Researchers Built the First Noninvasive Mind-Controlled Robotic Arm

The Six Million Dollar Man may no longer just be the title of a futuristic television show. We are getting closer and closer to that reality with every new robotic and medical discovery.

A team of researchers have made a major breakthrough in the field of noninvasive robotic device control and have developed the first ever successful robotic arm that is controlled by the mind using only thoughts.

The researchers from Carnegie Mellon University in Pittsburgh Pennsylvania, in collaboration with the University of Minnesota, used a noninvasive brain-computer interface (BCI) to control the robot arm that was able to continuously track and follow a computer cursor, according to a press release from Carnegie Mellon.

Previously, BCI’s have had a good performance controlling robotic devices using signals sensed from invasive brain implants. These implants require precision medical and surgical expertise to correctly install and operate the device at a very high price tag in terms of money and potential risk to the users. Because of this, they have been used in just a few clinical cases.

Being able to noninvasively control robotic devices will have a much broader use and will benefit people who are paralyzed or have movement disorders.

The biggest challenge to BCI research on noninvasive external sensing is that they receive “dirtier” signals that lead to less precision control of the robotic device. The implanted ones are much better. However, the researchers still believe that noninvasive technology is the way to go in terms of the number of patients that could be helped.

“There have been major advances in mind controlled robotic devices using brain implants. It’s excellent science,” Bin He, the department head and professor of biomedical engineering at Carnegie Mellon was quoted as having said in the press release. “But noninvasive is the ultimate goal. Advances in neural decoding and the practical utility of noninvasive robotic arm control will have major implications on the eventual development of noninvasive neurorobotics.”

He and his lab proved that they could access signals deep within the brain and achieved a high resolution of control over a robotic arm. They have managed to overcome the dirty or noisy EEG signals to achieve a real-time continuous 2D robotic design.

The research was published in the June 2019 issue of Science Robotics and shows the team’s unique approach to solving the enhanced BCI learning by almost 60 percent and enhanced continuous tracking by more than 500 percent. The technology was tested on 68 non-disabled people with up to 10 sessions for each and is directly applicable to patients. The team hopes to begin clinical trials in the near future.

“Despite technical challenges using noninvasive signals, we are fully committed to bringing this safe and economic technology to people who can benefit from it,” says He. “This work represents an important step in noninvasive brain-computer interfaces, a technology which someday may become a pervasive assistive technology aiding everyone, like smartphones.”

It’s hard to imagine all the uses for this noninvasive technology. People who are paralyzed could be able to walk or grasp and hold objects just by thinking about what to do. The advent of the six million dollar man is getting close.