The purpose of this paper is to construct a methodology for smooth communications between humans and robots. Here, focus is on an anthropomorphic mechanism which is indispensable in human-artifact communications. In this paper we propose a model of utterance understanding based on the anthropomorphic mechanism in the emerging relationship between humans and robots. Concretely speaking, we implement a robot interface system that applies our proposed model. The characteristic of our interface system is its ability to construct a relationship between a human and a robot by a method of having an agent which interacts with the person, migrates from the mobile PC of the person to the robot. Psychological experiments were carried out to explore the validity of the following hypothesis: By anthropomorphizing a robot based on such a relationship, a person can estimate the robot's intention with ease, and, moreover, the person can even understand the robot's unclear utterances made by synthesized speech sounds. The results of the experiments statistically supported our hypothesis.