AUSTIN, Texas — In one of the first studies of its kind, several people with motor disabilities were able to use a wheelchair that translates their thoughts into motion.
The study conducted by researchers at the University of Texas at Austin and published today in the journal iScience is an important step forward for brain-machine interfaces – computer systems that turn mental activity into action. The concept of a thought-powered wheelchair has been studied for years, but most projects have used able-bodied subjects or stimuli that cause the device to more or less control the person rather than the other way around.
In this case, three quadriplegics, unable to move their arms and legs due to spinal injuries, used the wheelchair in a crowded natural environment with varying degrees of success. The interface recorded their brain activity and a machine learning algorithm translated it into commands that steered the wheelchair.
The researchers said this is a sign of future commercial viability for mentally powered wheelchairs that can help people with limited motor function.
“We have demonstrated that the people who will actually be the end users of these types of devices are able to navigate in a natural environment using a brain-machine interface,” said José del R. Millán, professor at the Cockrell School of Electrical and Computer Engineering at the Chandra Family of Engineering, which led the international research team. Millán is also a professor of neurology at Dell Medical School at UT Austin.
The study is further important because of the non-invasive equipment used to operate the wheelchair. The researchers did not implant any type of device into the participants, nor did they use any type of stimulation on them.
The participants wore a cap covered with electrodes that recorded electrical activity in the brain, known as an electroencephalogram (EEG). An amplification device sent these electrical signals to a computer which interpreted each participant’s intentions and translated them into movement.
When people sustain severe injuries that end in paralysis, the brain loses pathways to transmit commands to the body and create movement. But the mind remains active and the interface is able to capture and facilitate movement, as if the brain is talking to the body instead of a computer.
Two important dynamics largely contributed to the success of the study. The first is a user training program.
Users learned methods to visualize the movement of the chair as if they were imagining moving their hands and feet. When researchers observed study participants, they saw changes in their brain activity as they spoke commands.
The second contributor borrows from robotics. The researchers fitted their wheelchairs with sensors to understand the surrounding environment. And they also deployed robotic intelligence software that helped the chair fill in the blanks in user commands to facilitate precise and safe movement of the wheelchair.
“It works a bit like riding a horse,” Millán said. “The rider can tell the horse to turn left or enter a gate. But the horse will ultimately have to figure out the best way to execute those commands.
This research complements another project Millán has been working on, the creation of a new EEG electrode that can be worn for long periods of time without being replaced.
Long-term electrodes are part of the ultimate goal of these projects. And the researchers plan to integrate all the other technologies involved directly into the modified wheelchair.
Project team members include Luca Tonin of the University of Padua in Italy; Serafeim Perdikis from the University of Essex; Taylan Deniz Kuzu, Jorge Pardo, Thomas Armin Schildhauer, Mirko Aach and Ramon Martinez-Olivera from Ruhr-University Bochum in Germany; Bastien Orset from the Federal Polytechnic School of Lausanne in Switzerland; and Kyuhwa Lee from the Wyss Center for Bio and Neuroengineering in Switzerland.
#Brainpowered #wheelchair #shows #promise #real #world #Dell #School #Medicine