RESEARCH | CARNEGIE MELLON COLLEGE OF ENGINEERING
Breakthrough in Mind-Controlled Robotic Arm
A team of researchers from Carnegie Mellon University, in
robotic limbs using their own “thoughts.” Such noninvasive
collaboration with the University of Minnesota, has made
BCI technology, if successful, would bring such much-
a breakthrough in the field of noninvasive robotic device
needed technology to numerous patients and even
control. Using a noninvasive brain-computer interface (BCI),
potentially to the general population.
researchers have developed the first-ever successful mind-
However, BCIs that use noninvasive external sensing,
controlled robotic arm exhibiting the ability to continuously
rather than brain implants, receive “dirtier” signals, leading
track and follow a computer cursor.
to lower resolution and less precise control. Thus, when
Being able to noninvasively control robotic devices using
using only the brain to control a robotic arm, a noninvasive
only thoughts will have broad applications, in particular
BCI doesn’t stand up to using implanted devices. Despite
benefiting the lives of paralyzed patients and those with
this, BCI researchers have forged ahead, their eye on the
movement disorders.
prize of a less- or non-invasive technology that could help
BCIs have been shown to achieve good performance for controlling robotic devices using only the signals sensed from
patients everywhere on a daily basis. Bin He, department head and professor of biomedical
brain implants. When robotic devices can be controlled with
engineering at Carnegie Mellon University, is achieving that
high precision, they can be used to complete a variety of daily
goal, one key discovery at a time.
tasks. Until now, however, BCIs successful in continuously
“There have been major advances in mind controlled
controlling robotic arms have used invasive brain implants.
robotic devices using brain implants. It’s excellent science,”
These implants require a substantial amount of medical
says He. “But noninvasive is the ultimate goal. Advances
and surgical expertise to correctly install and operate, not to
in neural decoding and the practical utility of noninvasive
mention cost and potential risks to subjects. As such, their use
robotic arm control will have major implications on the
has been limited to just a few clinical cases.
eventual development of noninvasive neurorobotics.”
A grand challenge in BCI research is to develop less
Using novel sensing and machine learning techniques,
invasive or even totally noninvasive technology that would
He and his lab have been able to access signals deep within
allow paralyzed patients to control their environment or
the brain, achieving a high resolution of control over a
