Slashdot Mirror


Robotic Whiskers Sense Shape and Texture

An AC writes,"NewScientistTech has a story about robotic whiskers capable of sensing shape and texture in a similar way to those belonging to rats and seals. The 'bending moment,' or torque, exerted at the base of each whisker is used to extract feature information. The artificial whiskers could be used on interplanetary rovers, or allow underwater vehicles to track moving objects by their wake. Check out the slightly creepy video of them stroking a sculpted face."

59 comments

  1. Rats and Seals? by Blakey+Rat · · Score: 4, Funny

    I have to tell you that my cat is sitting right here on my desk and she's PISSED!

    1. Re:Rats and Seals? by Bob54321 · · Score: 0, Offtopic

      I thought we could all avoid jokes involving the word "pussy" but now you've gone at let the cat out of the bag...

      --
      :(){ :|:& };:
    2. Re:Rats and Seals? by AmberBlackCat · · Score: 1

      That's right. I'm pissed.

    3. Re:Rats and Seals? by MCRocker · · Score: 4, Funny
      I have to tell you that my cat is sitting right here on my desk and she's PISSED!
      Ewww! That can really mess up your keyboard :(
      --
      Signatures are a waste of bandwi (buffering...)
    4. Re:Rats and Seals? by Anonymous Coward · · Score: 0

      You're cat is pissed? I though she was just a pussy.

    5. Re:Rats and Seals? by SchwarzeReiter · · Score: 1
      I have to tell you that my cat is sitting right here on my desk and she's PISSED!
      Take the monitor down from her tail.
  2. Um... Really lame video by BadAnalogyGuy · · Score: 0

    It would have been nice to see the whiskers deliver the information to allow a computer to draw what it was sensing. Dragging a model head across the feelers without any feedback wasn't exactly a convincing demo.

    1. Re:Um... Really lame video by Who235 · · Score: 1
      Dragging a model head across the feelers without any feedback wasn't exactly a convincing demo.

      I agree.

      Plus they should have waited until that Chia-pet was fully developed before subjecting it to the rigors of a lab environment. I suspect that it will never be able to grow a uniform coat of sprouts now, thanks in large part to the creepy whiskers dragged across its face for (no doubt) hours at a time.
  3. Re:Moo by BadAnalogyGuy · · Score: 0, Flamebait

    God may have given cats, rats, and seals environment-sensing whiskers, but it will be a scientist that gives them to humans.

  4. BK-wired. by Anonymous Coward · · Score: 0

    "Check out the slightly creepy video of them stroking a sculpted face."

    The King doesn't mind.

    ---

    "Slashdot requires you to wait between each successful posting of a comment to allow everyone a fair chance at posting a comment."

    TRM comes to slashdot.

  5. they make a sound.... by macadamia_harold · · Score: 1

    NewScientistTech has a story about robotic whiskers ... Check out the slightly creepy video of them stroking a sculpted face.

    They seem to be making a noise.. it sounds like "Ph'nglui mglw'nafh Cthulhu R'lyeh wgah'nagl fhtagn"

    1. Re:they make a sound.... by mattcoz · · Score: 0

      Well isn't that great, we're creating robots with the desire to wake ancient evil creatures. This really ruined my day.

  6. Re:Moo by PresidentEnder · · Score: 2, Insightful

    While I myself am a christian, to simply state your beliefs as fact and deride others without making logical arguments only drives people away from the very beliefs you want to convince them of.

    --
    I used to carry a bottle of whiskey for snake bite. And two snakes. -Nefarious Wheel
  7. Re:Moo by 8ball629 · · Score: 1

    Since when is looking to nature, looking to God?

    Anyway, it sounds like this technology will soon be used by the Navy.

  8. interesting point //Re:Um..Really lame video by Anonymous Coward · · Score: 5, Informative

    Hi, I'm one of the authors of the paper.

