Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Cheap Four-fingered Robot Hand Edges Closer To Human Dexterity

Soulskill posted about 2 years ago | from the talk-to-the-hand dept.

Robotics 73

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."

cancel ×

73 comments

Sorry! There are no comments related to the filter you selected.

Perhaps they can make robotic Obama (-1)

Anonymous Coward | about 2 years ago | (#41075413)

That actually has a brain.

http://25.media.tumblr.com/tumblr_m94ibsqQMr1ruplzzo1_500.jpg

Not just the dream of bioengineering profession (0, Offtopic)

Anonymous Coward | about 2 years ago | (#41075439)

Owners of adult book and sex toy shops everywhere eagerly await that windfall.

Re:Not just the dream of bioengineering profession (0)

Anonymous Coward | about 2 years ago | (#41075871)

I was kind of disappointed with the video; I was hoping for a FULL demonstration of it's capabilities.

Re:Not just the dream of bioengineering profession (3, Funny)

Lord_of_the_nerf (895604) | about 2 years ago | (#41076589)

I see what you did there.

It says 'flashlight' not 'fleshlight'.

Re:Not just the dream of bioengineering profession (1)

Anonymous Coward | about 2 years ago | (#41078025)

Why would you even NEED a fleshlight if you had robotic grip like that!

Re:Not just the dream of bioengineering profession (1)

Impy the Impiuos Imp (442658) | about 2 years ago | (#41081441)

> A robot that can reproduce the dexterity of the human hand

"No. We are not adding that as a UML use case."

That's nothing. (3, Funny)

bmo (77928) | about 2 years ago | (#41075443)

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

Re:That's nothing. (2)

jd2112 (1535857) | about 2 years ago | (#41076665)

Larry Ellison, is that you?

Re:That's nothing. (2)

furbearntrout (1036146) | about 2 years ago | (#41078435)

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

Why is this hard? (2, Insightful)

Anonymous Coward | about 2 years ago | (#41075483)

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.

Re:Why is this hard? (3, Insightful)

Anonymous Coward | about 2 years ago | (#41075717)

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.

Re:Why is this hard? (2)

mdfst13 (664665) | about 2 years ago | (#41075793)

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.

Re:Why is this hard? (5, Insightful)

bryonak (836632) | about 2 years ago | (#41075955)

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.

Re:Why is this hard? (5, Interesting)

Animats (122034) | about 2 years ago | (#41077377)

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.

Re:Why is this hard? (1)

Animats (122034) | about 2 years ago | (#41077387)

(Sorry, "no concept of repetitive gait.")

Re:Why is this hard? (2)

localman (111171) | about 2 years ago | (#41078273)

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

Re:Why is this hard? (1)

olau (314197) | about 2 years ago | (#41079275)

Agreed. Thanks!

Re:Why is this hard? (1)

Anonymous Coward | about 2 years ago | (#41077581)

I'm surprised that this and walking are such difficult tasks for robots.

This is because walking feels easy to you. It feels easy to you because all of the heavy computation is being done subconsciously, so from introspection you really have no way to know how difficult it is. It's just like vision in that respect. The main thing to realize is that when you walk you are NOT repeating the same actions over and over - that you appear to be doing so is a major achievement of your brain. Your brain is continuously changing your steps and posture based on feedback from your entire body. It just so happens that the mapping from input to movements that your brain is making is far more complex than what it would seem like to you based on introspection. It's the same thing in vision - if I rotate an object in front of you it will not appear to you that the object is changing even though the visual impression the object is making on your eyes changes dramatically, so your brain is doing some impressive computation that you never get to observe.

Re:Why is this hard? (1)

DarwinSurvivor (1752106) | about 2 years ago | (#41077977)

Regarding walking, try walking (or standing) with half-spheres glued to the bottoms of your feet (flat side up). You'll quicly realize how much "walking" involves minute sensory perception in the soles of the feet feeding even more minute changes in the weight being moved between your feet and ankles and each side of your foot.

Re:Why is this hard? (1)

Anonymous Coward | about 2 years ago | (#41077987)

They have had robot hands for a long time (walking has different issues of changing centroids and keeping balance) they just cost a lot of money.

