A Fuzzy Emotional Agent for Decision-Making in a Mobile Robot

Emotions have been shown to have a significant influence on the decision-making process of human beings and, thus, play an important role in intelligent behavior. As a means of providing similar intelligence, we are investigating the use of emotional agents in the decisionmaking process of a mobile robot. We propose a fuzzy logic model that captures the inherent uncertainty of emotions. The model is used to generate decisions based on both internal and external states and incorporates the use of sensory information to extract environmental conditions. In this way, the agent will react to a changing environment and can take an action according to a mixture of emotions generated by multiple states. As a first step towards addressing the complexity, the model deals with three negative emotions: fear, pain and anger, chosen because of their innate structure. In this paper, we discuss our fuzzy logic model and describe the implementation of an emotional agent on a small mobile robot in which sensory information is used to generate emotions.