    I think what you are suggesting is that there should be simultaneous video of (1) the whiskers sweeping over the sculpted head, and (2) the computer drawing the image generated by the whiskers. Is that what you mean by "feedback?" If so, you're right, that would be a more convincing video. However, the system doesn't yet operate in real time. Real time operation wasn't our goal. Our goal was to illustrate the basic mechanical principle (bending moment alone gives you all the info you need, even in the presence of significant slip), and to demonstrate that this principle could work for both robots and rats (and seals, underwater)

    The video posted here was intended to give an intuitive impression of the size of the whiskers compared to the head, the speed of the whiskers (currently slow, but that could be changed), the extent that the whiskers "slip" when they hit the head. The fact that the whiskers slip so much makes feature extraction really difficult, especially with no force sensors.

    Thus, while I understand that you're dissapointed that we didn't have real-time image extraction, I take issue with the epithet "lame" as applied to our video. ;-) Real-time extraction wasn't the point of the paper. But thanks for your comments -- always interesting to hear different perspectives.

    1. Re:interesting point //Re:Um..Really lame video by BadAnalogyGuy · · Score: 1

      I don't think realtime data analysis is necessary to have a good demo. But when you're showing off the technology, it's got to be more than just dragging a couple wires across a dummy.

      I recommend taking down the "demo" as it serves no purpose except to make people question the project and the people behind it. Better to have a good paper and let the audience imagine how terrible the technology is than to give a demo that removes all doubt.

      Not that it's terrible technology, of course. Just that you wouldn't know it from the demo video linked to from this article.

    2. Re:interesting point //Re:Um..Really lame video by Anonymous Coward · · Score: 5, Informative

      Remember that the media puts a very different spin on things than scientists and engineers might if they were presenting the work. We have virtually no control of the spin that any given website chooses to put on the article. Apparently this website has given the impression that the video is a "demonstration" of the technology. If I were presenting this video to an audience, I would not say that this was a demo, but rather that it is an illustration of how difficult the sensing problem is. Then I would explain our algorithm in some detail, describing how we overcame the obstacles exemplified in the video.

      So when you say that the video has no purpose -- I think that is a result of the website not explaining the video correctly. The primary purpose of the video is to illustrate how hard the sensing problem is. How would you cope with the whiskers slipping and sliding all over the object, if you only had a sensor at the base of the whisker? It's a hard problem!

      If the video is interpreted as a "demo," then it is a better demo if you look at the computer-generated image that the whiskers were able to extract. See the figure in the original article. The head on the left is the original sculpture. The image on the right is the sculpture as reconstructed by the whiskers.

      You are absolutely correct that it's important to have a good paper when showing any scientific work. The peer-reviewed paper will appear in Nature tomorrow.

    3. Re:interesting point //Re:Um..Really lame video by BadAnalogyGuy · · Score: 1

      I think you underestimate my ability to cope with whiskers slipping and sliding all over my face.

      That came out wrong...

    4. Re:interesting point //Re:Um..Really lame video by ortholattice · · Score: 2, Interesting

      Yes, the video should be viewed in the context of the final image it reconstructs. Once you see the final image - shown on the article page for the 99% of readers who clicked on the video but didn't RTFA (a hyperlink labeled "video" being the /. equivalent of "ooh, shiny button") - it is pretty damn impressive that the information can be extracted from such "crude"-looking stroking. Although it's somewhat eerie that the original sculpture looks vaguely "female", whereas the reconstructed image looks vaguely "male". Also, the video was painful to look at - I grimaced at the thought of that thing poking me in the eye...

    5. Re:interesting point //Re:Um..Really lame video by HorsePunchKid · · Score: 1
      ...it is a better demo if you look at the computer-generated image that the whiskers were able to extract. See the figure in the original article.

      So you're suggesting I should read the article before drawing conclusions about your research? I can't imagine how that will help, but I guess I could give it a shot just this one time...

      --
      Steven N. Severinghaus
    6. Re:interesting point //Re:Um..Really lame video by Anonymous Coward · · Score: 0

      >Although it's somewhat eerie that the original sculpture looks vaguely "female", whereas the reconstructed image looks vaguely "male".