Why are things so expensive (0)

Anonymous Coward | about 2 years ago | (#41075519)

I officially announce an ardiuno contest, for person to make a working hand without a spending 10,000-250,000 dollars, wins some glory or something...

Re:Why are things so expensive (1)

Em Adespoton (792954) | about 2 years ago | (#41075617)

Mostly the people doing this for $75 don't have to publish to the media and the journals to keep their funding coming :)
Time to go home and play table tennis with my robot.
.
.
.
.
.
I joke. Just think about how much it costs to build a human who can do these things? It takes an expensive year or so of constant biofeedback, fueling, and training for people to accomplish these tasks, and they already have all the required actuators and sensors.

I never asked for this (0)

Anonymous Coward | about 2 years ago | (#41075535)

...but I want it anyway.

Code name: "Rosie" (0)

Anonymous Coward | about 2 years ago | (#41075553)

Come on, you know you were thinking about it.

Re:Code name: "Rosie" (0)

Anonymous Coward | about 2 years ago | (#41076631)

I knew there would be a Rosy Palm, or a Mary Five-fingers joke in here, somewhere!

Re:Code name: "Rosie" (1)

wierd_w (1375923) | about 2 years ago | (#41084003)

No! Its Palmula! Palmula Handerson!

Why not just 3 fingers? (1)

mister_playboy (1474163) | about 2 years ago | (#41075561)

Seems like an arrangement of two fingers on one side and an opposed thumb on the other would be sufficient.

This would also be a little less "uncanny valley".

Why not just 3 fingers, indeed? (2)

bdwoolman (561635) | about 2 years ago | (#41075999)

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. [liveleak.com] 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.

Re:Why not just 3 fingers, indeed? (1)

thelexx (237096) | about 2 years ago | (#41077735)

Reading on the subject (hand issue with a close family member) tells me that using toe joints to regain some finger functionality is not unknown in Western medicine currently. And I would speculate that a large part of the issue with five v. three is the cosmetic effect. This really can't be underestimated. It's the reason why many who currently can use a traditional clasping-hook prosthesis choose not to.

BTW and kinda-on-topic - IMO the current state-of-the-art in hand prosthetics is from Touch Bionics [touchbionics.com] . Great, great stuff. Here's hoping that over the next decade or so we see some real progress in this area, for children as well as adults. Hat's off to Nemours [nemours.org] and their use of 3D-printing [youtube.com] .

Re:Why not just 3 fingers, indeed? (1)

sjames (1099) | about 2 years ago | (#41085387)

Interestingly, when toes are transplanted to act as fingers, they come to resemble fingers after a while.

Form follows function. (1)

bdwoolman (561635) | about 2 years ago | (#41087637)

That is interesting. Where did you find that out? It's too cool. Is the increased activity causing some stem cells to trigger and develop new tissue?. How does the toe somehow know? Thanks sjames.

I don't know if you watched the clip I linked to, but the guy had seemingly had higher functionality in the end with his toe fingered hand than he did with his congenitally disabled hand. Hopefully he stays away from his table saw.

Re:Form follows function. (1)

sjames (1099) | about 2 years ago | (#41087925)

I'm not honestly sure where I first saw that, but I think it was a documentary on Discovery.

I imagine part of it is simply a matter of customary use resulting in remodeling, more or less the way bone and muscle change if you exercize them.

Why the electronic glove? (1)

Dwedit (232252) | about 2 years ago | (#41075571)

Making a glove?
Why make an electronic glove when you can wear a specially printed regular glove and use several cameras to see where everything is?

But I Still Have All My Fingers (2)

nikolardo (2266242) | about 2 years ago | (#41075595)

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.

Perhaps not (1)

delta42 (1882902) | about 2 years ago | (#41075615)

"perhaps most impressively, dropping a AA battery into a flashlight"

The hand struggles with the insertion and then the video is cut right before the flashlight is about to fall.

I do not mean to pry... (0)

Anonymous Coward | about 2 years ago | (#41075635)

but you don't by any chance happen to have 6 fingers on your right hand?

Dj Mixer (0)

Anonymous Coward | about 2 years ago | (#41075675)

I find it interesting that they are apparently using a DJ oriented USB/MIDI Controller - albeit possibly just using the crossfader to control speed ( or tempo ) - of movement through a the pre-programmed (MIDI?) sequence.

