An innovative brain-computer interface (BCI) allowed a quadriplegic man to pilot a virtual drone through a complex obstacle course using nothing but… his thoughts.
The individual, who remains anonymous, lost mobility due to a spinal cord injury and was fitted with a BCI with 192 electrodes implanted in the region of the brain responsible for hand movement, according to a study published January 20 in Nature Medicine.
Researchers at the University of Michigan, led by Matthew Willseydeveloped a AI algorithm to interpret the neural signals captured by the electrodes. By imagining specific finger movements, the participant was able to generate different signals to control the virtual drone, according to .
The AI model mapped the participant’s brain activity to imagined movements, allowing them to control four distinct entrances: two signs derived from the imagination of movements of different pairs of fingers and two others from the thumb.
With practice, the subject gained the ability to navigate the virtual drone accurately, maneuvering it through obstacles with ease. Although a real drone could have been used, the experience was carried out virtually to prioritize safety and convenience.
The experience takes on even greater meaning knowing that the individual had a long-standing passion for flying.
“For him, it was a dream come true. which he thought was lost when he suffered the injury. He had a passion and a dream to fly. He seemed very capable and qualified; he would ask us to make videos and send them to friends,” Willsey said.
Recent advances in BCI — especially Elon Musk’s Neuralink — have allowed people with paralysis to dictate text through a .
Despite the success, there are still obstacles. Each user needs individualized training to calibrate the AI model, and this training must be repeated over time as electrode performance declines due to brain changes or signal variability.