      Thanks for pointing this out. The faces do look somehow "different." What's particularly odd is that if you look at individual facial features -- the eyes, nose, mouth, eyebrows, cheeks -- the individual features look more similar to each other than the two faces do.

      We're not quite sure how to account for this, but our best guess is that it is a perceptual effect having to do with how good we humans are at face recognition. Somehow the "gestalt" of the face appears different even if the individual features appear mostly similar. Perhaps an artist could comment on this phenomenon.

  9. Artificial Skin; Animal-Like Robots? by Garrett+Fox · · Score: 5, Informative

    These whiskers tie in with existing research into artificial skin that can "feel." This 2005 NASA article describes mecha-skin that uses IR sensors to detect touch. Japanese researchers (2005) reported having a type that senses temperature and pressure through actual touching.

    The skin research should be useful both for robotics and for replacement parts for humans, as an alternative to the clunky biological hand transplants that have been carried out. (I think I'd rather have a Luke Skywalker robot hand than a mismatched corpse's!) These artificial hand researchers will probably be interested as well, because having a prosthesis that can be sensed as well as controlled is necessary for it to be as good as the original. The big issue is how easy it will be to get these touch signals into the human nervous system in a useful way. For robots, the data can be built into existing software for making maps of a robot's surroundings. I picture a robot rat running a maze with a set of these whiskers. Won't whiskers serve as a low-energy-cost alternative to sonar and other sensing systems?

    The odd thing is that here, the research is not into copying human abilities, but those of (nonhuman) animals. I wrote a silly article arguing that future robots will be made to resemble animals, not humans, and Charles Van Doren (in A History of Knowledge) predicted "warm and fuzzy" robotics. Is that where we're headed?

    --
    Revive the Constitution.
    1. Re:Artificial Skin; Animal-Like Robots? by Rowanyote · · Score: 1

      Animal shaped robots avoid the problems associated with the uncanny valley http://en.wikipedia.org/wiki/Uncanny_Valley

  10. Re:Moo by Anonymous Coward · · Score: 4, Funny

    God has already given me this ability. I like caving, and I have grown a moustache the same width as my body to stop me from getting trapped in narrow caves.

  11. Biomimetics by Garrett+Fox · · Score: 3, Insightful

    (Deist) Thomas Paine's The Age of Reason argued that Nature is the only reliable scripture!

    Actually there's a whole field of "biomimetics" that recognizes that evolution has solved a lot of engineering problems already, giving us clues into things like ideal shapes for sails (birds' wings) and durable macro-scale materials (beehives). The trick to that field is in figuring out what aspects of nature to imitate; for instance, the Wright Brothers studied birds but didn't feel compelled to build a true "ornithopter" or glue feathers on their Flyer. Nature has to operate under a very different set of constraints: no foresight, no metal smelters, etc.. One description I read somewhere was to imagine a human having to design a car that grows from motorcycle to sedan size and is capable of self-driving, self-fueling, and reproduction! So, we're not just "looking to nature," but figuring out what parts of it are worth stealing.

    --
    Revive the Constitution.
  12. Re:Moo by prichardson · · Score: 3, Interesting

    Assuming the existence of God:

    If God had taken out patents, people would be able to reference them, a good thing. We could probably cure cancer, and the whole Human Genome thing wouldn't have been necessary.

    Also, they would have expired twenty years after they were granted, so they'd be public domain now anyway.

    If only God actually HAD taken out patents...

    --
    Help I'm a rock.
  13. Re:Moo by Anonymous Coward · · Score: 1, Funny

    Back when I had a beard, I could tell when my girlfriend was going to come by sensing the change in the tension of her thigh muscles.

  14. Robotic Whiskers? by BigRockinDaddy · · Score: 2, Funny

    I guess it was just me that read the article and thought, "Hmmm, high-tech curb feelers". Just what the moon rover was missing. Next they can create fuzzy dice that mimic a birds direction sense.

