Dynamic Behavior Selection Model based on Emotional States for Conbe-I robot

Abstract

Currently, the rapid development of non-industrial robots that are designed with artificial intelligence (AI) methods to improve the robotics system is to have them imitate human thinking and behavior. Therefore, our works have focused on studying and investigating the application of brain-inspired technology for developing the conscious behavior robot (Conbe-I). We created the hierarchical structure model, which is called ``Consciousness-Based Architecture: CBA{''} module, but it has limitation in managing and selecting the behavior that only depends on the increase and decrease of the motivation levels. Consequently, in this paper, we would like to introduce the dynamic behavior selection model based on emotional states, which develops by Self-organizing map learning and Markov model in order to define the relationship between the behavioral selection and emotional expression model. We confirm the effectiveness of the proposed system with the experimental results.