I for one (1)

simonbp (412489) | about 2 years ago | (#41075783)

Do not think that the four-fingered hands of our robotic overlords are cartoonish at all.

hell yeah Midi controller! (0)

Anonymous Coward | about 2 years ago | (#41075809)

Let's see your vinyl control a robot!

Gives a whole new meaning (2)

ilikenwf (1139495) | about 2 years ago | (#41076305)

..to giving someone the finger!

Have to steal and attach another one (2)

Dareth (47614) | about 2 years ago | (#41076461)

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

four finger discount? (1)

Gravis Zero (934156) | about 2 years ago | (#41076361)

now that they have decent hands, we will have robots stealing our cereal. they're always after me lucky charms.

So, when do I get my robot maid? (1)

FridayBob (619244) | about 2 years ago | (#41076439)

As I was saying, a robot maid is far more convenient than a flying car. It may take me longer to get home in a normal car, but once I get there my house will be clean, my clothes folded, my lawn will be cut, my trash will be out and there will be food on my table.

Mandatory 'Addams family' walking hand reference (1)

sonamchauhan (587356) | about 2 years ago | (#41076465)

(end of message)

How will they count to 10, with 8 fingers? (2)

Brad1138 (590148) | about 2 years ago | (#41076749)

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

Re:How will they count to 10, with 8 fingers? (1)

BradleyUffner (103496) | about 2 years ago | (#41077043)

Easy, they just count to 12 instead.

Re:How will they count to 10, with 8 fingers? (0)

Anonymous Coward | about 2 years ago | (#41078275)

counting to ten with 4 fingers:
0001 = 1
0010 = 2
0011 = 3
ect
1010 = 10

Re:How will they count to 10, with 8 fingers? (1)

Hillgiant (916436) | about 2 years ago | (#41080225)

Pff. It's easier than that:

00
01
10
done.

Interesting Video (0)

Anonymous Coward | about 2 years ago | (#41076751)

...which was completely ruined by the music. I get that you're showing off something futurist, but I'm not watching a fan-made video for my favorite band.

All This And Flying Cars Too (2)

fm6 (162816) | about 2 years ago | (#41076799)

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.

Re:All This And Flying Cars Too (1)

funky_vibes (664942) | about 2 years ago | (#41079383)

I don't think it was that optimistic, how were they supposed to know that computing development would virtually come to a halt for 20 yrs?

Re:All This And Flying Cars Too (1)

fm6 (162816) | about 2 years ago | (#41082233)

Excuse me? Come to a halt? Moore's Law is a myth? All those university compsci departments are just shams?

Re:All This And Flying Cars Too (1)

cellocgw (617879) | about 2 years ago | (#41082831)

I suspect the GP's post about 20 years' halt in development refers to either or both of the lag in declassifying WW2 computer development and the abandonment of computer theory at Princeton's IAS (see Turing's Cathedral).

Re:All This And Flying Cars Too (1)

fm6 (162816) | about 2 years ago | (#41083835)

Neither of which had a significant impact on the growth of computer technology, which has been exponential since the 1940s. And I mean "exponential" in the literal sense, not as a buzzword for "really big".

Re:All This And Flying Cars Too (1)

cellocgw (617879) | about 2 years ago | (#41084135)

How do you know that they had no effect ('impact' is incorrect)? We might have had a significantly different, and better, fundamental design paradigm that eliminated bus bottlenecks, improved failure management, and so on. After all, there's a lot of room to change the constant "K" in exp(K*time) :-)

Re:All This And Flying Cars Too (1)

space_in_your_face (836916) | about 2 years ago | (#41079829)

Randall Munroe (xkcd guy) wrote about the difficulty for robots to manage the most simple things in our world. And what would a robot apocalypse look like [xkcd.com] .

