Researchers at Korea University in Seoul, South Korea and Technical University of Berlin in Germany have created a brain-computer interface for a lower limb exoskeleton that decodes signals from the user’s brain for the user to move forward, turn side to side and stand. The results of the study were published in the Journal of Neural Engineering.
According to a joint press release from the two universities, the system uses an electroencephalogram (EEG) cap to decode brain signals as users stare at one of five flickering light emitting diodes (LEDs), each of which flickers at a different frequency. The use of EEG allows the researchers to separate the signals generated by the exoskeleton from other brain signals and identifies them through the EEG readout.
“Exoskeletons create lots of electrical ‘noise,’” Klaus-Robert Müller, PhD, professor and researcher in the Machine Learning Group, Department of Computer Science at Technical University (TU) of Berlin and an author on the paper, said in the release. “The EEG signal gets buried under all this noise — but our system is able to separate not only the EEG signal, but the frequency of the flickering LED within this signal.”
Shown is a volunteer operating the brain-computer control interface.
Source: Korea University and TU Berlin
Müller and colleagues tested the system on healthy individuals, but believe it has the potential to help people with amyotrophic lateral sclerosis or high spinal cord injuries to walk. The control also works as an add-on to other devices, according to the release. The next step for the researchers is working to reduce the “visual fatigue” crated by long-term use of a system relying on flickering LEDs.
“We were driven to assist disabled people, and our study shows that this brain control interface can easily and intuitively control an exoskeleton system — despite the highly challenging artefacts from the exoskeleton itself,” Müller said.
Reference: Müller K-R, et al. J Neural Eng. 2015;doi: 10.1088/1741-2560/12/5/056009.
Disclosure: See the study for authors’ relevant financial disclosures.
