An experiment study of gesture-based human-robot interface

Abstract

Mutual adaptation is considered as a key issue in realizing interactive robot systems that play an important role in the field of medical robotics. In order to develop a mutually adaptive interactive robot system, we take a bootstrapping approach consisting of three stages: a human-human WOZ experiment, a human-robot WOZ experiment, and a human-adaptive robot experiment. Recently, we entered the third stage where we developed an experimental environment of the gesture-based human-robot interface using a motion glove and conducted an experiment to compare it to a traditional joystick interface. Primary results of this experiment suggested that the environment works well as a one-way adaptive interface system because some adaptive behaviors were observed. In addition, we have found that the gesture-based interface can work more efficiently and reduce the average task completion time compared to the joystick interface, although the subjective evaluation of its easiness of use is inferior to that of a joystick at present.