Machinery for artificial emotions

Abstract

We present a preliminary definition and theory of artificial emotion viewed as a sequential process comprising the appraisal of the agent global state, the generation of an emotion-signal, and an emotion-response. This theory distinguishes cognitive from affective appraisal on an architecture-grounded basis. Affective appraisal is performed by the affective component of the architecture; cognitive appraisal is performed by its cognitive component. A scheme for emotion classification with seven dimensions is presented. Among them, we emphasize the roles played by emotions and the way these roles are fulfilled. It is shown how emotions are generated, represented, and used in the Salt & Pepper architecture for autonomous agents (Botelho, 1997). Salt & Pepper is a specific architecture comprising an affective engine, a cognitive and behavioral engine, and an interruption manager. Most properties of the cognitive and behavioral engine rely upon a hybrid associative, schema-based long-term memory. In Salt & Pepper, emotion-signals, represented by label, object of appraisal, urgency, and valence, are generated by the affective engine through the appraisal of the agent's global state. For each emotion-signal there are several nodes stored and interconnected in long-term memory. Each of these nodes contains an emotion response that may be executed when an emotion-signal is generated. Emotion intensity relates to the activation of the node. It is shown that the Salt & Pepper architecture for autonomous agents exhibits several properties usually related to emotion: state and mood congruence, compound emotions, autonomic emotion-responses, and different emotion-responses to the same stimulus including the generation of different motives. The implementation of a concrete example is described.