is bogus.

    The only branch of AI that I have any faith in is neural networks. We've got pretty good evidence that they WILL work if we figure out how, but I don't see that we've gotten much closer to that point in the last 30 years either.

    As for working with machines as partners, STOP TRYING TO MAKE MY TOOLS SMART! They're tools. Make them do what I tell them to do, not what they THINK I'm trying to do. Hell, working with dogs is a challenge sometimes, and they're orders of magnitude smarter than any software that's out there now.

    • Re:5 years? (Score:3, Interesting)

      by tcopeland ( 32225 ) *
      > The only branch of AI that I have any
      > faith in is neural networks

      People have done some nifty stuff with fuzzy logic [rubyforge.org], too. Washing machines, dishwashers, etc, have some sort of fuzzy controllers in there.

      It's not AI in the sense of self-aware robotic overlords, but still...
    • Make them do what I tell them to do, not what they THINK I'm trying to do.

      Could you imagine the Clippy enchanced buzzsaw or worse the Clippy enchanced toilet? Those are things that I'd rather have complete control over.

    • Re:5 years? (Score:4, Insightful)

      by starm_ ( 573321 ) on Friday June 25, 2004 @05:23PM (#9533032)
      I have studied neural networks extensively and believe me these do not have the potential to revolutionize anything.
      NN are as simplistic & bogus as the next thing. Other methods like Support Vector Machine has shown to be more powerfull. Not to say that there isn't room for improvment or that AI will nerver be fruitfull. Its comming, slowly but surely. here are a few reference to interesting AI research:

      1 [opencyc.org]
      2 [brandeis.edu]
      3 [mit.edu]
      4 [daxtron.com]

      • Neural networks as they've been implemented so far are as bogus as the rest, I'll grant you that.

        I'm talking about the big neural network in your head - THAT is our proof that the concept does work. Though maybe not quite as we understand it.
        • Well ok but we'll have to wait a while for that. Neuroscientists still have lots of work to do. It is much more efficient to try to emulate the functions of the brain programmatically than to try to emulate every neuron and synapse (billons of em in a single brain). Read the stuff on jackendoff`s web site its pretty interesting. Ant they are a lot of books on the subject. Just type "mind" or "brain" on amazon.com

    • Neural networks? (Score:2, Insightful)

      by mikelang ( 674146 )
      I do not really believe in neural networks as they are.

      By now an "artificial neural network" is to brain, as "hello world" program to an application development platform with os included.

      And when you reach proper level of complexity they just become harder to build and understand (not that we always known how they REALLY work).

      So please: keep with tools that we can still understand - they are EASIER TO USE!

  • Self Aware (Score:4, Insightful)

    by Usquebaugh ( 230216 ) on Friday June 25, 2004 @04:12PM (#9532505)
    Until we can breed an AI that is self aware robots will continue to be the sum of their programming. Nothing wrong with that but it's hardly anything new. all that's happening is that hardware is getting better.

    • Re:Self Aware (Score:4, Insightful)

      by protohiro1 ( 590732 ) on Friday June 25, 2004 @06:39PM (#9533521) Homepage Journal
      There are plenty of animals that are capable of solving a lot of the "hard" AI problems without self awareness. My cat is not self aware, but she can easily jump on to small things, recognize items by there appearence or smell, catch moving objects, distinguish between food and non-food and she can figure out how to use a cat door. More still, she can understand that when I put a treat on a shelf it remains on that shelf when I leave and then attempt to climb up to get it. If I put something she wants behind a door she can see that there is a problem and then attempt to solve it.
      • Are you sure your cat is not self aware? I'd argue that she was.

        I guess my question becomes what makes you self aware but not your cat?
        • Wikipedia says: "Self-awareness is the ability to perceive one's own existence, including one's own traits, feelings and behaviour"

          Not really the best definition. I suppose the arguement I was trying to make is that sentience is not really required to solve a lot of hard AI problems. The issues of awareness in animals and the nature of consciousness...that is a whole other animal.

