Object recognitions are challenging tasks, especially partially or fully occluded object recognition in changing and unpredictable robot environments. We propose a novel approach to construct semantic contexts using ontology inference for mobile robots to recognize objects in real-world situations. By semantic contexts we mean characteristic information abstracted from robot sensors. In addition, ontology has been used for better recognizing objects using knowledge represented in the ontology where OWL (Web Ontology Language) has been used for representing object ontologies and contexts. We employ a four-layered robot-centered ontology schema to represent perception, model, context, and activity for intelligent robots. And, axiomatic rules have been used for generating semantic contexts using OWL ontologies. Experiments are successfully performed for recognizing partially occluded objects based on our ontology-based semantic context model without contradictions in real applications.
展开▼
