Cognitive architecture for F-2 companion robot to support semantic shifts and cognitive domains via scenario oppositions

Abstract

We develop an applied cognitive architecture, which can operate on companion robots and support cognitive functions typical of higher order human communication, such as humor and cognitive domains like imagination, irony and theory of mind. In the applied studies this architecture, developed as a real-world interface for the cognitive model, operates on F-2 companion robot or runs text processing on the server without the robot. The robot constructs representation for speech, visual and tactile events in a unified way, based on the semantics representations. To simulate cognitive domains and humor, we implement parallel processing of speech syntax and semantics, so that a meaning for an alternative syntactic tree (homonymy) can be used for a humorous utterance. The parallel processing is implemented via an engine of scenarios – if-then operators or productions. The scenarios, invoked by a stimulus, compete with each other basing on the oppositions of their semantic markers. The winning scenario forms a “believable” representation of a stimulus for the robot, while the suppressed (opposed) scenarios form the representations of cognitive domains. If a stimulus is evaluated as “bad”, but an opposed scenario suggests “good” representation, this representation is used for imagination. If a scenario suggests an emotional interpretation and assigns “me/myself” marker, while the correct representation suggests “another” person in this position, this representation is used for the theory of mind – another person’s point of view. Scenarios, departing from a stimulus, are also used as an inference engine that forms derived semantic representations to be replied by the robot. This mechanism is also combined with emotional evaluation, as a rational inference may invoke emotions or shift the category of an object in the initial stimulus.