In order to design and realize intelligent autonomous agents, a very active research trend has concentrated its attention on the study of models of mental activity, encompassing the explicit representation of mental attitudes. In this paper we propose an original point of view about mental activity modeling, founded on two basic claims: i) mental attitudes should be regarded as autonomous active entities; ii) an intelligent agent should be conceived as a distributed structure, where global behavior is produced by interactions among active mental entities.In order to substantiate and motivate this proposal, attention is focused on two mental entities, namely intention and persuasion, and their main features are illustrated and discussed. Later, a general agent architecture based on active mental entities is introduced, its basic components are defined, and its operation outlined. The proposed paradigm is then illustrated through some examples concerning an application to autonomous mobile robot control architectures.
Publisher's on-line resources