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

 


Forgot your password?
Close
typodupeerror
×
Space

NASA Controls Jet With Nerve Signals 175

Posted by timothy from the whose-tights-exactly? dept.
__roo writes: "According to this press release, NASA scientists were able to control a 757 jumbo jet simulation using neurolectric machine control -- muscle-nerve signals fed to a computer, which used a neural net to learn how to interpret the signals. The first prototype armband was made from exercise tights, and used metallic dress-buttons as dry electrodes. This page has high resolution photos of the device."
This discussion has been archived. No new comments can be posted.

NASA Controls Jet With Nerve Signals More

NASA Controls Jet With Nerve Signals

Comments Filter:
  • Everyone becomes educationally equal? Uhm... Would you mind telling us what planet you're from?

    Access to the same information does not equate to the same education. If you don't have someone who can properly feed you the information in a way that you can understand, having all the information in the universe isn't going to help you one bit. And knowing a lot of trivia does not make you educated either. It just means you know a lot of shit, but doesn't mean you understand any of it.

    Fear my low SlashID! (bidding starts at $500)
  • Explain, in two hundred words or less, why you couldn't do this with a $5.99 joystick from Fry's, and perhaps a keyboard.
    Well, you'd also need live video feed, full-telemetry feed, and a set of rudders and throttles (multiple engines). 5.99 joysticks tend to have bad centering; a $40-50 quality one would be better, and a military grade one even better.

    This also requires a high-quality, high-bandwidth low-latency wireless connection (no satellite bounces).

    Doing this on models is hard enough, much less a modern widebody. And it's usefulness would be restricted to 'Airplane'-type scenarios (Don't eat the fish!) where both pilots are incapacitated without affecting the primary systems. Maybe in a highjacking situation (with ground-based override? There would be SOME way to turn it off unless they integrate it into the flight control computer on a fly-by-wire craft. Plus you then open yourself to highjacking from the GROUND. Lol.)

  • Excellent book by Dale Brown goes DEEP into this. Check it out.
  • The Boeing 777's auto-pilot is apparently capable of landing the plane completely automatically.
  • eh...perhaps because that's the way it's being presented? Nah, that wouldn't have ANYTHING to do with it. If NASA wanted to say "this is just a demonstration, of course we would expect there to be limitations because of xyz obvious problems" they could easily have done so.

    As for Karma Whoring, so sorry to those with sour grapes, but I just say what I think. Been at this for, oh, many months, and still ain't nowhere near massive Karma, so if I'm a KW I must suck pretty bad.

  • Usually 757s are not considered "jumbo jets".

    This is a title reserved usually for 747s.
  • Actually, there is ZERO reason (except for cost) that this system isn't used already. Aircraft computers are already capable of navigating an aircraft to an airport, lining it up on the runway, and landing it...the systems just aren't connected together.

    Pilots nowadays are only used for three things:
    1. Navigating the plane while on the ground.
    2. Navigating the plane while in holding patterns around the airports
    3. Emergency collision avoidance
    Given the assumption that the tower will clear a flight path and that somebody will be sitting there to hit the brakes when the plane touches down, there is no reason at all why planes couldn't land themselves after pushing the big, red emergency button :-)
  • Well, if they can make it to the public, maybe I can use it to control my server room. Combined with wearable monitor, it's nice to type virtually in the air and control my *nix boxes in the server room.
  • I saw "made from exercise tights," and immediately thought, "Son, there's a panty in your head."

    What about the physical resistance to movements a control stick offers? Having never flown a 757, I can't comment first hand, but isn't the "feel" of the stick one way in which a pilot is able to keep aware of the condition/movement of the plane? On the other hand, perhaps this sort of thing would give better control to the pilot, who could concentrate less on just holding on to the controls, and more on controlling the plane in an emergency. Perhaps a dual system? Physical stick and neural armband, each as a back-up to the other, pilots choice on which to use as primary control device?

    --
  • If the power goes out in a 757, I think you're going to be in a world of hurt whether the joystick is virtual or gripped firmly in your sweatly little hand.

    Of course. But I was responding to speculation that this kind of tech. (well, more specifically more advanced stuff like direct mind-computer links) will become pervasive throughout everyday life.
  • I noticed that, too. Why is the joystick right next to his hand? I thought the point was that you didn't need a joystick anymore. Phallic imagery?

    -B
  • I remember watching star trek voyager once. when they had to drop their core. (core dump, get it?). What happens when the user thinkgs in exclamation, "Oh Shit!"

    ---
  • If the avionics are advanced enough for this, just push the red "EMERGENCY" button on the top of the instrument panel. It will put the plane level at altitude, and eventually it'll land as best it can at the nearest airport. It's there to give Hollywood stewardesses other things to do. It's standard equipment, effective as of the next "Die Hard" movie.
  • Well, it is more complicated than that...for example at 300 MPH it's not unusual to have significant weather events within 1/2 hour. But it's almost possible, so I'm only being a little silly. Particularly because there already are aircraft for which it will be easier to do. Not that pilot incapacitation happens easily...
  • indistinguishable == inability to perceive a difference.

