University of Minnesota researchers have developed a way to control a robotic arm by using their minds.
While it is not necessarily mind control, it does have some interesting implications to help millions of people who are paralyzed or have neurodegenerative diseases.
The technology uses a noninvasive technique called electroencephalography (EEG), where researchers created a brain-computer interface and made a specialized EEG cap fitted with 64 electrodes that converts “thoughts” into action through advanced signal processing and machine learning.
Subjects were able to reach and grasp objects at random and fixed locations on a table, and move objects off the table to another surface. Source: University of Minnesota “This is the first time in the world that people can operate a robotic arm to reach and grasp objects in a complex 3-D environment using only their thoughts, without a brain implant,” says Bin He, a University of Minnesota biomedical engineering professor. “Just by imagining moving their arms, they were able to move the robotic arm.”
Researchers tested eight human subjects wearing the EEG cap, and the subjects gradually learned to imagine moving their own arms—without actually moving them—to control the robotic arm in 3-D space. By learning to control a virtual cursor on a computer screen, participants used the robotic arm to reach and grasp objects in fixed locations on a table. Later they were able to do the same with objects in random locations on a table. They were also able to move objects from the table to a three-layer shelf by only thinking about the movements.
All eight subjects were able to control the arm and pick up objects in fixed locations with a success rate of about 80%. Moving objects from the table to the shelf averaged a success rate of above 70%.
How It Works
The EEG cap works because of its geographical relation to the motor cortex—the area of the brain that allows movement, researchers say. When humans think about moving or begin moving, neurons in the motor cortex product electric currents. Just thinking about these different movements activates new assortments of neurons.
Differentiating these assortments with advanced signal processing led to the brain-computer interface used in the research project. Bin He has been working on the technology for more than three years. He began his research by flying a small quadcopter using EEG technology.
“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 says. “We’re happily surprised that it worked with a high success rate and in a group of people.”
The next step is to test the interface technology on a robotic prosthetic limb attached to a human body, or to examine how the technology could work with someone who had a stroke or is otherwise paralyzed.