This hand shows our strengths... (1)

Covalent (1001277) | about 2 years ago | (#41077133)

...and the robot's weaknesses. The fluidity of the arm and hand are nearly as good as a human's. But the hand is human controlled. If this was controlled by a computer, it probably wouldn't be able to do many of the things in the video. But even forgiving that, it's the fluidity that would be lacking. Humans can make incredibly detailed and precise movements without thinking, something computers are probably still decades away from duplicating (maybe more).

four fingers is nothing new (1)

swell (195815) | about 2 years ago | (#41077147)

Mickey Mouse and all his friends and all the cartoon characters since have done well with 4 fingers.

Humans and most creatures with more than four digits are wasting at least one of them. Where is your dog's thumb? What's it good for? Yes, scratching it's ear, that's all. How often do you need all five appendages to accomplish something worthwhile? You can even throw a Series winning curve ball with only 4.

OK, many robot designers have used a minimal number of fingers, but a few have stubbornly looked for five finger solutions. Four seems optimal.

RAID: Redundant Array of Independent Digits (1)

tepples (727027) | about 2 years ago | (#41081373)

Mickey Mouse and all his friends and all the cartoon characters since have done well with 4 fingers.

Cartoon characters don't lose fingers permanently. Humans do. The fifth finger is for redundancy in case another finger becomes inoperable.

Re:RAID: Redundant Array of Independent Digits (1)

swell (195815) | about 2 years ago | (#41084885)

"Cartoon characters don't lose fingers permanently. Humans do. The fifth finger is for redundancy"

No, the fifth (middle) finger is for stickin it to the Man.
Great title, interesting point; but regarding robots a total of 4 is still optimal.
Especially if they connect with magnets (see TFA) and can be immediately replaced if they fall off.

Yay! A DJM-300! (0)

Anonymous Coward | about 2 years ago | (#41077175)

My first mixer. I think they are using it for applying force in an analog way...I never would have thought of that.

Four fingers is enough for anyone! (1)

drfreak (303147) | about 2 years ago | (#41077225)

- William Gates III.

Off the shelf MIDI (0)

Anonymous Coward | about 2 years ago | (#41077251)

I suppose they kept costs down by using MIDI ( note the USB/MIDI DJ controller they use to modulate the 'tempo' of the sequence ).

Standards keep cost down (MIDI) (1)

ptrrabbt (2712669) | about 2 years ago | (#41077265)

Note the use of off the shelf hardware ( MIDI/USB DJ controller, sending a tempo CC, changing the speed of the (MIDI?) sequence ). I find MIDI to be very usefull in embedded project controllers.

Re:Standards keep cost down (MIDI) (0)

Anonymous Coward | about 2 years ago | (#41077351)

Looks like a DJM-300. I thought they were using it to decide how much power to apply to the hand. He is mainly, it looks, using the cross-fader which would be a pretty gentle transition across its range from 'grab it hard' to ' grab it lightly'. It does not send out any signals that I am aware of...it takes an input and modifies the output in a completely analog way.

Re:Standards keep cost down (MIDI) (1)

ptrrabbt (2712669) | about 2 years ago | (#41087357)

Definitely not an audio mixer - note the little "platters" for virtually manipulating a "record", and the single white cable coming from the rear.

Doh! (1)

cervesaebraciator (2352888) | about 2 years ago | (#41077453)

When they attempted to use the robotic hand to automate functions in a nuclear reactor plant, the experiment failed miserably. Unfortunately, the hand is only adept at opening cans of Duff beer and eating donuts.

Octal (1)

InspectorGadget1964 (2439148) | about 2 years ago | (#41077587)

We use a decimal system because wwe have ten fingers (Allegedly). Would a robot fitted with that hand default to octal?

real market exists (1)

Max_W (812974) | about 2 years ago | (#41078557)

No one, not for any money wans to wash dishes in restaurants or clean public toilets.

If the problem solved in robust and realistic way, there would be the billions' market for such robotized devices.

And in basements all over the world... (1)

hyades1 (1149581) | about 2 years ago | (#41078977)

Across the face of the Earth, slashdotters everywhere raise their unkempt heads. For the first time hope shines in their reddened, monitor-strained eyes. As one, they unleash a great cry of joy into the fapmosphere, and shout, "Wow...that would REALLY feel like somebody else!"

Greg Warren is vindicated (1)

boristdog (133725) | about 2 years ago | (#41080899)

Soon claiming a robot arm did it will be a good legal defense.

Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>