    Any technology indistinguishable from magic ==
    any technology which cannot be perceived (/classified) differently from magic

    is insufficently advanced.

    The point being that it is a refutation of the original quote: sufficiently advanced technology would, of necessity, be well understood and explainable to the last microscopic detail. An insufficiently advanced technology is one where there are many unexplained questions and 'magical' effects. The technology of electrical capacitance was insufficiently advanced in ancient times -- capacitors were holy objects with the power to hurt and kill.
    Programming on an old, bizarre, system with many acts of 'black magic' is another example of technology, or more generally, knowledge, that is insufficiently advanced -- as it is only partly understood, and therefore 'magical'.
  • The day after i watched that movie, i was at work and some stupid program crashed on the stupid NT machine, and the error message it gave said the memory could not be "read" and i laughed my ass off =:-)
  • In order to improve reaction times, Pilots (read: navigators) have been ordered into small chambers full of reaction enhancing drugs (read:spice) as seen in the movie (and book) Dune!

    seibed
  • So when can we use this to start controlling our TV's? The couch potatoes don't even have to exercise their thumbs anymore! Better yet, why not get typing linked up to this thing?

  • This is a prototype, of course, with all it's attendant bulk and fragility. I would guess future versions might resemble a fat wristwatch and utilize some sort of short-ranged wireless protocol.

    And as for the 'sliding' issue, that's one of the reasons why they use a neural net in the first place: it can adapt to changes in signal characteristics. They've done similar things with genetic algorythms before.

  • .. that while this technology has uses now (right now!), it's true utility won't be seen until we can do some sort of direct neural / central nervous system input. It's all well and good to interpret my arm motions as commands, but to be a truly effective pilot (or effective controller of anything) I need feedback.

    But, if / when we succeed in that... mouhahahaha.. Perhaps some sort of CNS nerve tap? .. gotta figure a way to do it that doesn't require surgery more complex than getting a pierced ear.

    Perhaps a neural net could be trained to learn how to input signals rather than interpret outputs? A sufficiently powerful, changing magnetic field can induce a change in charge within a conductor (this is how nerve inductors work), but they suck (bulky, power hogs, heat, crappy resolution).

  • hmmm...

    maybe its the start of too much specialization, and that we will all forget how to do mundane things, and then when we all forget how to do everything, the empire will collpase, and then some place called a "foundation" will set up a pseudo religion and make everyuthing okee dokee....


    tagline

  • This sounds like a movie I saw where the russians developed a fighter jet that was controlled by the mind. It flew how where you thought it to fly. The cacth was that you had to think in russian.
  • In my experience translating after thinking is totally diffrent than thinking in another language. I am a native speaker of two languages, though, and this would be really hard to explain to people who have never thought in another language.
  • The advantage to this scheme is that it's completely voluntary. It's no more than a more convenient and hidden keyboard that you can choose what to type onto. Granted, there may be circumstances where you don't think before... thinking (to the computer), but it would take a lot of trickery before someone else could get you to tell them whatever they want.
    --

  • You can find it in the Internet Movie Database [imdb.com].

  • My favorite incredibly-long-and-stupid-pointless-name was:
    (and i am not making this up, look at the thing in a store some time)

    'Saitek Cyborg 3D USB Gold'.

    I laughed so hard I about shat my pants when I saw an ad for it in pc gamer.
  • The Power Glove was nothing like this. All it did was contain little switches inside that activated depending on what joints you had bent in your hand. Yes, it did suck, but this is completely different. :)
  • except that the person he was visualizing killing was a "friendly".
  • If you can find the right neurons, and the guy doesn't mind having a bunch of electrodes stuck through his skull and membranes into the appropriate regions of the brain... probably.

    A neural net is simply a nonlinear function fitter, after all; it takes a vector of inputs and produces output(s), based on preselected, preferably at least locally differentiable nonlinear functions of weighted combinations of inputs -- with the weights being what's trained. If you have enough nodes in a couple of hidden layers, and useful inputs, AND enough training time, you can have enough degrees of freedom for the fitting to work well.

    But you need to find the appropriate inputs, which since it's meant for conscious control, means you need to find neurons which can be consciously influenced. That's probably harder, much harder, in the CNS than for nerves that control voluntary muscle movements, because we *have* largely voluntary control over most of our muscles (excluding reflex arcs and so forth), and since the nerves that trigger muscle movements aren't hard to find, compared to individual neurons in the brain.
  • I think they described it very poorly in the movie (of course, it's a movie, who cares about the details?). It seemed to me that to fire the weapons or whatever the pilot had to think the Russian command for that action. I never saw the difference between thinking the command phrase immediately and thinking the command phrase in English then thinking the translation. In both cases, you are "thinking" the command phrase.

    I do realise that there is a difference between translating. Because I don't speak any other languages well, I have to think in English then translate. My multi-lingual friends (most of whom have Englsh as a second language) tell me they think in the language they are speaking at the time. Some of them even dream in different languages.