  15. Conspiracy by suv4x4 · · Score: 2, Funny

    I believe this is some sort of real piece of conspiracy going on here.

    So QRIO and AIBO were discontinued, but almost every next day you can read about yet another freeky appendage or a robot designer to be inserted up your ass and crawl your intestines.

    What are these guys preparing for us !?

    Man, I'm so no taking the red pill.

    1. Re:Conspiracy by suv4x4 · · Score: 3, Funny

      or a robot designer to be inserted up your ass

      ok.. that was a curious type of typo to make...

  16. I for one... by commisaro · · Score: 2, Funny

    ... welcome out new tentacled robotic overlords.

  17. Re:Moo by MSTCrow5429 · · Score: 1

    Most scientists are not atheists.

    Putting a dash for the "o" in "God" is a misinterpretation of Scripture.

    --
    Slashdot: Playing Favorites Since 1997
  18. Re:Moo by DuChamp+Fitz · · Score: 1

    don't you mean "deny H-m", I mean, you don't want to piss H-m off, do you?

  19. Re:Moo by Vicious+Blayd · · Score: 1

    Anyway, it sounds like this technology will soon be used by the Navy.

    Thus giving an altogether more literal definition to "Navy SEALs."

  20. Question by tygerstripes · · Score: 2, Interesting
    Hi,

    Thanks for posting - it is a really interesting concept and I'm glad you're doing the work (though if you need another test-dummy, count me out please). I hope you'll post another article once you've got a shiny real-time working model that maps onto a monitor - this is slashdot after all :-P

    I have a question though. Is the length of the whiskers pre-defined in constructing the image? Mammal whiskers are always growing, falling out, getting clipped (burned, in my cat's case - "ooh, that candle looks shiny..."), but they learn how to interpret and adapt to their whisker-sense. Presumably at this early stage it would be impossible to generate appropriate feedback for such learning, but do you intend to have similar learning algorithms going on with your whiskers at a later stage? With something as independent and unmaintainable as rovers, I would think it critical to account for whisker-damage in this way.

    Another point that interests me is that of whisker-friction. If the whiskers could sense whether they were being "pulled" or not by friction on a surface, that might provide some useful (or at least interesting) information on the texture of an object, and wouldn't add significantly to the weight or complexity of the sensing apparatus, I suspect.

    I'd be really interested to hear what you think.

    --
    Meta will eat itself
    1. Re:Question by Anonymous Coward · · Score: 0

      >I have a question though. Is the length of the whiskers pre-defined in constructing the image? Mammal whiskers are always >growing, falling out, getting clipped (burned, in my cat's case - "ooh, that candle looks shiny..."), but they learn how to >interpret and adapt to their whisker-sense.

      That's an interesting question, and there are really two answers. First, if the whiskers are cylindrical (as the wires on our robot are), then it turns out that the the length doesn't matter to the estimate of distance. By measuring the bending moment at the base of the whisker, we can determine the distance out along the whisker where it contacted the object, without knowing the absolute length of the whisker. Second, the whiskers of a real rat (or seal) are not actually cylinders. They are tapered, so as to form a cone. In the conical case, the length of the whisker does matter to the estimate of distance. This implies that the rat has to have some "mental," or learned model of how a whisker of a particular length interacts with the environment. If the whisker length changes, it has to relearn the mapping between bending moment and distance. This might sound complicated, but it's actually not that unusual. For example, think about how quickly you can adjust to wearing gloves or not wearing gloves, or wearing steel-toed boots, or any number of sensorimotor perturbations.

      This might lead you to wonder -- why would rats have tapered whiskers instead of cylindrical ones. If their their whiskers were cylindrical, then they wouldn't have to learn a remapping if their whiskers were damaged. We don't entirely know the answer to this question, but we think it has something to do with the location of the "sweet spot" on the whisker -- that is, the region of contact where the whisker is most sensitive to changes in bending moment. The whiskers also have an inherent curvature that is likely to affect their response properties.

