Effect that presentation method by YOLO’s object recognition results gives to an operator wearing HMD on mobile robot remote control system

Abstract

An operator feels a burden when he/she controls a rescue robot remotely because it is necessary to keep watching camera image to find target object. We think this burden can be improved by using deep learning object recognition. In this study, we examine effect that how presentation method by YOLO’s object recognition results gives to an operator wearing HMD. In the experiment, three methods of presentation were set: no object recognition, only one object recognition result, and 80 kinds of object recognition results. Under each presentation method, we measured time it took for the operator to operate the robot and complete the given task. In addition, we ask a questionnaire for each experiment. The results of the questionnaire showed that method to present only one object recognition result was useful.