  • The movie was "Firefox", with Clint Eastwood. IIRC the thought control only controlled the weapons, but you are right about having to think in Russian. One of the scientist characters said to Clint "You cannot think in English then translate", which I always thought was stupid - if you are thinking of the Russian translation of an English phrase, you are still thinking Russian, aren't you?

  • What happens?? I'll tell ya!! America's Funniest Plane Crashes NEXT ON FOX!!

  • oh wait, wrong story....
    anyway, this is certainly great if the pilot looses both hands during combat/flirting with the stewardess/repairing device xyz/whatever...
    I just want this for my remote control, pressing a finger for those quick channel flicks is just too much work

  • Check out Stelarc's work [va.com.au] ...

  • I might be able to keep up with those damn javascript pr0n popups.

    "Uh...sorry honey, I just hit a bogus link and the browser went wild! No, no I have no idea what goatse.cx stands for. Isn't it some foreign dish? "Uh-oh"?? It's...umm... it's a site for helping guys with stress I think..."

    --Clay

  • Yours basically reads like this: "Any insufficiently advanced technology is indistinguishable from magic."

    No it doesn't. He's wrong, but so is this explanation of why. Your orignal point still stands, unless he's trying to make the point that a really really advanced technology would seem better than magic. If so, then it's just silly.

  • Hmm... consider the potential of this combined with a laser retinal display and a wearable computer. If you wore long sleeves, the only external evidence would be a slightly bulky pair of glasses[1] with a wire down your shirt (unless it used Bluetooth...), and you'd have your hands free. To use the computer, press a switch on your watch to activate a virtual keyboard and/or mouse, or a more task-oriented gesture interface.

    Hmm, all I need now is a few non-geek applications <sef>

    [1] Although AFAIAA LRDs haven't got this far... yet.

  • You know, this whole idea sucked really bad the first time when it was called a POWER GLOVE.

    Liar! The Wizard [imdb.com], the 90-minute Nintendo commercial which I believe was the first real advertisement of the Power Glove, continues to be one of my greatest childhood memories.

    THE POWER GLOVE!
  • So this pilot walks into a bar...Next time he should duck!

    Ha ha. yuck, yuck, yuck
  • What story are you referring to?
  • is Firefox

    "But you must THINK. . . in Russian."
  • Lil late, I used to work in the neurolab in 1998 and spent some time on the software for the BioMuse [biocontrol.com] which was the first generation of the hardware behind this stuff. They have much more advanced technology out, but biocontrol is a good starting point. I haven't been out to the lab since I left so I'm not sure at all what they are using now.

    Good luck with it.

  • Controlling a device with an arm muscle is far different from "mind tapping". The brain is extremely complex, and the chances that we'll be able to decode nuron firings specific enough to identify complex commands is not likely without some type of embedded device. Plus, every brain is different which only adds to the problem. Right now we can "read" emotions via the electrical signals in the brain, but this equivalent to using the clapper to control devices. Its cool, but I highly doubt it'll get to the point where you can think "up" or "down" and a device could read it.
  • how is someone else going to *easily* take control of the aircraft

    Offhand, I'd suggest that every crewer capable of flying the plane would be fitted with their own "neural device" prior to take off, with either the onboard computer calibrated for each pilot, or a calibration-on-a-chip type of thing, where the pilots neural patterns are stored in the armband, and activated when plugged in. Then it would be a simple matter of plugging the lead from the "device" into the computer, flicking a switch and away you go.

    --
  • neural net should be able to distinguish.

    It's the should part that I find scary. I've done some work with neural nets. Machine learning is not like other stuff you've worked with. It is not deterministic. You can't say with 100% accuracy that any non-trivial output is correct. Neural nets just don't work that way. Straight C code can at least be understood, even if exhaustive proof of correctness is beyond most Q&A department. Very few people can understand even the simplest neual net.

  • Nope, it says just what its supposed to. It does make sense. Think about it.
  • It would be different if the device could read nerve signals that do not correspond to muscle movements, but that does not appear to be the case.
    There would be many disadvantages to using non-muscular impulses. On the not-so-serious side, what if the pilot has a vision of the plane crashing? That would suck. But by using muscular impulses, the pilot need not learn anything new. In addition, he/she would have greater control over the airplane. Also, accidents would be greatly reduced due to the fact that there are fewer mechanical devices. The neural net learns your motions, so any excessive movement would be cancelled-out by the computer. It can also re-learn if parts of the plane become disabled.
  • Isn't the problem (and benefit) with neural networks, that they are somewhat non-deterministic? I mean, it's all well and great if 99% of the time the plane behaves correctly according to its training, but what about that 1% of the time where some rogue neuron determins that the pilot *really* means to do a 180?

