A robot emotion model with history

Abstract

In this paper, we present a novel robot emotion model that can be used for social robots engaged in human-robot interactions (HRI). The proposed model effectively determines the robot's emotional state based on its own emotion history, the affect of the user whom the robot is interacting with, and the HRI task at hand. The model uniquely uses an nth order Markov Model (MM) to track the robot's emotion history during interactions. Simulated experiments were conducted using the robot emotion model to persuade different users to comply with various tasks. The results showed that the model is able to effectively determine a robot's emotion based on different input scenarios. Furthermore, the novel use of emotion history allows the robot emotion model to be trained faster.