An international team of researchers has developed a new wearable brain-machine interface (BMI) system that allows its users to control a wheelchair or robotic arm by imagining an action. The system offers hope for better quality of life for people with physical disabilities, including patients with locked-in syndrome, who are unable to move or communicate despite being fully conscious.
BMI systems such as electroencephalography (EEG) collect brain signals and process them into commands. They usually depend on wires, take long to set up, are uncomfortable, and need gels and pastes to keep skin contact.
Under the leadership of associate professor Woon-Hong Yeo, a research team at the Georgia Institute of Technology paired wireless soft scalp electronics with virtual reality to create a new, portable BMI system. “The major advantage of this system to the user, compared to what currently exists, is that it is soft and comfortable to wear, and doesn’t have any wires,” explains Yeo, who is the director of Georgia Tech’s Center for Human-Centric Interfaces and Engineering, in a statement.
While EEGs frequently struggle with low-grade signal collection, the researchers have improved this issue in the new device. It employs imperceptible microneedle electrodes integrated with soft wireless circuits, as well as a machine-learning algorithm along with virtual reality to ensure the device accurately translates brain signals into actions.
So far, the device has only been tested on able-bodied subjects. “This is just a first demonstration, but we’re thrilled with what we have seen,” says Yeo.
During testing, device users were able to accurately control virtual reality with their thoughts and contributed to the researchers’ information gathering process. “The virtual prompts have proven to be very helpful,” he adds. “They speed up and improve user engagement and accuracy. And we were able to record continuous, high-quality motor imagery activity.”
The team’s future research will explore more advanced integration of stimulus-based EEG and how to further improve the device’s electrode placement.
The study appeared in the journal Advanced Science.