    And what if, say, a stewardess given the pilot his coffee bumps him, and causes the plane to spiral out of the control? There is something to be said for good old fashioned mechanical controls.
  • everyone becomes educationally equal

    Well, it's kind of absurd to argue about something this far off, but it seems to me that everyone would know the same things, to the extent that now, everyone has access to the same things on the Web. But there's a difference between having access to the text of "The Cathedral and the Bazaar", and fulling understand all of its implications. That's why I said that I think humanity will focus on understanding and mastering. So society can still be stratified-- by how quickly understanding comes to each person.
    --

  • If you've used a mouse for a couple years, you already use it without thinking about the individual muscle movements.

    Cochlear ear implants already exist that interface directly to nerves. This removes the requirements for muscle movement, so mass doesn't need to be accelerated, so the bandwidth should be higher than normal humans' typing rates.
    --

  • Well, it appears that they've programmed the computer to only respond to input if the pilot has curled his hand into a fist. So it is possible for the pilot to "let go", just as they would release their grip on a real stick before moving their hand.
    --
  • eg. A direct neural connection, not attempting to distinguish a signal from millions of ganglia through the skull. So my proposal is a little different from the way they've done the airplane control.

    And yes, neurons in the CNS [btinternet.com] are a little different than ones in the PNS [btinternet.com]. But not enough to make a difference, especially once you've put electrodes into them, because they both use the sodium/potassium/etc. ions for electrical signalling.
    --

  • The Power Glove was nothing like this. All it did was contain little switches inside that activated depending on what joints you had bent in your hand. Yes, it did suck, but this is completely different. :)
    Yes, but... what possible use could this complex neural net have that could not be achieved with a cheap Power Glove (or the equivalent)? It would be different if the device could read nerve signals that do not correspond to muscle movements, but that does not appear to be the case.

    I don't get it.
  • It's not perfect, of course, but it's conceivable that all one needs to do is don a light slave suit and control a plane in the same way one would control rollerblades or skis; muscle control!
    Imagine that! Technology marches on. Perhaps one day we'll be able to control a car, just by moving the muscles in our hands and feet!

    Nah, it'd never happen.
  • Huh? The initial weighting is usually random, but after that, training and output computation is generally purely deterministic. We're talking about simple, simulated neurons modelled via nonlinear functions (often sigmoids), after all -- not something complicated like massively parallel, asynchronous biological tissue with cycles, massive connectivity, and so forth.

    You can even write down the overall behavior of an output node as a single equation of an inputs -- it just might not be that enlightening in terms of understanding WHY it chose those weights.
  • One thing that the story didn't talk about, but would probably be useful - does the interface provide any feedback to the pilot (aside from the plane dipping & rolling, of course)?

    Electrical or sonic stimulation for instance? Feedback would bring the user "into the neural net", and would probably assist in learning how to use the interface & speeding up the user's reactions quite a bit!
  • The crash of their neural net based interface :P
  • Yeah, luckily they edited those scenes out of "Top Gun"... :)

    --

    "I'm surfin the dead zone
  • till I can play Quake 3: Arena with this?
    Intellimouse, schmellimouse! I want electrodes hooked up to my USB port, dammit!

    But above all the question is: Who will volunteer to port this to 2.4.2??

  • Actually, I'm reasonably certain the 757 still is hydraulic. You'll hear a lot of Boeing pilots grumbling about Airbus' fly-by-wire. There have been cases of planes (Boeings, not sure which 7x7) landed "manually," via hydraulics only. Takes one guy down on the floor hauling on the pedals with all his strength, but it's better than nothing.

    Oh, and one more thing... a "jumbo jet" is a 747. Despite the higher number, a 757 is relatively dinky. Single-aisle, and all.

  • Doesn't need a neural net for that. Gal up in Northwest area got busted for giving her significant other a batch of pot-laced brownies... to take to the crew lounge and share.

    That sort of thing makes the FAA very unhappy. Not to mention the airline, since the guys can't fly until they test clean...

  • Ok, so this is a cool hack for pilots. But this technology has great uses than aircraft control systems.

    People with degenerative muscle conditions can benefit from this technology as it removes the physical barriers from controlling devices.

    On another note.....

    Ever played a flight or driving sim. Remember how bad you were to start off with? The feedback level from the joystick/wheel is a poor substitute for the real thing.

    When driving or riding I use the sensations I receive back through the wheel or bars to correct my driving/riding/flying.

    So how remote of a sensation would flying a plane be if you lose this link? The PR talks about the system being used without any tactile feedback.

    So to compensate would a pilot be best grabbing a joystick, whether real or not, and using this as a tactile prop.

    And then we are back to square one.... joystick/yoke control :)

  • On virtual reality:
    "The day an unemployed iron worker can lay in his barka-lounger and fuck Claudia Schiffer for $19.95, it'll make Crack look like fucking Sanka" --Dennis Miller
  • Hmm, another of Arthur Clarke's visions come true? The brain cap? Will it also help detect the seeds of criminal behavior and alert the authorities before it manifests itself? I like Clarke's stuff, but I would rather die than wear a brain cap.

