Using brain activity to control robotic limbs

The newest technology from the University of Minnesota helped paralyzed patients or those with neurodegenerative diseases are able to control a robotic arm with their brains.

Using an electroencephalography (EEG) based brain-computer interface, researchers were able to record brain activity and convert the “thoughts” into actions with advanced signal processes and machine learning.

"This is the first time in the world that people can operate a robotic arm to reach and grasp objects in a complex 3D environment using only their thoughts without a brain implant," said Bin He, a University of Minnesota biomedical engineering professor and lead researcher on the study. "Just by imagining moving their arms, they were able to move the robotic arm."

Researchers tested the cap on eight healthy participants who gradually learned how to control the robotic arm. Participants began with imaging their own arms controlling the robotic arm in a 3D environment. They then controlled a virtual cursor on a computer screen before moving on the controlling the robotic arm to reach and grasp objects on a table. The final step was to move the robotic arm, grab objects scattered around a table and move them onto a shelf.

All participants were able to control the arm to pick up objects with an average success rate of 80 percent. Participants had an average success rate of 70 percent when trying to then place the object onto the shelf. The next step for researchers is to develop a brain-controlled robotic limb with the same success as the arm as well as expanding the technology to work with someone who had suffered a stroke or is paralyzed.

"This is exciting as all subjects accomplished the tasks using a completely noninvasive technique. We see a big potential for this research to help people who are paralyzed or have neurodegenerative diseases to become more independent without a need for surgical implants," said He.