An anonymous reader tips us that researchers at Toyota have developed a brain-machine interface system that allows for control of a wheelchair using thought. The system processes brain thought patterns (such as the thought of moving one's left foot) and can turn them into left, right, and forward movements of the wheelchair with a delay as short as one-eighth of a second. That's a big improvement over existing systems, which can take as long as several seconds to analyze and react to the user's thoughts. "The system has an emergency stop that can be activated by the user puffing his cheeks. The BMI adjusts itself over time to the characteristics of each driver's brainwaves. If a person dedicates three hours a day to using the system, the BMI can reach 95% accuracy in a week, researchers said."
I was going to say just this. 95% sounds good until you start thinking about it - but that means that in every hour of usage, the chair is going to spend three full minutes misbehaving. I can't find exact statistics or standards for conventional electric wheelchairs but I'd be amazed if the mean time before failure is measured in minutes rather than months or years.
I was going to say just this. 95% sounds good until you start thinking about it - but that means that in every hour of usage, the chair is going to spend three full minutes misbehaving.
OK, sure, but answer this: When you go out for an hour walk, do you ever stumble or overbalance? Sure, the wheelchair isn't perfect -- but neither are we.
Three minutes? I'd guess this thing is about as effective at understanding the brain's motive commands as an average six year old. That's pretty good.
The human being has a built in risk management system. I wouldn't like the 5% failure to happen say at the train platform or near a road crossing. We take special care and do a lot of subconscious checking in more dangerous situations. True we are not foolproof, but we have a lifetime of reasoning to fall back on. The wheelchair system is a bit like a child. Kids need extra help in similar conditions becasue their peripheral vision is not great, their sense of risk and reasoning is still developing. I'm sur
Granted, 95% accuracy isn't amazing, especially in situations where you can't afford to make a mistake. This being said, I'm pretty sure that such a sophisticated device could easily implement some collision/stair avoidance (for instance).
I know I've tried putting my roomba on top of a table (or tried to make it go off the stairs), but it just stops when it gets to an edge. It also stops when its bumpers hit a wall, by the way. I don't know how much this wheelchair would cost, but I wouldn't be surprised
"I was going to say just this. 95% sounds good until you start thinking about it - but that means that in every hour of usage, the chair is going to spend three full minutes misbehaving. I can't find exact statistics or standards for conventional electric wheelchairs but I'd be amazed if the mean time before failure is measured in minutes rather than months or years."
Depends how you define "failure". For the type of patient that need this interface the existing interface methods would have up to a 100% failue rate simply because their disability prevents them from using it with a reasonable degree of accuracy.
Good point. Their current option is 'not', so any control is good. Also, if they're reading the inputs 8 times a second, I'd presume that they would do some form of filtering to improve accuracy in practice.
I was going to say just this. 95% sounds good until you start thinking about it - but that means that in every hour of usage, the chair is going to spend three full minutes misbehaving.
Depends on how it fails for that 5%. If 95% of the time, it understands and executes the command perfectly, but the other 5% of the time, it doesn't understand and thus executes no command, then that's pretty good.
Additionally, which 5% are we talking about? Does it fail every 57min for 3min reliably? Every 19min for 60sec? Every minute for 3sec? Or every 10sec for half a second?
Breaking it down like that and what do you get? A very small delay between reaction times every few seconds. Perhaps not even a noticeable delay since their optimal response time is 0.125sec
The statement was "If a person dedicates three hours a day to using the system, the BMI can reach 95% accuracy in a week", they didn't say that 95% was the highest accuracy one could obtain. After a full month of usage, you could find yourself at decimal point level inaccuracy.
But hitting that wall or doorjamb the other 5% of the time really sucks.
I have a colleague with cerebral palsy who uses a powered wheelchair and she accidentally bumps doorjambs and corners of tables all the time. I don't know if it is 5% of the time, but there's not a whole lot of paint on the the door casings in our lab. It's actually not that big a deal because she is completely surrounded by the chair so it's pretty hard for her to get hurt. And she doesn't, you know, go right up to the edge of staircases or train platforms or anything. I'm sure that they are working on that
Yeah, the wheelchair can read minds, but can it flash a light to indicate "yes" or "no"?
I know you were going for funny but for many patients I would imagine something similar (with a less ridiculous methodology perhaps) to be a useful feature that could probably be easily implemented through this technology.
