Behavior Selection Method for Entertainment Robots Using Intelligence Operating Architecture

To get and hold a user’s attention, entertainment robots should be able to think and behave like a human being to show various responses in a certain situation. For this purpose, this paper proposes a behavior selection method for entertainment robots using intelligence operating architecture (iOA). The iOA consists of five parts and 15 modules to implement the robot intelligence, which is motivated by the key functions of human brain. In the internal state part, the strengths of the robot’s internal states, i.e. motivation, homeostasis, and emotion, are updated. The sensory information is converted to contexts in the context module. Considering both the internal states and contexts, a behavior which is composed of four expressions, i.e. facial expression, gesture, movement, and voice expression, is selected in the problem solving module. To show the effectiveness of the proposed method, a software entertainment robot is implemented for simulations. The simulation results show that entertainment robots with different characteristics can be created and they can generate various behaviors by the proposed behavior selection method.