Brain-Computer Interface Humanoid Pre-trained for Interaction with People

Abstract

People with the disabilities are in need to have an assistive technology that will alleviate their life through improving its social aspects. This article presents a Brain-Computer Interface (BCI) based remote presence system for humanoid NAO robot. The system would be useful for partially or fully paralyzed patients to interact with people and live active social life. A P300 based BCI is used to control high-level desires of the humanoid and visual stimulus presentation is implemented to control a humanoid robot. ”Programming by Demonstration (PbD)” methods are used to train the robot to perform human interactive actions and NAO robot native speller is used to talk with people. In general, the proposed solution combines two major techniques: Programming by demonstration and BCI. An experiment is designed and conducted on 5 different healthy subjects to perform a handshake, waving, walking and etc., verifying the applicability of the proposed approach.