Slashdot Mirror

← Back to Stories (view on slashdot.org)

Cheap Four-fingered Robot Hand Edges Closer To Human Dexterity

Posted by Soulskill on from the talk-to-the-hand dept.

ananyo writes "A robot that can reproduce the dexterity of the human hand remains a dream of the bioengineering profession. One new approach to achieving this goal avoids trying to replicate the intricacy of the bones, joints and ligaments that produce our most basic gestures. A Sandia National Laboratories research team has adopted just such a strategy by designing a modular, plastic proto-hand whose electronics system is largely made from parts found in cell phones. The Sandia Hand can still perform with a high level of finesse for a robot, and is even capable of replacing the batteries in a small flashlight. It is expected to cost about $10,000, a fraction of the $250,000 price tag for a state-of-the-art robot hand today. The Sandia Hand's fingers are modular and affixed to the hand frame via magnets. This gives the researchers the flexibility to design interchangeable appendages tipped with screwdrivers, flashlights, cameras and other tools. The fingers are also designed to detach automatically to avoid damage if the hand hits a wall or other solid object too hard. The researchers say the hand can even be manipulated to retrieve and reattach a fallen finger. The Hand's current incarnation has only four fingers, including the equivalent of an opposable thumb. In the video with the article, the Sandia Hand demonstrates a number of capabilities, including, perhaps most impressively, dropping a AA battery into a flashlight."

17 of 73 comments (clear)

  1. That's nothing. by bmo · · Score: 3, Funny

    I am running a breeding program to produce smart cats with opposable thumbs on my secret tropical island in the Pacific.

    They can already open their own cans of catfood.

    You are all doomed.

    --
    BMO

    1. Re:That's nothing. by jd2112 · · Score: 2

      Larry Ellison, is that you?

      --
      Any insufficiently advanced magic is indistinguishable from technology.
    2. Re:That's nothing. by furbearntrout · · Score: 2

      YOU are doomed. I, however, give excellent belly rubs.

      --
      Crap. What did the new CSS do with the "Post anonymously" option??
  2. Why is this hard? by Anonymous Coward · · Score: 2, Insightful

    I'm surprised that this and walking are such difficult tasks for robots. I would have thought that reverse engineering the hand would be easy once you've got actuators working. And the human gait has been observed to death and yet we can barely get the robots to walk. It's amazing that these structures we have working examples of cannot be mimiced yet in this day and age. Working consciousness, computer vision, anything that involves some sort of understanding on the part of the machine - I get. But a physical thing like the hand or the human gait? Both seem really well understood.

    But I guess they apparently aren't.

    1. Re:Why is this hard? by Anonymous Coward · · Score: 3, Insightful

      Everything seems simple to the person who isn't trying to do it.

      Practical real world experience tells us how complicated so much of life really is.

    2. Re:Why is this hard? by mdfst13 · · Score: 2

      I'm pretty sure that we can make a robot that mimics the human gait. The problem is that unless we also have the robot mimic the human shape and composition, the robot will fall over while doing so. And that's not the worst problem. The much harder problem is for a robot to do things like change direction while walking. This is the kind of thing that our brains are evolved (or intelligently designed if you prefer) to handle well. It's a complex physical problem involving balancing a number of factors. It's not just copying what humans do; it's copying what we do *unconsciously*.

      You mention that you have no trouble understanding that computer vision is hard. You understand that walking involves vision, right? That's how you avoid walking into things. Walking also involves a sense of balance and other things that you don't get from electric motors.

    3. Re:Why is this hard? by bryonak · · Score: 5, Insightful

      Do this with a friend: place your phone on your open palm. Let your friend repeatedly hit your hand from below, not too hard, but enough to make the phone jump 1-2 cm. You probably won't have any troubles preventing the phone from dropping on the floor.
      Now take two or three pens, stick them between the fingers of your clenched fist and make sure they are somewhat parallel. Place your phone on them and let your friend hit the sticks from below. You probably don't want to do that, as your phone would land on the floor pretty soon. Using sticks that better approximate your hand, or even better, a display dummy hand, won't help much.

      It's not replicating the mechanical arrangement of your joints, but doing something useful with it. The instantaneous sensory feedback your hand gives you about it's own position and the probable position of the phone (pressure, slight air movement, etc), a good deal of which isn't exactly conscious, is quite hard for us to replicate today (with the resources most robotics teams have). Computers still struggle with the fuzzy matching your hand-eye coordination provides to your muscles in order to move in the right direction.
      Add to that the visual tracking problem you mentioned, and it turns into quite a feat.

    4. Re:Why is this hard? by Animats · · Score: 5, Interesting

      I'm surprised that this and walking are such difficult tasks for robots. I would have thought that reverse engineering the hand would be easy once you've got actuators working. And the human gait has been observed to death and yet we can barely get the robots to walk. It's amazing that these structures we have working examples of cannot be mimiced yet in this day and age. Working consciousness, computer vision, anything that involves some sort of understanding on the part of the machine - I get. But a physical thing like the hand or the human gait? Both seem really well understood.