You don't need a "no" response, actually. You can communicate quite well with just a "Yes". (Here is where I explain all of the humor out of the Capt. Pike joke.) The computer can automatically scan through a series of options and the user can activate when it gets to the option he or she wants. If no response, it simply assumes No and moves on.
If you want to see examples of this system at work, check out Jean-Dominique Bauby's system in the film The Diving Bell and the Butterfly, where it scans the letters of the alphabet in order of frequency (in French in his case).
Stephen Hawking uses a row-column system that scans through dictionaries of whole words large blocks at a time, each selection narrowing down the options to the word, so that he only has to resort to spelling things out for infrequently occurring words.
Sounds more like the other way around. You, watching a high-speed racing game (or TV show), "thinking" about the movement, and then... miserably crashing your head against the 46" LCD in front of you...
Now, I can't wait for the YouTube videos documenting such behavior!
Oh, good, I stand a relatively good chance of being able to stop myself before rolling into traffic. Although, to be fair, I'd much rather face a 5% error rate than have no control at all. Not to mention that's only one week of training.
This was done a few years ago in a different way: you wear an electronic collar which eavesdrops on the nerves running to your vocal chords. These signals are then decoded into words. Finally, some words, like "forward", are interpreted as intentions to move. The system is called the Audeo.
Finally, some words, like "forward", are interpreted as intentions to move.
I can imagine how this could be very entertaining to see in action. Imagine someone on a stage giving a speech in one of these. "...these figures show clearly, we should move forward AAAAAAAAAAAaaaaaaaaaaaaah" CRASH.
This technological advance screams out to be mounted on a mobile beer fridge. Far more convenient than waiting for a buddy to finish his pint, then using that time-worn phrase, "While you're up..."
Okay, I'll say this again, because it doesn't seem to have filtered through to the general population yet. Until the singularity, the human brain will be able to learn more easily than a computer. Please stop trying to teach computers the thought patterns for specific movements, and just provide a neural interface for the brain to work with. The brain will be able to figure out what signals it needs to fire to get the wheelchair moving (or whatever) soon enough.
FWIW, my own idea of how to do this would be to put a few small electrodes into a person's lower arm, far away from the brain (and have a sensitive meter to detect nerve firings).
Why not just put the electrodes into the person's feet? Then when they're walking along, the wheelchair can just follow a few paces behind them. That way, if they ever find themselves paralyzed and unable to send nerve firings to their feet, they'll find it rather convenient to have a wheelchair available.
Okay, I'll say this again, because it doesn't seem to have filtered through to the general population yet. Until the singularity, the human brain will be able to learn more easily than a computer. Please stop trying to teach computers the thought patterns for specific movements, and just provide a neural interface for the brain to work with. The brain will be able to figure out what signals it needs to fire to get the wheelchair moving (or whatever) soon enough.
FWIW, my own idea of how to do this would be to put a few small electrodes into a person's lower arm, far away from the brain (and have a sensitive meter to detect nerve firings). Once the brain figures out what nerves are important for this interface, you then use that interface to deliver signals to operate other equipment.
I know in theory this sounds good but has it ever been demonstrated to work? Can adults recruit new brain areas like this?
Okay, i'll look like some troll already mods, but give me a second.
I just feel that this is just another promo ad that gets sent to tech sites from some publicists to get the title of the technology spread with their name on it.
Yeah I'll stop. Mod me down. I just think it's odd that this stuff gets press like it's something brand new. Perhaps sell us by saying its much better? Something. Please.
This is slightly off topic, but I hope this technology develops fast enough to get Stephen Hawking some great things before he dies. I'd love to see him given something that would allow him to type letters just by thinking of them.
I want to see.. (Score:3, Funny)
Re: (Score:2)
Re:I want to see.. (Score:5, Informative)
Parent
Re: (Score:2)
95% accuracy is pretty awesome. (Score:4, Insightful)
Re:95% accuracy is pretty awesome. (Score:5, Interesting)
Parent
Re: (Score:3, Insightful)
I was going to say just this. 95% sounds good until you start thinking about it - but that means that in every hour of usage, the chair is going to spend three full minutes misbehaving.
OK, sure, but answer this: When you go out for an hour walk, do you ever stumble or overbalance? Sure, the wheelchair isn't perfect -- but neither are we.
Three minutes? I'd guess this thing is about as effective at understanding the brain's motive commands as an average six year old. That's pretty good.
