Controlling robots with brainwaves and hand gestures
news.mit.edu
news.mit.edu
Without something invasive like implanted trans-cranial electrodes or non-portable like fMRI, you're never going to get anything past unreliable 1D control with the noise you get from trying to capture highly-attenuated microvolt potentials from the scalp.
I built a brainwave-controlled Pong game using EEG for fun for my university project back in 2012:
The time resolution of any existing fMRI implementation would be way to low for driving anythin mechanical reliably. The implanted electrodes though are being used already (lookup 'Obama handshake robot') and further researched. Very, very interesting stuff. Also depending on the implantation location one can theoretically get around the problem of EEG where people first have to learn to control the robot by randomly trying some thoughts to see what they do (because EEG just picks up everything): e.g. implant in the higher level motor action planning areas directly (well, if functional in the patient) is a better starting point.
It would be interesting to see if the brain could adapt to a new input and learn how to interpret it.
Rat experiments seem promising: http://www.sciencemag.org/news/2015/10/brain-implant-lets-ra...
On the other hand there's longevity of electrodes, making hardware smaller etc. And then, probably biggest thing for now, the software side: developing (possibly self-learning) accurate algorithms for decoding of the signals (both single-neuron spikes + low frequency spectrum of the surrounding area) is just hard. Also because a lot of things about the brain are in essence still rather unknown it's sometimes a bit of programming in the dark.