Mind Over Matter: Robotic Arm can be Controlled with Mind Power
With this new invention, the mind truly masters the body. A team with the University of Minnesota created a robotic arm that users control with their minds alone. This research could help millions paralyzed or suffering neurodegenerative diseases regain a sense of autonomy.
The system uses a non-invasive technique called electroencephalography (EEG) based brain-computer interface. Effectively, it takes weak electrical activity and turns those pulses into action. An EEG cap containing 64 electrodes converts those electrical impulses and thoughts into action.
“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 biomedical engineering professor and lead researcher on the study. “Just by imagining moving their arms, they were able to move the robotic arm.”
But He specializes in brain-computer interface study. Three years ago, He first developed the EEG cap and brain-computer interfaces (BCI) to fly a quadcopter drone with his mind. The video and research made international headlines. Now, He accomplished his goal of aiding in “bypassing[ing] damaged areas” of the brain.
“Three years ago, we weren’t sure moving a more complex robotic arm to grasp and move objects using this brain-computer interface technology could even be achieved,” He said to campus news. “We’re happily surprised that it worked with a high success rate and in a group of people.”
In this research, eight subjects walked through sessions wearing the EEG cap. First, they had to visualize using their arms moving without actually moving them. Then they controlled a computer screen cursor before using the robotic arm itself.
Each subject had to move the robotic arm to pick up and reach for objects on a shelf in front of them. The student subjects had an 80 percent average success rate in picking up objects from fixed locations. They had a slightly lower success rate of 70 percent on moving objects from the table to the shelf.
According to the research, a major challenge came from developing an interface complex enough to replicate true anthropomorphic control. The team had to delicately duplicate how the brain talks to the body without oversimplifying commands. They also had to craft a robotic arm responsive enough to acutely read the nuances of each subject’s thoughts.
The report even notes the Minnesota team became one of the first (if not the first) to succeed in using a prosthetic arm via EEG cap and BCI.
“Such previous efforts have primarily constrained the BCI control system to be discrete in one dimension or a plane without exploring the full possibility of controls in three-dimensional space,” the study noted.
he potential for such a project isn’t lost on He: “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.”
