An emotion-generation model for a robot that reacts after considering the dialogist

Abstract

This paper proposes an emotion-generation model for a robot that distinguishes different aspects of a human's personality. The robot reacts differently, depending on the human communication it receives. In this cutting-edge research area, several studies have demonstrated robots that generate reactions to humans by judging their interaction. However, these reactions do not change when the communicating human displays a variety of personality traits. This is because the robot only responds to the input without taking the human's personality into account. To solve this issue, we propose an emotion-generation model for robots that produces different reactions depending on the human communication it receives. In this model, the robot has a degree of intimacy that judges the human's personality. The degree of intimacy increases when the human satisfies the robot's desire and decreases when he/she does not. The simulation results confirmed that the robot shows a friendly reaction to a human with a high degree of intimacy and an unfriendly reaction to one with a low degree of intimacy.