Using a cognitive model to include human emotions and intentions in Human-Machine Interaction

Detection and understanding of human intentions and emotions are relevant aspects of human-machine interaction, and the paper deals with a possible approach based on a cognitive framework named SeARCH-In (Sensing-Acting-Reasoning: Computer understands Human Intentions). The paper describes how the PSI cognitive model is implemented by visual perception capabilities, and managing semantic knowledge trough a suitable ontology. The proposed implementation will be able to recognize user faces, to recognize and track human postures by visual perception. The ontological knowledge approach is employed for human behavior and expression comprehension, and the stored user habits are used for building a semantically meaningful structure for perceiving human intentions.