A new SSVEP based BCI application on the mobile robot in a maze game

Abstract

In order to promote the quality of life for the subjects with motor neuron disease, an interesting maze game operated by steady state visual evoked potential (SSVEP) based brain-computer Interface (BCI) was developed. The SSVEP based BCI provides 4 options including: "counterclockwise", "clockwise" "forward" and "backward". A liquid crystal display (LCD) monitor is used as the visual stimulation device showing 4 option icons flickering at different frequencies respectively to induce subject's brain waves. Then the visual evoked potential signals of the subject can be acquired and pre-processed. The corresponding electroencephalogram (EEG) features are also extracted and identified in the decision model. According to the output results of decision model, the subject can control the mobile robot to move forward, backward or turn around. Ten subjects were asked to participate in the related experiments to evaluate the proposed EEG analysis method in the SSVEP based BCI system. The experimental results showed that the average accuracy of the SSVEP based BCI for controlling the mobile robot is above 83%. The result showed that the proposed SSVEP based BCI control is able to help the subjects with motor neuron disease enjoy the maze game entertainment.