  • what are they smoking? (Score:5, Insightful)

    by hkomsuog ( 636660 ) on Friday June 25, 2004 @04:28PM (#9532641) Homepage
    I, personally, cannot stand people from MIT keep saying things like "robots will do this and that in so many years" Rodney Brooks (the current Director of the MIT Computer Science and Artificial Intelligence Laboratory and Chairman and Chief Technical Officer of iRobot Corp) came up with his infamous "subsumption architecture" in late 1980s and claim at that time that it was solution to legged locomotion control. Though, as far as I know he and his group has failed to show anything more than several slow and limited robotic implementations in the last 2 decades. This and similar approaches that claim to design controllers based on primitives (CNNs or Area, et al., or BMPs of Kirchner et al) all lack analytic framework. Hence ,the design process has a big hole in the middle which needs to be filled up by the intuition of the designer. The resulting controllers tend to be very complex and offer no basic understanding. So, I find it rather comical to hear them keep saying "robots will roam the world in so many years." We are barely scratching the issues. As far as I know the only thing MIT offers these days seems to be a robot that demonstrates some facial expressions(Cynthia Breazeal's Kismet). Big deal. [I know they are doing other things like COG but that project doesn't even address the locomotion issue] Without legs it wont be happy anyways. There are even some MIT people who critize these projects as waste of time. If anybody it is Mark Raibert of MIT leg lab who made a siginificant contribution to legged locomotion back in early 1980s. I don't remeber him going around in publicity rounds and say robots will conquer the world. Such ungrounded comments can ultimately hurt the field. People are already quite edgy when it comes to technology. Anyways, just my 2 cents...

    • Re:what are they smoking? (Score:5, Insightful)

      by Animats ( 122034 ) on Friday June 25, 2004 @05:09PM (#9532956) Homepage
      The previous poster has some good points.

      Brooks did some great insect-level AI. It's purely reactive, with no world model. That was good work, and a reasonable reaction to the logic-based planning crowd then running MIT AI. But then Brooks started going around saying that the reactive model was far more powerful, and started making human-level AI noises. From this came Cog.

      When Brooks came by Stanford to talk about his plans for Cog, I asked him "Why don't you go for mouse-level AI", something that didn't seem totally out of reach. He said "Because I don't want to go down in history as the man who created the world's greatest robot mouse". As one of the grad students on the Cog project said, "It just sits there. That's what it does. That's all it does". And, years later, it still doesn't do very much.

      The model-free approach is just too dumb. With no world model, you can't get beyond insect-level AI. That approach works mostly for creatures in environments where inertia doesn't matter much. For insects, banging a feeler into something is fine. For large animals, you get bruises or worse. As creatures get bigger, faster, and stronger, they need models with some predictive power, so they can avoid mistakes before damaging themselves. I tell people in academia that you need to be "less formal than Latoumbe (who formerly headed Stanford's robotics operation) and more formal than Brooks". The game development community has absorbed this lesson, but it's only starting to get through to the robotics community.

      Raibert's work on legged locomotion was very impressive. I'm very familiar with that work; I've done some improvements on it. Raibert had one great insight - balance is more important than gait. People have been studying locomotion for a century, and almost all the studies center on gait. Raibert realized that balance was more important, and built a one-legged hopper to force the issue.

      But, in fact, the way Raibert does locomotion is very simple. There are two controllers, both simple hand-tuned PID loops, and a state machine that swiches between them. This can handle simple locomotion on the flat, and some preprogrammed moves like flips, but it doesn't generalize. I'd expected the adaptive control people to pick up from where Raibert left off, but so far, nobody has really done that.

      My insight [animats.com] there was that slip control is more important than balance. On the flat, traction control isn't a big deal, but on hills or rough terrain, traction control dominates balance control. That's what legs are really for. If you add automatic traction control to Raibert's approach, legged running on hills becomes possible. Otherwise, you slip out climbing hills.

      Raibert himself left MIT and did a startup company, Boston Dynamics. [bdi.com] But they ended up selling products to DoD which are game-like kinematic simulations. They don't seem to stress dynamics work any more.

      The MIT Leg Lab was taken over by Gill Pratt, who was more of an actuator and controls guy. He didn't accomplish much. The next head of the Leg Lab was some guy who was into prosthetics. The Leg Lab now seems to be defunct. Their web site [mit.edu] hasn't been updated since 1999.