      But I guess they apparently aren't.

      Locomotion is reasonably well understood now, but that took a long time. The posting above illustrates one of the major misconceptions. Locomotion is not about gaits. For over a century, starting when Muybridge took the first movie, people did gait studies and obsessed on footfall patterns. That's all wrong.

      The first big breakthrough was when Raibert built a self-balancing one-legged hopper. With one leg, there aren't many gait options, and balance dominates the problem. Basic balance on the flat is 1) when in contact with the ground, level the body, and 2) when in the air, position the foot for a landing at the point that will result in zero change in speed. Displace the landing point slightly to accelerate or decelerate.

      On the flat, it's all about balance. Once you get off flat surfaces, traction control starts to dominate the problem. I did some work on that. It's like ABS for feet; the robot must keep side forces below the break-loose point.

      Once you have basic traction and balance, gait is an emergent behavior. Which foot can most usefully achieve the traction and balance goals? (With more than 4 legs, there are many options.) When something is maneuvering fast or recovering from an upset, there's concept of repetitive "gait". It's more of an asset management problem. Look at some of the Big Dog videos in detail to see this.

      Robot manipulation has been underestimated for decades, too. McCarthy once thought it was going to be a summer project to program a robot to assemble a Heathkit TV set kit. Big underestimation. That's still beyond the state of the art. (Stanford actually bought the TV set kit, which was finally assembled by some student and put in the CS department lounge.)

      Robots manipulate all sort of useful things in controlled environments, but manipulation in uncontrolled environments is still very poor. Willow Robotics has demonstrated towel and sock folding, which is cutting-edge work. The DARPA ARM program, not so much.

      Progress is picking up now that enormous compute resources can be devoted to the problem. It will pick up further when a simulator good enough to debug in is developed. DARPA is funding Willow Garage to upgrade Gazebo to do that. I suspect that the physics engine Gazebo uses is not up to the job, but that can be fixed by applying enough money.

      Money is important here. We're now at the point where throwing money at robotics produces real progress. That wasn't true 20 years ago, when NASA blew something like $100 million on the Flight Telerobotic Servicer and got zip.

    5. Re:Why is this hard? by localman · · Score: 2

      Now that's the kind of Slashdot comment I miss. Thanks for the enlightening info!

  3. Cheaper than this by Spy+Handler · · Score: 2

    the "$250,000 state-of-the-art robot hand"

  4. But I Still Have All My Fingers by nikolardo · · Score: 2

    This kind of thing makes me almost wish I'd lost a finger or a hand sometime. Screwdrivers? Cameras? Flashlights? Fingers that FALL OFF instead of HURTING when they get hit? My flesh-and-bone phalanges take too long to heal as it is. Next time I hurt one, it's coming right off.

  5. Why not just 3 fingers, indeed? by bdwoolman · · Score: 2

    I saw a documentary once about some poor Chinese guy who lost all his fingers in some kind of accident. The Chinese doctors removed some of his toes (the guy had pretty long toes) and ginned up a three-fingered hand for him with, of course, toes for fingers. It appeared to work really well. The guy seemed damned happy about it. Come to think of it, I would be, too.

    I looked briefly for a link to the old China story, but only came up with an upbeat human interest yarn about an American guy born with two fingers on one hand getting this same operation. He was fine with his congenital two-fingered hand but needed a toe transplant only after he cut off one of the two fingers on his defective hand using a table saw. After some physio he is doing better with three than he did with two. Even if two of them were (are?) toes. Which, frankly, comes as no great surprise.

    So I guess a robot with three fingers would be pretty functional, too.

    --
    "No fear. No envy. No meanness." Liam Clancy
  6. Gives a whole new meaning by ilikenwf · · Score: 2

    ..to giving someone the finger!

  7. Have to steal and attach another one by Dareth · · Score: 2

    Have to steal and attach another one to actually have a middle finger to give!

    --

    I only look human.
    My mother is a halfling and my dad is an ogre, so that makes me an Ogreling
  8. Re:Not just the dream of bioengineering profession by Lord_of_the_nerf · · Score: 3, Funny

    I see what you did there.

    It says 'flashlight' not 'fleshlight'.

  9. How will they count to 10, with 8 fingers? by Brad1138 · · Score: 2

    Seriously though, I have always wondered, if we had 8 total fingers/thumbs, would we have a base 8 number system?

    --
    If you could reason with religious people, there would be no religious people
  10. All This And Flying Cars Too by fm6 · · Score: 2

    This exemplifies why Science Fiction was too optimistic when it assumed that robots (real thinking robots, not the programmable waldos that presently go by that name) would be ubiquitous by now. The basic things humans can do — parse visual data, parse language, manipulate object, make decisions based on complicated data sets — appear to be simple, but are actually complicated processes that resulted from millions of years of evolutionary tweaking.

    I'd mention the problems with the Three Laws of Robotics, but that always starts a flame war with some rabid Asimov fan, so I'll refrain. I will say that I think that machines that can truly think are still a long way away, and when they do appear they'll be as different from us as airplanes are from birds.