The new findings, published in Science Robotics, could help people with paralysis use robotic arms with just their thoughts.

A team of researchers from Carnegie Mellon University and the University of Minnesota has collaborated to make a breakthrough in the field of noninvasive robotic device control.

Using a noninvasive brain-computer interface (BCI), the researchers have revealed the first-ever mind-controlled robotic arm that is able to track and follow a computer cursor. 

The findings could see life-changing applications for people suffering from neurological diseases and paralysis.

A big step for BCIs

BCIs have already shown success in allowing the control of robotic devices using signals sensed by brain implants. However, up until now, these devices have been invasive, needing surgery to place them in a patient’s brain.

Due to this, their use has been limited to only a few clinical trials. With the new findings, set out in a paper published in Science Robotics, this is now likely to change.

One of the great barriers to BCI development has been having less invasive, and noninvasive technology that would allow paralyzed patients to control robotic arms using their mind. Now, researchers seem to have overcome this boundary.

Technology in its infancy

BCI’s themselves are still in relatively early development, and noninvasive BCI’s are even further behind, with the noninvasive counterparts typically being slower and less precise.

Bin He, Trustee Professor and Department Head of Biomedical Engineering at Carnegie Mellon University, and his team of researchers are setting out to make improvements one step at a time.

“There have been major advances in mind-controlled robotic devices using brain implants. It’s excellent science,” He told Eurekalert.

“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.”

New findings

In the paper, published in Science Robotics, the team showed that they established their own framework for BCIs.

It addresses user engagement and training for the devices, as well as the spatial resolution of noninvasive neural data via EEG source imaging.

The paper, titled “Noninvasive neuroimaging enhances continuous neural tracking for robotic device control,” also highlights the fact that that the team’s specialized approach to noninvasive BCIs increased learning by nearly 60% for traditional center-out tasks.

Continuous tracking of a computer cursor was also enhanced by over 500%.

Experts hope the findings will lead the way for a world in which easy-to-use noninvasive BCIs can be used to vastly improve the quality of life for people with disabilities.