Towards affective integration of vision, behavior, and speech processing

Abstract

In each subfield of artificial intelligence such as image understanding, speech understanding, robotics, etc., a tremendous amount of research effort has so far yielded considerable results. Unfortunately, they have ended up too different to combine with one another straight-forwardly. We have been conducting a case study, or AESOPWORLD project, aiming at establishing an architectural foundation of "integrated" intelligent agents. In this article, we first review our agent model, which integrates the seven mental and the two physical faculties: recognition, planning, action, desire, emotion, memory, language, and sensor, actuator. We then describe each faculty of recognition, action, and planning, and their interaction by centering around planning. Image understanding is understood as a part of this recognition. Next, we show dialogue processing, where the faculties of recognition and planning also play an essential role for communications. Finally, we discuss the faculty of emotions to show an application of our agent to affective communications. This computation of emotions could be expected to be a base's for human-friendly interfaces.