News for hackers. Stuff that matters.
Re:Microsoft demos muscle-computer interface, air Guitar Her... by aggie on Thursday August 02, 2012 @10:10AM (#4328800)
I am working in a lab that is developing a similar technology, the main difference being we use a single muscle site to control two degrees of freedom (primarily moving a cursor on a screen). We are also working on applications for severely paralyzed individuals who can use the "ear wiggling" muscles (auricularis superior--the side of your head) to control anything from a television remote to a motorized wheelchair. The control isn't perfect, but with a few hours of training most participants are achieving cursor-to-target accuracies of around 80%. One participant was able to reach 100% in one session.

It is fun to play with a muscle-computer interface for a while, but I don't think it will catch on as a heavy-use gaming controller unless they significantly improve upon current technology. It is simply too imprecise, though on/off (button) control like what is used for Guitar Hero is better suited for it than x,y movement of a cursor. Trying to control the equivalent actions of what you can do with a PS3 controller is out of the question.

Re:Microsoft demos muscle-computer interface, air Guitar Her... by Matti on Thursday August 02, 2012 @10:32AM (#4328910)
Would most or all participants reach cursor-to-target accuracies in the 98-100% range if you allowed them to continue training indefinitely?
Re:Microsoft demos muscle-computer interface, air Guitar Her... by aggie on Thursday August 02, 2012 @10:49AM (#4328989)
Probably yes. Our focus so far has been to demonstrate that it is physiologically possible to control multiple degrees of freedom with a single muscle site, so we haven't done extensive testing to address that. It's also worth noting that hitting a target and having very precise control of movement, as you would with a mouse, are not the same. I doubt the precision would ever reach that of a mouse, but it could conceivably get close.