Patient on wheelchair, possibly disabled or battling multiple sclerosis (MS)

(© saelim -

AUSTIN, Texas — Scientists have developed a mind-controlled wheelchair that may transform the lives of people with severe disabilities. In experiments, quadriplegics paralyzed from the neck down were able to navigate through cluttered spaces — using brainpower alone.

Volunteers controlled direction by thinking about moving specific body parts, like their hands to turn left and feet to turn right. A computer turned neuronal signals into digital motor commands. Three men wore skullcaps fitted with electrodes that detected the communications via a transmitter.

“We show that mutual learning of both the user and the brain-machine interface algorithm are both important for users to successfully operate such wheelchairs,” says José del R. Millán, the study’s corresponding author from The University of Texas at Austin, in a media release.

“Our research highlights a potential pathway for improved clinical translation of non-invasive brain-machine interface technology.”

The chair, described in the journal iScience, will help paralyzed patients gain new mobility. Each individual underwent training sessions three times a week for two to five months.

2 patients achieved almost perfect accuracy

At the outset, they had similar levels of accuracy of around 43 to 55 percent, but that rose up to 98 percent during the training course. The headset uses a monitoring method known as EEG (electroencephalography), attaching small sensors to the scalp.

An algorithm was able to discriminate patterns encoded for “going left” from “go right.” The team identified improvements over time as a result of machine and human learning.

“We see from the EEG results that the subject has consolidated a skill of modulating different parts of their brains to generate a pattern for ‘go left’ and a different pattern for ‘go right,’” Millán says. “We believe there is a cortical reorganization that happened as a result of the participants’ learning process.”

By the end, two of the participants were able to drive their wheelchairs across a cluttered hospital room without assistance.

They went round obstacles, including screens and beds, that mimicked a real-world environment. Unfortunately, the third patients failed to complete the task.

His accuracy increased only slightly during the first few sessions and remained stable for the rest of the training period. This suggests machine learning alone is insufficient for successfully maneuvering such a mind-controlled device.

“It seems that for someone to acquire good brain-machine interface control that allows them to perform relatively complex daily activity like driving the wheelchair in a natural environment, it requires some neuroplastic reorganization in our cortex,” Millán explains.

The cortex is the brain area responsible for movement and sensation.

It takes constant practice to master the system

The study also emphasized the role of long-term training for potential users. Prof. Millan notes that one participant who performed exceptionally at the end of the study struggled in the first few training sessions.

The project is one of the first to evaluate clinical translation of non-invasive brain-machine interface technology for quadriplegics. These individuals lose the ability to voluntarily move the upper and lower parts of their body, usually through an accident.

The researchers now want to figure out why the one individual didn’t experience an improvement during the training period. They believe a more detailed analysis of all participants’ brain signals will shed light on the differences and open the door to interventions for those who struggle with the technology in the future.

South West News Service writer Mark Waghorn contributed to this report.

Our Editorial Process

StudyFinds publishes digestible, agenda-free, transparent research summaries that are intended to inform the reader as well as stir civil, educated debate. We do not agree nor disagree with any of the studies we post, rather, we encourage our readers to debate the veracity of the findings themselves. All articles published on StudyFinds are vetted by our editors prior to publication and include links back to the source or corresponding journal article, if possible.

Our Editorial Team

Steve Fink


Chris Melore


Sophia Naughton

Associate Editor