Previously, we reported on a technology called Brain-computer interface (BCI) which enables people with paralysis to control off the shelf tablet devices just by thinking about making cursor movements and clicks. Think of it like a mind-controlled mouse. BCI translates a participant’s brain activity into commands that a computer can understand. The research team that is evolving this science suggests that even people who lose their capacity to speak may be able to continue to communicate with this technology.
However, it required a baby aspirin-sized implant to detect the signals associated with intended movements produced in the brain’s motor cortex. Those signals are decoded by the implant and routed to external devices. A similar system had already proven successful in enabling people to move robotic arms or to regain control of their own limbs, despite having lost motor abilities from illness or injury.
The thing is, as wonderful as that is, it would be much better if it were possible without the implant, which requires brain surgery. This is what a team of researchers from Carnegie Mellon University, in collaboration with the University of Minnesota have managed to achieve. Their breakthrough in the field of noninvasive robotic device control uses a noninvasive brain-computer interface (BCI), meaning no implant required!
The researchers have developed the first-ever successful mind-controlled robotic arm exhibiting the ability to track and follow a computer cursor continuously. This could be a total life changer for paralyzed patients and those with movement disorders. Furthermore, as it wouldn’t require complex surgery, it would cost a lot less, making it affordable for many more people.
Being able to control robotic devices using only thoughts noninvasively could even be useful for many other applications; the potential of this technology’s usefulness is vast. For example, the technology could help a variety of people, by offering safe, noninvasive “mind control” of devices that can allow people to interact with and control their environments.
The ultimate goal in BCI research is to develop less invasive or even totally noninvasive technology that would allow paralyzed patients to control their environment or robotic limbs using their own “thoughts.” The reason implants have been necessary is because without them, the signal is not clear. But the researchers remained persistent with their mission to make it work so that the technology could quickly help patients everywhere on a daily basis.
Bin He, department head and professor of biomedical engineering at Carnegie Mellon University, said:
There have been major advances in mind controlled robotic devices using brain implants. It’s excellent science. But noninvasive is the ultimate goal. Advances in neural decoding and the practical utility of noninvasive robotic arm control will have major implications on the eventual development of noninvasive neurorobotics.
Bin He and his lab have been able to access signals deep within the brain using novel sensing and machine learning techniques. They have achieved a high resolution of control over a robotic arm this way. Bin He is overcoming the noisy EEG signals leading to significantly improved EEG-based neural decoding, and facilitating real-time continuous 2D robotic device control, through the use of noninvasive neuroimaging and a novel continuous pursuit paradigm.
This higher resolution signal has enabled (for the first time) the use of a noninvasive BCI to control a robotic arm that’s tracking a cursor on a computer screen. With human subjects, Bin He has shown that a robotic arm can now smoothly follow the cursor continuously, without the problem of jerky, discrete motions (as though the robotic arm was trying to “catch up” to the brain’s commands) like previous noninvasive BCI. The technology has been tested in 68 able-bodied human subjects so far (up to 10 sessions for each subject), including virtual device control and controlling of a robotic arm for continuous pursuit.
The team published a report of the study in Science Robotics. The paper explains their new framework that addresses and improves upon the “brain” and “computer” components of BCI by increasing user engagement and training, as well as the spatial resolution of noninvasive neural data through EEG source imaging. The team’s unique approach to solving this problem not only enhanced BCI learning by nearly 60% for traditional center-out tasks, but it also improved continuous tracking of a computer cursor by more than 500%.
Bin He said:
Despite technical challenges using noninvasive signals, we are fully committed to bringing this safe and economic technology to people who can benefit from it. This work represents an important step in noninvasive brain-computer interfaces, a technology which someday may become a pervasive assistive technology aiding everyone, like smartphones.
