The BCI control applied to the interactive autonomous robot with the function of meal assistance

Abstract

A brain-computer interface (BCI) system is proposed to control an interactive autonomous robot with a function to assist with feeding meals. The subject’s electroencephalogram (EEG), regarded as the control command, can be utilized to combine with system integration technologies to establish a BCI control robot system with an automatic feeding function. At present, the integrated technologies of the automatic feeding robot encompasses image recognition, voice recognition, the robot’s mechanism design, the gripper, tactile sensor design, etc. The automatic feeding robot can be controlled by steady state visual evoked potential (SSVEP)-based BCI to use the gripper grasping a utensil to ladle food to the subject’s mouth successfully. The signal processing algorithm adopted for the SSVEP-based BCI is magnitude squared coherence (MSC). Ten subjects participated in the BCI test for choosing the food on the plate. The average of MSC values for different visual stimulation frequencies were calculated and compared.