Development of control assistant system for robotic wheelchair-estimation of user's behavior based on measurements of gaze and environment

Abstract

We develop a control assistant system for a robotic wheelchair as a guide robot. This system detects the head pose and gaze direction of the user and recognizes a position and surrounding environment using sensors and a map. Since the system can detect where the user is looking from the measurements, it can estimate attentions of the user on the wheelchair. Experimental results prove that the user's intentions and attentions are related with the duration of gaze and can be distinguished by the information which our robotic wheelchair system can measure.