Re: (Score:3, Insightful)
Re: (Score:2, Interesting)
I know I've tried putting my roomba on top of a table (or tried to make it go off the stairs), but it just stops when it gets to an edge. It also stops when its bumpers hit a wall, by the way. I don't know how much this wheelchair would cost, but I wouldn't be surprised
Re:95% accuracy is pretty awesome. (Score:5, Insightful)
Depends how you define "failure". For the type of patient that need this interface the existing interface methods would have up to a 100% failue rate simply because their disability prevents them from using it with a reasonable degree of accuracy.
Parent
Re: (Score:2)
Re:95% accuracy is pretty awesome. (Score:4, Insightful)
I was going to say just this. 95% sounds good until you start thinking about it - but that means that in every hour of usage, the chair is going to spend three full minutes misbehaving.
Depends on how it fails for that 5%. If 95% of the time, it understands and executes the command perfectly, but the other 5% of the time, it doesn't understand and thus executes no command, then that's pretty good.
Parent
Re:95% accuracy is pretty awesome. (Score:4, Insightful)
Additionally, which 5% are we talking about? Does it fail every 57min for 3min reliably? Every 19min for 60sec? Every minute for 3sec? Or every 10sec for half a second?
Breaking it down like that and what do you get? A very small delay between reaction times every few seconds. Perhaps not even a noticeable delay since their optimal response time is 0.125sec
Parent
Re:95% accuracy is pretty awesome. (Score:5, Insightful)
The statement was "If a person dedicates three hours a day to using the system, the BMI can reach 95% accuracy in a week", they didn't say that 95% was the highest accuracy one could obtain. After a full month of usage, you could find yourself at decimal point level inaccuracy.
Parent
Re:95% accuracy is pretty awesome. (Score:5, Insightful)
Parent
Re: (Score:3, Funny)
Re: (Score:3)
But hitting that wall or doorjamb the other 5% of the time really sucks.
I have a colleague with cerebral palsy who uses a powered wheelchair and she accidentally bumps doorjambs and corners of tables all the time. I don't know if it is 5% of the time, but there's not a whole lot of paint on the the door casings in our lab. It's actually not that big a deal because she is completely surrounded by the chair so it's pretty hard for her to get hurt. And she doesn't, you know, go right up to the edge of staircases or train platforms or anything.
I'm sure that they are working on that
Thought / Action Barrier (Score:3, Insightful)
Re:Thought / Action Barrier (Score:5, Insightful)
There's a difference for most of us between thinking ABOUT moving our foot and thinking TO move our foot.
Parent
Re:Thought / Action Barrier (Score:5, Funny)
You've got that spot on. I spend a lot of time thinking about moving my butt out of bed. Especially now that it's winter here in the southern hemi.
Parent
Re: (Score:2)
http://www.youtube.com/watch?v=0x3W6hutEj8 [youtube.com] :-P
Captain Pike calling... (Score:5, Funny)
Re: (Score:2)
I know you were going for funny but for many patients I would imagine something similar (with a less ridiculous methodology perhaps) to be a useful feature that could probably be easily implemented through this technology.
Re: (Score:2)
Yeah, the wheelchair can read minds, but can it flash a light to indicate "yes" or "no"?
From what I've learned of the future(ama) I think you mean "yes" and "yes, yes".
Re: (Score:2)
Re: (Score:2)
Re:Captain Pike calling... (Score:4, Interesting)
You don't need a "no" response, actually. You can communicate quite well with just a "Yes". (Here is where I explain all of the humor out of the Capt. Pike joke.) The computer can automatically scan through a series of options and the user can activate when it gets to the option he or she wants. If no response, it simply assumes No and moves on.
If you want to see examples of this system at work, check out Jean-Dominique Bauby's system in the film The Diving Bell and the Butterfly, where it scans the letters of the alphabet in order of frequency (in French in his case).
Stephen Hawking uses a row-column system that scans through dictionaries of whole words large blocks at a time, each selection narrowing down the options to the word, so that he only has to resort to spelling things out for infrequently occurring words.
Parent
Wheeee! (Score:2, Insightful)
Re: (Score:2)
Now, I can't wait for the YouTube videos documenting such behavior!
Here they are.. (Score:4, Funny)
That's nearly perfect. (Score:2, Interesting)
Re: (Score:3, Insightful)
"Oh, good, I stand a relatively good chance of being able to stop myself before rolling into traffic."
Which is why the brake is controlled with the breathing tube.
It's called the Audeo (Score:3, Interesting)
This was done a few years ago in a different way: you wear an electronic collar which eavesdrops on the nerves running to your vocal chords. These signals are then decoded into words. Finally, some words, like "forward", are interpreted as intentions to move. The system is called the Audeo.
