Developing sophisticated robot reactions by long-term human interaction

Abstract

In this study, we proposed an emotion generation model for robots that considers mutual effects of desires and emotions. Many researchers are developing partner robots for communicating with people and entertaining them, rather than for performing practical functions. However, people quickly grow tired of these robots owing to their simplistic emotional responses. To solve this issue, we attempted to implement the mutual effects of desires and emotions using internal-states, such as physiological factors. Herein, the simulation results verified that the proposed model expresses complex emotions similar to humans. The results confirmed that the emotions expressed by the proposed model are more complex and realistic than those expressed by a reference model. © 2013 Springer-Verlag.