8 SERVO 09.2013
by Jeff and Jenn Eckert
Back in 1994, a concerned
citizen wrote to the L.A. Police
Department and claimed that — if
they would allow it — he could
connect a slew of electromagnetic
sensors to the brain of O.J.
Simpson's dog and thus obtain its
testimony in the murder case.
Presumably, he was put away
somewhere for his own safety, but
researchers at the University of
Minnesota's College of Science and
Engineering ( cse.umn.edu) have
accomplished pretty much the same
thing — minus Fido.
By strapping a skullcap fitted with
64 electrodes onto some of his
students, Prof. Bin He enabled them to deftly control the
movements of a quadcopter using only their thoughts.
During the tests, the subjects faced away from the UAV
and imagined using their hands to make it turn right,
turn left, rise, and fall. Their brainwaves were relayed to
the 'copter via Wi-Fi, and they tracked its motion on a
screen that displayed images from an onboard camera.
After a few training sessions, each student was able to
navigate through large rings suspended from the ceiling.
This isn't all fun and games, however. According to
Karl LaFleur, a senior engineering student and one of the
participants, "Our next step is to use the mapping and
engineering technology we've developed to help disabled
patients interact with the world. It may even help
patients with conditions like autism or Alzheimer's
disease, or help stroke victims recover. We're now
studying some stroke patients to see if it'll help rewire
brain circuits to bypass damaged areas."
Mind-controlled UAV navigates through garlands of balloons.
This is Research?
You have to admire academic’s creative use of language. For
example, who would suspect that when researchers at Chiba
University's Namiki Lab ( mec2.tm.chiba-u.jp) set out "to develop
the technology of a high speed human-interactive robot in which
the robot reads the opponent's intention and moves in response
to the opponent's motion and human purpose expectation," they
were really just programming a Barrett four-axis arm to play air
hockey. Robots have already been doing that for years.
For example, a You Tube video from back in 2006 shows a
Sarcoman unit doing the same thing. The difference, however, is
that this one "is able to strategize playing against its human
opponent" and shift its strategy based on how the opponent
The obvious next step is to supplement the robotic strategic
dynamism with algorithms to optimize the human
implementation of malted grain-derived potables (i.e., teach the
robot to bring me a beer.)
Robotic player anticipates its opponent's moves.