Official site: http://www.theaudeo.com/ [theaudeo.com]
Video: http://www.youtube.com/watch?v=iyQv61899HE [youtube.com]
Article: http://zone.ni.com/devzone/cda/tut/p/id/6130 [ni.com]
Re: (Score:3, Funny)
I can imagine how this could be very entertaining to see in action. Imagine someone on a stage giving a speech in one of these. "...these figures show clearly, we should move forward AAAAAAAAAAAaaaaaaaaaaaaah" CRASH.
It must be said... (Score:4, Funny)
This technological advance screams out to be mounted on a mobile beer fridge. Far more convenient than waiting for a buddy to finish his pint, then using that time-worn phrase, "While you're up..."
Gah... brains are meant to be good at learning (Score:2, Insightful)
Okay, I'll say this again, because it doesn't seem to have filtered through to the general population yet. Until the singularity, the human brain will be able to learn more easily than a computer. Please stop trying to teach computers the thought patterns for specific movements, and just provide a neural interface for the brain to work with. The brain will be able to figure out what signals it needs to fire to get the wheelchair moving (or whatever) soon enough.
FWIW, my own idea of how to do this would be t
Re:Gah... brains are meant to be good at learning (Score:5, Funny)
FWIW, my own idea of how to do this would be to put a few small electrodes into a person's lower arm, far away from the brain (and have a sensitive meter to detect nerve firings).
Why not just put the electrodes into the person's feet? Then when they're walking along, the wheelchair can just follow a few paces behind them. That way, if they ever find themselves paralyzed and unable to send nerve firings to their feet, they'll find it rather convenient to have a wheelchair available.
Parent
Re: (Score:2)
FWIW, my own idea of how to do this would be to put a few small electrodes into a person's lower arm
If they had nerve impulses getting as far as their lower arm, they'd be able to use a joystick.
Re: (Score:2)
Re: (Score:2)
Okay, I'll say this again, because it doesn't seem to have filtered through to the general population yet. Until the singularity, the human brain will be able to learn more easily than a computer. Please stop trying to teach computers the thought patterns for specific movements, and just provide a neural interface for the brain to work with. The brain will be able to figure out what signals it needs to fire to get the wheelchair moving (or whatever) soon enough.
FWIW, my own idea of how to do this would be to put a few small electrodes into a person's lower arm, far away from the brain (and have a sensitive meter to detect nerve firings). Once the brain figures out what nerves are important for this interface, you then use that interface to deliver signals to operate other equipment.
I know in theory this sounds good but has it ever been demonstrated to work? Can adults recruit new brain areas like this?
meh.. post some decent articles kdawson (Score:4, Interesting)
I just feel that this is just another promo ad that gets sent to tech sites from some publicists to get the title of the technology spread with their name on it.
this article, (06/29/2009) [gizmodo.com]
Brain controlled wheelchair developed at University of South Florida (02/11/2009) [robotliving.com]
from European scientists, Brain Controlled Wheelchair (05/11/2008) [ubergizmo.com]
Ambient Tech creates brain controlled wheelchair (09/06/2007) [newscientist.com]
Brain controlled wheelchair from spanish inventor (01/29/2007) [futurismic.com]
University of Electro Communications in Japan develop brain controlled wheelchair (08/11/2006) [pinktentacle.com]
Yeah I'll stop. Mod me down. I just think it's odd that this stuff gets press like it's something brand new. Perhaps sell us by saying its much better? Something. Please.
Re: (Score:2)
Fair point, and shouldn't be modded down, but the difference is that this one interprets dance moves!
Advertisements (Score:3, Funny)
Super balmer (Score:4, Funny)
Stephen Hawking (Score:2, Interesting)
Just Askin' (Score:3, Funny)
Is it an EVIL brain/machine interface?
Is it an EVIL wheelchair?
Are they EVIL thoughts?
Re: (Score:2)
Unfortunately, your choice of font is still living in 1925.
Re:For those who RTFA: Though-Controlled Robot!! (Score:4, Funny)
Direct brain interfaced control by a robot? Now THAT's interesting!
(I, for one...)
Parent
Re: (Score:3, Insightful)
Re:BMI... (Score:4, Funny)
Anyone got a creative alternate title?
Brain Control Interface? Mind Control Interface?
That sounds like I'm gonna need a tinfoil hat.
Parent