    Steven
  • Your sig says:

    "Any technology indistinguishable from magic is insufficiently advanced."

    But that doesn't make sense (nor is it funny as a joke). I think you meant 'distinguishable'... right?
  • It's an entirely new interface, and is not limited by the older constraints of older interfaces.

    Meaning that, unlike a cheap Power Glove, you are not limited to the degrees of freedom that your fingers and hand have. If you want to tap the muscular controls of your entire body, you can. If you want to tap into the muscles of just your arm, you can. If you just want the hand, you can. So it is already a superset of the powerglove. It would also mean that you aren't limited to on/off switches, but also the more analog like nature of muscle response over time and signal strength.

    What use can the complex neural net have? Why not do an analogy?

    We have fly by wire systems in which a computer device controls an aircraft and multiple control surfaces in ways and at rates that humans cannot, because there is too much information too process.

    Not lets switch the direction of logic; you have a human controller, with much more sensitive and flexible control points than a Power Glove or joystick can sense. The neural net would allow one to almost directly map the human musculature to the airplane control surface, allowing both more control and higher reliability, without reducing flexibility or increasing complexity. It's not perfect, of course, but it's conceivable that all one needs to do is don a light slave suit and control a plane in the same way one would control rollerblades or skis; muscle control!

    Geek dating! [bunnyhop.com]
  • A car currently only allows for two/three degrees of freedom, what with the accelerator/brake and steering.

    The proper analogy is if we use the muscles to actually control/dictate the ABS system, the 4 wheel independent suspension (anticipating speedbumps and potholes with active control), and 4 wheel drive.

    Geek dating! [bunnyhop.com]
  • Resistance is futile.

    I wouldn't predict 'direct neural tapping' to be as mindblowing as you suggest.

    If we all have our brains wired up to computers, they can perhaps become extensions of ourselves, the way a watch, a shoe, a sword can become an extension of a person.

    But that does not mean we can become extensions of each other. People with quick and adaptable brains, in the neuro-plasticity sense, and not the smart and gifted sense, might be able to quickly learn how to communicate with each other, any more than two people from the same school speaking the same language are extensions of each other.

    One would *still* have to interpret each person, the same way we interpret our vision, our sounds, our smells, our reality. We gain one more sensory organ, perhaps, but that's about it. We'd probably have to invent a synchronization language to allow ourselves to taste our SO's ice cream, but it still wouldn't mean *we* would be tasting it. It would probably still route it through our own taste centers, just that our two different taste centers may start to synchronize more.

    Geek dating! [bunnyhop.com]
  • I am curious if anybody knows how hobbyist friendly this field is. It looks like the physical hardware needed to pick up these signals isn't much, but i can imagine you need some _REALLY SPIFFY_ (read expensive, large, current-hungry, heat dissipating...) amplifiers to make this sort of thing work

    I'm not sure. Remembering the halcyon days of 8-bit BBC Microcomputers, I remember we had some kind of thing set up where you could influence a point on the screen from a couple of electrodes taped to your skin. I don't think it was quite the same technology, but it did work to a degree. Details are foggy because I was only about 11 years old at the time ;-)

  • I've said it before, and i'll say it again. New technology goes strait to porn...
    Even the pictures on the site suggest it... notice the hands... [nasa.gov] :)
  • Hey, this reminds me of that research project at (stanford?) a few years ago where they hooked some rig up to a guy's head and his brainwaves moved the mouse around.

    No telling if they ever figured out how to click (or distinguish between right/left click, mousewheel, 3rd button, etc), but imagine the frag potential....
  • ZAP!!! Turbulence sucks!

    Seriously, just because you can do something doesn't mean you should. How would you like to drive your car with no feedback at all? Holding on to an "air" steering wheel means that you have no feel for what the parts actually doing the work - the tires - are doing. What if there is a steering failure and the tires (or rudder) won't turn? How will you know? By looking at a display? Great, add that to the thousand other control items you have to look at in a cockpit.

    We are just now getting to the point where fly/drive/control-by-wire systems are providing the necessary amount of feedback to the user to allow the user to gather the same information that was available in analog systems all along.

    I think that this will be a great technology, but only if there is a compatible means of providing feedback to the user. All of the references to this type of technology in SF have always included force feedback as part of the equation.

  • This is incredible.

    This is one step closer to the concept in sci-fi type stories where the vehicle is just an extension of your body. The plane/ship/space-vehicle/car just reacts to commands straight from your brain and eventually you get so used to the commands that it's just like using your own body. I know all the fears that a situation like that poses, but think of how cool it would be. Drag races with reaction times lower than ever thought possible simply because you don't have to wait for the signal to go from eye to brain to nerve, to muscle, to vehicle device, to vehicle drive. Instead it would go from eye to brain to vehicle and go!

    Yeah, I know there would be better and more important ways to use it (think of dog-fights in the air or space with vehicles that are mind controlled), but drag-racing is in my family.;-).

  • So the idea of this device alone makes me nervous...

    Which makes me jittery...

