Academics develop mind-controlled wheelchairs for tetraplegics

When it comes to advances for people with neurological disabilities and paralysis, the brain-computer interface (BCI) projects of Neuralink and the Defense Advanced Research Projects Agency’s (DARPA’s) Brain Initiative show great promise, especially when it comes to mobility.

There are some major problems though. Progress on this front has often been slow, expensive, and—largely—failed to transfer from a lab setting to the real world.

But that’s not to say there aren’t other companies making huge strides in BCI technology for people with paralysis.

Join TNW in Valencia!

The heart of technology is coming to the heart of the Mediterranean

A paper published this week by a German, Italian, Swiss, and American academic team looked at just that. It shared a successful research project in which three participants with tetraplegic spinal-cord injury (paralyzed from the shoulders down) successfully controlled an electric wheelchair with their minds. This includes navigating, steering, turning and controlling the chair’s motion through hospital obstacle courses.

The customized powered wheelchair used in the study is equipped with an RGB-D camera, a laser rangefinder and a small monitor for brain-machine interface feedback.

Participants wore an electrode-covered cap that recorded the brain’s electrical activity, otherwise known as an electroencephalogram (EEG). An amplifier transmits these electrical signals to a computer that interprets the intentions, turning them into movements.

Participants trained by mobilizing the wheelchair, such as imagining turning a steering wheel, and expanding their ability in three sessions a week over five months.

Why is this research important?

This research has increased the efficiency of both the brain-machine interface and the subject

In addition to being a great example of cross-institutional collaboration, the study is important for several reasons. Until now, people have had to surgically insert electrical implants into the motor regions of their brains to control these types of machines.

Surgery is not only risky, but inappropriate for many people. Furthermore, this is the only study of its kind not limited to able-bodied subjects. You read that right, most studies fail to use the people who will be the end users of the technology.

Research is also significant because it involves an intensive and long period of training in which participants’ abilities may increase over time. It also offers skill development in ways that are applicable in a real-world setting.

At the end of the research project, the two participants were able to move the wheelchairs with an impressive 95 to 98% accuracy, an increase from the original score of 43 to 55%. This result comes from improvements in the computer’s ability to decode patterns of brain activity that indicate a desire to move left or right. A third participant did not improve.

And while the computer’s AI got smarter throughout longitudinal training, the most successful participants also learned to act with computer. Users were able to help the computer understand their intentions, effectively teaching as they learned. This led to changes in their brain activity and showed the potential for people who could benefit from training to control a motorized wheelchair using a brain-machine interface.

Tetraplegia is one of the most debilitating conditions around. Although the study represents only a small test sample of people living with severe disabilities, it provides a precedent for future research and shows a new direction for neurological research.