This paper discusses how to develop Human Robot Interaction (HRI) based on Wikipedia Ontology and Robot Action Ontology. For the purpose, we implement a system which enables robots to communicate with users in various topics with voice and perform related actions to the topic using a full programmable humanoid robot named Nao. In this study, Wikipedia Ontology, which is developed by extracting the general concepts and relationships among them from Japanese Wikipedia, is utilized as a dictionary for natural language understanding. Robot Action Ontology is also developed for robot action control. We implement the system by relating these two ontologies. From the view point of development, however, there is a wide difference between these ontologies. Therefore, we propose the efficient method for relating these ontologies manually using rdfs:label. Case studies show us how HRI goes well with two topics: healthcare and movie directors.