Mobile Robot Control by BCI Based on Motor Imagery

Abstract

Current interests in BCI development mainly derive from rehabilitation engineering, assistant control for normal people, entertainment, brain cognition, and so on. This paper has developed an online mobile robot control system by BCI based on motor imagery (MI). In the system, the user can give control command by 'thinking'. The EEG signals from the user are acquired by a biological signal acquisition system. The MI, specific signal features that reflect the user's intent are extracted and translated into control commands. Through the wireless network, the computer can communicate with the mobile robot. The control commands can control the robot motion. The videos on the PC screen from the camera on the robot feedback to the user. Thus, the user can use feedback information to develop and maintain good correlation between his or her intent and the signal features employed by the BCI. The experimental results show that the system can extract features and translate those features into the robot commands correctly and efficiently for the real-time mobile robot control.