    Which gets picked up by the controller

    Which makes the plane shake

    Which makes me MORE nervous...oh what vicious cycle!

  • The ship who sang is getting closer (Score:3)

    by bluGill ( 862 ) on Thursday February 01, 2001 @12:01PM (#463864)

    I can't belive I'm the only Anne McCaffery fan here. Surely someone else must remember Helva, Simon, and Tia. Here we are getting closer to the day when cripples can scout around the universe and noone remembers Science Fiction has perdicted it.

  • Re:Oh scary........ (Score:3)

    by jafac ( 1449 ) on Thursday February 01, 2001 @12:37PM (#463865) Homepage
    um - little known fact:
    (would YOU publicise this?)

    Fighter pilots on long (8hr+) missions have been known to wear adult diapers.

  • Re:Uh, you're joking, right? (Score:3)

    by Chris Hiner ( 4273 ) on Thursday February 01, 2001 @04:20PM (#463866) Homepage
    The neural net would allow one to almost directly map the human musculature to the airplane control surface...
    Why did I suddenly picture the pilot running around, holding his arms straight out to the side "flying"?

  • Re:Macross Plus (Score:3)

    by Apache ( 14188 ) <foonix.yahoo@com> on Thursday February 01, 2001 @01:34PM (#463867)
    I am not sure if you are aware of this, but CARTOONS are not real.

    By definition, all theory is not "real". Macross plus had some interesting theories.

    I am a bit confused on the moderation, 3? This comment is not relevant to the story at all.

    One of the elements of the show is that there is a design competition between two designs, the YF-19 and the YF-21. One of the things that the YF-21 design had going for it was that it had an interface similar to the one mentioned in the story. The main difference is that the YF-21's interface didn't require the pilot to actually move any part of his body. He could simply "visualize" the whole aircraft as an extension of his body, and control it that way.

    Another thing worth mentioning, there was a scene where the YF-21's pilot visualized an easy way to kill the YF-19's pilot given the current circumstance. The YF-21's computer system took this as an order, and they YF-19's pilot was almost killed. This illustrates a potential danger in these kind of systems that the designers and/or users will have to be weary of.

  • Re:Mind Control (Score:3)

    by flimflam ( 21332 ) on Thursday February 01, 2001 @11:36AM (#463868)
    I wonder if people who haven't learned to integrate their activities with a machine at an early age will ever manage to have this happen as seemlessly as you suggest. The people who invent this stuff may end up using this stuff rather awkwardly, like someone speaking a late-learned language, while their children will truly be the ones that inhabit a new world.

    For some reason, I find the whole concept of this rather unsettling. I guess I don't like the idea of becoming overly dependant on a machine. What if the power goes out?

  • How hobbyist friendly is this field? (Score:3)

    by drenehtsral ( 29789 ) on Thursday February 01, 2001 @11:40AM (#463869) Homepage
    I am curious if anybody knows how hobbyist friendly this field is. It looks like the physical hardware needed to pick up these signals isn't much, but i can imagine you need some _REALLY SPIFFY_ (read expensive, large, current-hungry, heat dissipating...) amplifiers to make this sort of thing work, and then some really spiffy algorythms on the computer side to filter out noise that gets picked up, plus whatever low-level chatter is happening on that nerve...

    So here is my question: Does anybody that knows something in this field know of a source of information on this? Is the technology patented by somebody? How complex are the electronics, and are the algorythms for extracting the data public?

    The reason i ask is because i've always wanted to be able to do this, now i don't want to land jets, or play quake, i have a much more modest application in mind, i'd like to be able to get several (as few as four would still kick ass, although up to 10 would be nice...) reproducable (you don't have to be able to reproduce them from memory, there will be a visual feedback mechanism, so you know what you are inputting now, and you can watch it change as you "move"). I don't really have a practical use for this, and i'm sure i'll _always_ be able to type faster than i can use this method, but i still think it's very cool.

    So i guess if it's something i could concievable do for under $1000 assumming i already had microcontroller tools, a scope, prototyping tools, etc... (so i'm talking only parts, books, software that must be purchased, and oddball tools...)

    Thanks, and i really hope i hear from somebody, because this has sort of been a dream of mine since i was about 12 years old =:-)

  • Oh great! (Score:3)

    by SpinyNorman ( 33776 ) on Thursday February 01, 2001 @11:58AM (#463870)
    Control a Jumbo jet with nerve impulses...

    Stewardess bends over to pick somthing up, pilot gets a woodie, and plane goes into a nose dive!

    :-(

  • Oh scary........ (Score:3)

    by phunhippy ( 86447 ) <zavoid.gmail@com> on Thursday February 01, 2001 @11:25AM (#463871) Journal
    Course.. the pilot could start playing with himself.... watch that plane go up and down, up and down.... :)

  • good idea. (Score:3)

    by jon_c ( 100593 ) on Thursday February 01, 2001 @11:36AM (#463872) Homepage
    I've seen things like this, most of which we're really sophisticated "love testers". you know those machines in walmarts that tell you if your a "cold fish" or a "love machine". I believe those use a pulse rate, or some type of temperature.. or maybe a random number generator :)

    more recently I saw a product hyped up to "read your mind" you placed your finger on something, and was able to move a plane just by "thinking" about it. when in reality you we're subconsciously moving your finger the way you wanted to go, this kind trick is common in other applications.

