Ann Arbor Times

A brain-computer interface has enabled a research participant with tetraplegia to control a virtual quadcopter by thinking about moving his fingers. This technology divides the hand into three parts: the thumb and two pairs of fingers, allowing each part to move vertically and horizontally. The participant's thoughts about these movements direct the virtual quadcopter through an obstacle course.

“This is a greater degree of functionality than anything previously based on finger movements,” said Matthew Willsey, assistant professor at U-M and first author of the study published in Nature Medicine. The research was conducted while Willsey was at Stanford University.

Noninvasive approaches like electroencephalography (EEG) are less precise as they gather signals from large brain regions. In contrast, this study showed improved performance by reading signals directly from motor neurons, achieving a sixfold enhancement in quadcopter flight control.

The procedure involves placing electrodes in the brain’s motor cortex, which are wired to a pedestal connected to a computer. “It takes the signals created in the motor cortex that occur simply when the participant tries to move their fingers and uses an artificial neural network to interpret what the intentions are,” explained Willsey.

Conducted as part of BrainGate2 clinical trials, this research explored how neural signals could be combined with machine learning for external device control for those with neurological injuries or diseases. The participant joined the Stanford team in 2016 after a spinal cord injury left him unable to use his limbs.

“The quadcopter simulation was not an arbitrary choice; the research participant had a passion for flying,” said Donald Avansino, co-author and computer scientist at Stanford University.

Co-author Nishal Shah emphasized that controlling fingers is just one step toward whole-body movement restoration. Jaimie Henderson from Stanford noted that beyond games, this work fosters human connection: “People want to play games and interact with their friends.”

Henderson added that multifactor control schemes could extend to operating various software applications or composing music.

Researchers Nick Hahn, Ryan Jamiolkowski, Foram Kamdar, Francis Willett at Stanford, and Leigh Hochberg at Brown University also contributed to this study.

CAUTION: Investigational Device. Limited by Federal law to investigational use.