      > Another point that interests me is that of whisker-friction. If the whiskers could sense whether they were being "pulled" or >not by friction on a surface, that might provide some useful (or at least interesting) information on the texture of an object, >and wouldn't add significantly to the weight or complexity of the sensing apparatus, I suspect.

      This is another great question. The model that we have published (so far) assumes no friction. However, we are currently running tests on real rat whiskers to see what kinds of axial forces are generated. We think that the "pulling" force you suggest might help determine how far the whisker has gone past an object. The way that we think rats are determining texture is through the vibrations of their whiskers as they run them over different surfaces. These vibrations are likely to interact with the natural resonance properties of the whisker.

      Thanks for your interest! We have a lot fun with this work and enjoy sharing it with others.

    2. Re:Question by tygerstripes · · Score: 1
      God, this is the most interesting and intelligent discussion I've ever seen on Slashdot! More articles by researchers please, Editors!

      The change in cross-section hadn't occurred to me - which just goes to show how long it's been since I did Civil Engineering! Biologically speaking I suspect the shape of whiskers is a combination of the fact that they're specially adapted hairs, and the importance of keeping whiskers light and flexible. My structural mechanics is rusty, but I think a rigid, fixed-cross-sectional whisker would experience a significant stress due to internal bending moment along its length that increases by square along its length (from the free end), while the gradient of a graph mapping length against stress in a conical whisker decreases - partly due to the end being lighter, and partly due to the base cross-section increasing with length. If I had to design a free-ended beam, I'd make it taper. This also means that it can be made of a flexible material instead of maintaining rigidity along its length, which is of obvious benefit in the real world.

      Also, growing a thick fixed-section hair from scratch would, I imagine, be as irritating as all hell (if my girlfriend's whining about shaving is anything to go by).

      Anyway, I have to go and teach my gran to suck eggs, so I'll stop here. I shall definitely be keeping an eye out for that Nature publication...

      --
      Meta will eat itself
  21. Re:www.VerySimpleDrive.com by somersault · · Score: 0, Flamebait

    Why don't you try posting some constructive comments, and putting the link to that page in your signature (where it may actually be regarded as a useful link and not spam). Anyone with any morals would now not use that site just because of your flagrant advertising, and anyone who actually needs that hopefully knows how to use Google to find a storage site, or even just setup their own hosting.

    --
    which is totally what she said
  22. Re:Moo by Plutonite · · Score: 1

    ???

    Beard?

  23. Re:Moo by bogado · · Score: 1

    Is an exercise to the reader to figure out what he was doing with his girlfriend. ;-)

    --
    []'s Victor Bogado da Silva Lins

    ^[:wq

  24. This is old technology, I did this as a Senior HS by MrJerryNormandinSir · · Score: 1

    Man this is old stuff. I created wiskers for an Atari 400 computer way back in the early 80s. I was a Sr. In high school.
    The wiskers could detect a ball, box, wrench, dog bone, and pencil. Basiclly the wiskers were conductive and protruded through
    a conductive metal plate with circular holes for the "wiskers to poke through" Normaly the circuit was open.
    When an object brushed against the sensors it will close the circuit and I would detect a pattern. I had many different patterns
    stored for each object. The object detected was based on scoring, The highest score was detected as the image, if the image was detected wrong, that would get factored into my "learning" record. So the program got smarter. It was 1980 when I wrote this.
    I used a parallel to serial converter circuit to get the wisker pattern to the Atari 400. I thought it was "simple" stuff back then.

    Now that I'm 43 years old I realize the code was ahead of it's time.

  25. Re:Moo by stunt_penguin · · Score: 1

    Well thank fuck someone came out and said it. I'm a Catholic but for anyone to shove it down another's throat (even in flaming) is unacceptable and does the Church more harm than good. Fucking zealous pricks.

    --
    When the posters fear their moderators, there is tyranny; when the moderators fears the posters, there is liberty.
  26. Re:Moo by Chacham · · Score: 1

    only drives people away from the very beliefs you want to convince them of.