    The use of a neural net however is quite good. neural nets are currently used in speech recognition, and writing recognition. basically you say "here's some data, it means A", "here's some other data, it means B". the neural net will be able to tell the two apart and allow for a good degree of error. this is the jitz of it, I'm not really a student of the field.

    so it makes sense to use a neural net for a task of "these muscles patterns mean move left", and so forth. I'm just surprised I didn't hear about that success of such an application till they landed a freakin jet with it! but then again slashdot is eregular about there coverage of things, i imagine cmdrtaco and gang turned down the previous articals leading up to this one.

    -Jon

    Streamripper [sourceforge.net]

  • remote control for emergency landing? (Score:3)

    by tokengeekgrrl ( 105602 ) on Thursday February 01, 2001 @12:26PM (#463873)
    The first thing I thought of is if the pilot is injured or the instruments on board are damaged, the plane could possibly be landed safely by someone remotely from the airport, with the neural net overriding the standard system.

    - tokengeekgrrl
    "The spirit of resistance to government is so valuable on certain occasions

  • Wow! (Score:3)

    by RareHeintz ( 244414 ) on Thursday February 01, 2001 @11:26AM (#463874) Homepage Journal
    An input device such as this could lead to unprecedented speed and accuracy for first posters! You could set a "Twitch Macro(tm)" to type "FP!" and hit the "Submit" button.

    As for actual piloting or other safety-critical applications, though, I have to admit skepticism. Anything where fidgeting could actually result in death should probably be discouraged.

    OK,
    - B
    --

  • A few problems with that.... (Score:3)

    by d3spair ( 249152 ) on Thursday February 01, 2001 @11:32AM (#463875) Homepage
    I have a few concerns with that type of control: 1. What about muscle spasms or craps. Plus what if you need to "stretch" those muscles a minute? Do you now have to require co-pilots in every aircraft (course commercial aviation requires this anyhow)? 2. Hypothetically. If the pilots are incapicitated, how is someone else going to *easily* take control of the aircraft. Oooopss wait while I strap on some electrodes... oh nevermind there's the ground.

  • Not on my plane you don't (Score:4)

    by elmegil ( 12001 ) on Thursday February 01, 2001 @11:46AM (#463876) Homepage Journal
    From the article:

    This new technology is significant in that neuroelectric control of computers can replace computer keyboards, mice and joysticks for some uses

    It's been stated flippantly by some other posters, but I really seriously hope none of these uses include safety-critical applications, either for the user or for the user's "clients" of whatever sort. The example of an airline pilot is a good one--is it really smart to think that a pilot will be able to keep his hand under *complete* control for the duration of a 4 hour cross country flight? Much less the much longer intercontinental flights? Can you imagine the difficulty of keeping your arm completely still during the period of stable flight? I suppose it wouldn't be *that* hard to cut in and out with the autopilot, but still....

    Furthermore, one advantage sticks etc. have is they don't require you to be physically tethered to the control system. If a pilot today has some medical emergency, not only does the copilot have his/her own stick, but the pilot could be removed and any other person capable of flying the machine could very quickly take over. How long would it take 1) to move the electrodes and 2) train the neural net for another person?

    This really does not seem like it would be a good technology for any kind of control system where you have human failsafes to protect safety.

  • So this pilot walks into a bar... (Score:4)

    by goliard ( 46585 ) on Thursday February 01, 2001 @11:43AM (#463877)


    "I'll bet you $100 that I can, too land a plane with both hands behind my back!"

  • A little "over use" of quotes? (Score:4)

    by RussGarrett ( 90459 ) <russNO@SPAMgarrett.co.uk> on Thursday February 01, 2001 @11:40AM (#463878) Homepage
    Sheesh - the use of quotes in that article would make Dr. Evil proud:

    ...ability to control and "land" a simulated 757...
    ...control an aircraft without the aid of a "stick"...
    Scientists outfitted a "pilot" with an armband...
    ...a simulated "damaged" aircraft...


    Hmmm... a little over doing it? Do you need to put the word "pilot" in quotes (well, I did just then, but then I needed to, because... Oh, forget it.

  • broader perspective (Score:4)

    by swordgeek ( 112599 ) on Thursday February 01, 2001 @11:41AM (#463879) Journal
    OK first of all, there's a huge difference between what NASA does research on, and what the FAA approves. The FAA is a very conservative, safety-oriented organisation, and avoids change as much as possible. If this thing was put into fighter production tomorrow, it would be a decade before civil planes saw such a device.

    Secondly, let's look at what this is: a fundamentally new way of controlling a plane with the same old movements. It's exciting and innovative, but effectively the pilot is still flying in the same manner as he did before, although without a joystick in his hand. Fly-by-wire systems and positional sensors offer the same capability.

