A p300 model for cerebot - A mind-controlled humanoid robot

Abstract

In this paper, we present a P300 model for control of Cerebot - a mind-controlled humanoid robot, including a procedure of acquiring P300 signals, topographical distribution analysis of P300 signals, and a classification approach to identifying subjects’ mental activities regarding robot-walking behavior. We design two groups of image contexts to visually stimulate subjects when acquiring neural signals that are used to control a simulated or real NAO robot. Our study shows that the group of contexts using images of robot behavior delivers better performance.