Brain-Computer Interface Based Stochastic Navigation and Control of a Semiautonomous Mobile Robot in an Indoor Environment

In this paper, we propose a brain-computer interface (BCI) based on the control strategy which combines the simultaneous localization and mapping (SLAM) to obtain the unknown environmental information and builds a global environment map for a mobile robot. The online BCI analyzes the electroencephalograph (EEG) signals based on steady-state visually evoked potentials (SSVEP) that the human intentions can be recognized accurately, and the motion commands are produced by the multivariate synchronization index (MSI) algorithm. Probability potential fields (PPF) approach based on the probability density function of two dimensional normal distribution is connected with the brain signals to produce the motion commands which generate a trajectory without collision. The whole system is semi-autonomous when the RGB landmarks are regarded as the environmental features learned by the FastSLAM algorithm, and the robot's low level behaviors are autonomous since the stochastic navigation is executed by the BCI. In addition, a kinematic controller is also adopted to control the low level movements. The entire system has been tested and the results have verified the effectiveness of the proposed approach.