Robot Competition to Evaluate Guidance Skill for General Users in VR Environment

Abstract

Robot competition such as RoboCup@Home is one of the most effective ways to evaluate the performance of human-robot interaction; however, it takes a lot of costs for real robot maintenance and the practice of evaluation sessions. We have proposed a simulation software to evaluate human-robot interaction in daily life environment based on immersive virtual reality. In this paper, we design a task named `human navigation' in which the evaluation requires a subjective impression by the users. Through a substantiative experiment, we confirmed that the proposed task and system reduced the cost for the practice of the competition.