Narrative reasoning for cognitive ubiquitous robots
Résumé
The symbolic spatio-temporal reasoning is one of the major research challenges aiming to increase the autonomy and cognitive capabilities of ubiquitous robots in ambient intelligent systems. In these environments, there are several situations that are governed by complex processes and where multiple events must be correlated with respect to their spatial and temporal ordering to infer the right situation and to take the right decision. Inferring everyday human activities is a typical example that illustrates the complexity of spatiotemporal modeling and reasoning at a high semantic level. The ambition of this paper is to explore the potential of the narrative representation and reasoning for recognizing and understanding situations. This approach uses hierarchical structures of semantic predicates and functional roles of the Narrative Knowledge Representation Language (NKRL) and allows semantic descriptions of entities, events and relationships between events. A scenario dedicated to the monitoring, in smart home, of elderly people is presented and analyzed to show the feasibility of the proposed approach and its capacity to explain causal chains between observed events.