Recognizing behaviors and the internal state of the participants

Psychological research has demonstrated that subjects shown animations consisting of nothing more than simple geometric shapes perceive the shapes as being alive, having goals and intentions, and even engaging in social activities such as chasing and evading one another. While the subjects could not directly perceive affective state, motor commands, or the beliefs and intentions of the actors in the animations, they still used intentional language to describe the moving shapes. We present representations and algorithms that enable an artificial agent to correctly recognize other agents' activities by observing their behavior. In addition, we demonstrate that if the artificial agent learns about the activities through participation, where it has access to its own internal affective state, motor commands, etc., it can then infer the unobservable internal state of other agents.