DeLP based Semantic Location Lattice for Intelligent Robotic Navigation

Location models require a well-defined representation of spatial connectivity and hierarchical relationship between different spatial concepts; and are fundamental for location navigation, location based services and contextual query responses. Current location models rely on a priori knowledge of surrounding environment and mostly the semantics of relationships are over-looked. In this paper we propose an incremental semantic spatial relationship building approach for robotic agents based on formal concept analysis and defeasible reasoning. We consider a number of cases in which an autonomous robot with incomplete information about the environment can perform reasoning and update its location navigation. We use contextual information for establishing strength of partial order relationship between discovered concepts of robotic navigation/computing environment.