Tiny Helicopter Piloted By Human Thoughts
livescience.com
Tiny Helicopter Piloted By Human Thoughts
1–10 of 27 posts
Re: Tiny Helicopter Piloted By Human Thoughts
#2Whatever you do, don't think about getting hit in the face by a helicopter...
Re: Tiny Helicopter Piloted By Human Thoughts
#3Wired ran a story last year on a Chinese team that did the same thing already:
http://www.wired.com/gadgetlab/2012/08/zhejiang-university-c...
Re: Tiny Helicopter Piloted By Human Thoughts
#4How many directions can EEG control.
If this is just up and down based on your level of concentration, it is relatively useless. However, if it maps all 6 directions, it is pretty impressive.
Re: Tiny Helicopter Piloted By Human Thoughts
#5Wired ran a story last year on a Chinese team that did the same thing already: http://www.wired.com/gadgetlab/2012/08/zhejiang-university-c...
they mentioned that in the article
Re: Tiny Helicopter Piloted By Human Thoughts
#6How many directions can EEG control. If this is just up and down based on your level of concentration, it is relatively useless. However, if it maps all 6 directions, it is pretty impressive.
If you read the article, they have 2 signals, one corresponding to what you're imagining your right hand doing, one to what your left is doing.
With this you have turn left, turn right, and both together is turn up.
To really fly it you need another control for speed. (They just made the speed constant.)
Re: Tiny Helicopter Piloted By Human Thoughts
#7How many directions can EEG control. If this is just up and down based on your level of concentration, it is relatively useless. However, if it maps all 6 directions, it is pretty impressive.
Seems like a good candidate for machine learning. Train a neuralnet to recognize the EEG patterns that a given person wants to use to do a given operation.
For example, this one was having the subject think about making a fist, but it could be that having them "will" the copter to move right could be more intuitive. And with the right machine learning/recognizer it might be feasible.
This would be a serious amount of fun to work on.
Re: Tiny Helicopter Piloted By Human Thoughts
#8How many directions can EEG control. If this is just up and down based on your level of concentration, it is relatively useless. However, if it maps all 6 directions, it is pretty impressive.
the articles say 4 directions, but I'm going to assume that's because it's what they've been able to find clear enough patterns to map actions to. If they thought up a few more, ex "think about kicking your left leg" to move forwards, it could probably work. The leader talked about using wheelchairs and prosthetic limbs.
Re: Tiny Helicopter Piloted By Human Thoughts
#9How many directions can EEG control. If this is just up and down based on your level of concentration, it is relatively useless. However, if it maps all 6 directions, it is pretty impressive.
I wonder how many "channels" can be worked out? 2? 20? 2,000? 2,000,000? Anyone have any background on this? It's fascinating to think of the complexity of a machine that could be controlled, when compared to the inherent limitations of pedals, wheels, switches and the like.
Re: Tiny Helicopter Piloted By Human Thoughts
#10How many directions can EEG control. If this is just up and down based on your level of concentration, it is relatively useless. However, if it maps all 6 directions, it is pretty impressive.
If you read the article, they have 2 signals, one corresponding to what you're imagining your right hand doing, one to what your left is doing. With this you have turn left, turn right, and both together is turn up. To really fly it you need another control for speed. (They just made the speed constant.)
From what I know of existing EEG technology, the news here is left-right signaling, rather than simple on/off.
Fascinating and cool as hell, but really limited for HCI applications.