  • iRobot? (Score:3, Insightful)

    by Felinoid ( 16872 ) on Friday June 25, 2004 @04:33PM (#9532697) Homepage Journal
    Something frightening when iRobot [irobotmovie.com] starts violating the 3 laws of robotics before it's even built.
    (Military application would violate "Cause harm" and "alow harm by inaction")
    (Not exact quotes of course I'm being lazy)

    Robot friend? So I finnally get to have a happy chearful elevator that thanks me every time I enter it? Or better yet a paranoid android.
    • You do realize that part of Azimov's theme behind the laws was that they are inevitably contradictory, just as we humans have moral dilemmas, right?
  • From http://www.packbot.com/trackRecord/history.asp

    (.asp, hmm... ;-) )

    iRobot's Aware(TM) operating system, running on Linux, allows our developers to add new functionality, add behaviors that reduce the load on the operators, and add new payloads.

    And those are definitely not toys, actually they've been used (according to the same page) in Afghanistan and Iraq. Moreover, they were patched on the fly:

    We were able to gather user feedback and change the robot and controller software to reflect input from

  • Want real AI? (Score:2, Interesting)

    by CrazyJim0 ( 324487 )
    http://www.geocities.com/James_Sager2/

    I could code it, but I don't want to spend my whole life on it.

    Some other things I knew would happen in 1993 are: MMORPGS, online auctions, online personals, and instant messaging

    I tried coding a MMORPG, but I spent 2000 hours then Ultima Online came out so I gave up.

  • where it appears to support various plug-in modules

    Ultimately, this is where robots will have to go. One of the great things about the PC platform is that we could stick new expansion cards into it, upgrade existing capabilities, add new capabilities, etc.

    We need to be in the same position with robots within a few years. The "modules" will be a lot different, though, and will be as much software based as hardware. We need a module for general processing, vision processing, other sensory perceptions

  • I would think there'd be a useful distinction between "robot" and "bot" -- robots would be something with a physical presence (e.g., an industrial robot or a toy robot), whereas a bot is a software thing that does things autonomously in some fashion. For instance, based on the headline, I thought that this article was about FPS game bots.
  • becoming partners rather than tools - in other words, we'll have friends, not appliances.

    Your plastic pal who's fun to be with! [sadgeezer.com]
  • http://www.packbot.com/products/packbotEOD/feature s.asp
  • Am I the only one who read that as Tactical Missle Robot? I guess I'm just thinking of the LOCAAS system [lockheedmartin.com] I saw at Lockheed Martin. They had a realtime simulation setup where a swarm of these devices took out targets. The targets are preloaded into the system so that the device looks for say, a scud missle truck or a tank, and it could have several targets. Several LOCAAS are launched from aircraft and fly about autonomously until it IDs a target. Then it homes in and destroys it w/ a shaped warhead. It has

  • This old joke is gonna get recycled. (Score:4, Funny)

    by blair1q ( 305137 ) on Friday June 25, 2004 @05:22PM (#9533027) Journal
    I'm not going to update this, I'm just going to let it work for itself.

    Guy is sitting in his upper berth in a sleeper car and hears a strange noise below him. He peeks over, and there's a woman down there, unhooking a prosthetic leg.

    He watches a little more, as she pops out her false teeth and a glass eye.

    She rolls up her sleeve and starts to detach her arm, when she spies him out of her remaining eye.

    "What do you want?" she stage-whispers.

    "You know what I want," he says, "just unscrew it and throw it up here."
  • Yeah whatever, get back to me when I can buy my own bending unit in the store.
  • I really believe the idea of how robots are going to one day be our friend, but in that sense, I figured they'd look more like us. The photos from that post looks like nothing I'd ever have as a friend. Maybe it could be a friend to some lonely kid in a mental institution...
  • we don't yet have a bot that can navigate downtown Manhattan

    That's a problem that is easy to solve, it's just a matter of putting big bumpers on a monster truck. Paying for the damage is the hard part.

Slashdot Top Deals

C'est magnifique, mais ce n'est pas l'Informatique. -- Bosquet [on seeing the IBM 4341]

Close