    Ultimately though, this is the thin edge of the wedge. Make no mistake--this will lead to entirely new ways of interfacing with machines of all types, and may be the start of true virtual reality. (like the transistor was the start of the modern portable computer) This isn't a device - it's a technology.

  • The metric system. (Score:4)

    by fantom_winter ( 194762 ) on Thursday February 01, 2001 @11:35AM (#463880)
    I can see it now, the pilot is operating this airplane at a comfortable 5 meters above sea level, going about 400 meters/sec. Then he looks through his 2 meter thick double paned glass cockpit window, and his seat designed for the average 70cm man.

    All the time, he wonders when NASA will learn to convert to and from the English and SI system.

  • Re:Not on my plane you don't (Score:4)

    by tswinzig ( 210999 ) on Thursday February 01, 2001 @02:09PM (#463881) Journal
    Why do people always assume that HIGHLY EXPERIMENTAL devices such as this are going to be immediately implemented, exactly as they are shown in these articles.

    You know, it *is* possible that the people working on this technology just MAY have thought of the same scenarios as those envisioned here.

    How many people REALLY think the inventors of this technology expect a pilot to:

    - Not move their hand except to control the airplane for X amount of hours.

    - Not sneeze, scratch, or otherwise involuntarily move their hand.

    I mean, sheesh!!! Give these people some credit for having common sense...

    -thomas

  • Oooh boy...how original (Score:4)

    by WickedClean ( 230550 ) on Thursday February 01, 2001 @11:16AM (#463882) Homepage
    You know, this whole idea sucked really bad the first time when it was called a POWER GLOVE.

  • Macross Plus (Score:4)

    by Bonker ( 243350 ) on Thursday February 01, 2001 @11:17AM (#463883)
    The Anime Geeks will note that one of the Valkyrie fighter jets/mecha in the Macross Plus series was controlled via electrodes and biofeedback.

  • Re:Mind Control (Score:4)

    by Urban Existentialist ( 307726 ) on Thursday February 01, 2001 @11:32AM (#463884) Homepage
    I think that one of the biggest beneficiaries of this technology will be the entertainment industries. Futurists always make the mistake, IMO, of only addressing industrial and business uses of new technologies. I think that this technology could be used to great affect by Hollywood, Computer Games companies and of course the porn industry, which are all in the process of merging gradually anyway.

    The consequences of direct neural tapping are mind blowing, and in more than one sense. One question is that when everyone has their brains wired up to this tech and to the internet, everyone becomes educationally equal, and everyone can learn new skills very quickly. This technology is a step in the direction of a classless society.

    You know exactly what to do-
    Your kiss, your fingers on my thigh-

  • Watch out. (Score:5)

    by Carbonate ( 13973 ) on Thursday February 01, 2001 @11:21AM (#463885)

    Can you imagine the pilot having too much coffee?

    "Sorry folks for that wee bit of turbulence. I drank an extra cup of coffee today and I'm a little jittery"

    Probably going to be the first plane crash due too caffiene.

  • Re:Oh scary........ (Score:5)

    by Shotgun ( 30919 ) on Thursday February 01, 2001 @11:46AM (#463886)
    While you may not mean to be taken seriously, this does pose one of the problems with this technology. So what happens when they wire the fighter pilot up to the plane to get better performance and the pilot has to:

    -sneeze
    -scratch
    -use the bathroom (extreme stress can cause electrical output to go all over the scale)

  • Dream on (Score:5)

    by goliard ( 46585 ) on Thursday February 01, 2001 @11:35AM (#463887)
    This sort of technology can lead to mind controlled machines. In a decade or two, it could be possible for you to look up the definition for a word on m-w.com while simultaneoulsy carrying on a conversation, and the other person wouldn't ever know that you needed to look the word up.

    Er, no. This is about muscular nerves. Picking out eight myoelectrical signals through (several?) cm of meat is no mean feat, but distinguishing what's going on in millions of ganglia through a skull? And that's merely considering the scale difference; I dimly recall the idea that muscular nerves were qualitatively different than the ones which we think with.

  • Mind Control (Score:5)

    by interiot ( 50685 ) on Thursday February 01, 2001 @11:22AM (#463888) Homepage
    This sort of technology can lead to mind controlled machines. In a decade or two, it could be possible for you to look up the definition for a word on m-w.com while simultaneoulsy carrying on a conversation, and the other person wouldn't ever know that you needed to look the word up.

    It would be just like walking... at first, interacting with the computer pack would be awkward, but after a while you'd do it without thinking, and it would become a part of you.

    Just as the avilablility of an always-on DSL connection allows people to use mapquest rather than storing an atlas at their house, this technology will allow humans to forget the millions of trivial facts and focus on understanding and mastering skills.
    --

Slashdot Top Deals

Physician: One upon whom we set our hopes when ill and our dogs when well. -- Ambrose Bierce

Close