    Actually, that wasn't my intention at all. :)

  27. Re:Moo by Chacham · · Score: 1

    If God had taken out patents, people would be able to reference them, a good thing.

    Well, after they learned the language...

    We could probably cure cancer, and the whole Human Genome thing wouldn't have been necessary.

    More accurately, we'd be closer, if the goal is possible.

    Also, they would have expired twenty years after they were granted, so they'd be public domain now anyway.

    Which would destroy current patents...

  28. Re:Moo by Chacham · · Score: 1

    Most scientists are not atheists.

    Tell that to Slashdot.

    Putting a dash for the "o" in "God" is a misinterpretation of Scripture.

    Oh? Do you have any idea *why* i put the dash there, to then state that is a misinterpretation?

  29. Fast! by epp_b · · Score: 1

    Wow! That video downloaded at 800KB/s...I must be early.

  30. Re:This is old technology, I did this as a Senior by SpinyNorman · · Score: 1

    The system described isn't quite the same... the innovation is that they are using 2-D torque sensors on the whiskers, and apparently are able to reconstruct the 3-D surface of the object whiskered using the data... that's a rather major improvement over just detecting a profile with on/off switches! ;-)

  31. Re:This is old technology, I did this as a Senior by MrJerryNormandinSir · · Score: 1

    They should have improved on it, man I did this 27 years ago! I wasn't going agter 3D surface reconstruction, I was going after
    object recognition, and a self learning applicaiton. This is much more than just detecting a profile.

  32. Re:Moo by MSTCrow5429 · · Score: 1

    There's only one reason I've seen for the dash before. What reason did you put the dash in there for?

    --
    Slashdot: Playing Favorites Since 1997
  33. Re:Moo by Chacham · · Score: 1

    What reason did you put the dash in there for?

    Out of respect. Not to just throw G-d's name (proper noun) around.

    Basically, Jewish law (Yorah Deah, Hilchos Sefer Torah) forbids erasing G-d's name. So, many have accustomed themselves to not write G-d's name in Hebrew outright. This means leaving out a letter, or using the wrong letter (e.g. daleth instead of hay) or using a dash in between the letters, which is very common when the intent is not to write G-d's name, but use a name that include's one. This is not required, but is a custom based on respect and a "fence".

    Many have carried this custom over to other languages.

  34. Re:Moo by MSTCrow5429 · · Score: 1

    I'm a Jew, and Rabbi Telushkin points out that placing a dash in God is based on a misreading of Torah. See "A Code of Jewish Ethics: Volume 1: You Shall Be Holy." I can't remember the exact passage, as it was from a library book. Although the reason you give is a different reason, partly.

    --
    Slashdot: Playing Favorites Since 1997
  35. Re:Moo by Chacham · · Score: 1

    Rabbi Telushkin points out that placing a dash in God is based on a misreading of Torah.

    And i will point out that Rabbi Telushkin is wrong.

    See "A Code of Jewish Ethics: Volume 1: You Shall Be Holy." I can't remember the exact passage, as it was from a library book.

    No thanx. I don't really care enough to go get the book to see some passage that i know to be incorrect. However, if you feel so inclined, you may point it out to me, and i will show you the fallacy.

    Although the reason you give is a different reason, partly.

    The reason that i gave is _the_ reason Orthodox Jews do it (not everyone has the custom, however). Respect for G-d's name is a major part of halachah, the foremost case is one of the Ten Commandments, and plays a major part of Hilchos B'rachos.

  36. Re:Moo by MSTCrow5429 · · Score: 1

    Rabbi Telushkin is an Orthodox Rabbi, though.

    --
    Slashdot: Playing Favorites Since 1997
  37. Re:Moo by Chacham · · Score: 1

    Rabbi Telushkin is an Orthodox Rabbi, though.

    So?

    Either he has it correctly, or he doesn't. And i do not believe that he does. As i have mentioned the reason. And i can quote chapter and verse, Siman and S'if, for the relevant laws, and i know why people do it in Hebrew, and i know that it has carried over into English.