When robot comes to our daily life, sharing knowledge is a key factor to realize the symbiosis between human and robot. In previous research, Robot Technology (RT) ontology was proposed as a knowledge base to help robot understands human’s intention in daily activities. However, the method to build that ontology was not discussed. This paper presents our approach to build RT ontology based on basic-level knowledge. We proposed a new structure for RT ontology with Where, What, and How layers based on 4W1H. As for input data, we used educational books and MIT’s ConceptNet. Our method is able to build RT ontology automatically by extracting objects and human activities from these data sources. We also implemented a weighting mechanism for the new ontology. Result shows that our method achieved better accuracy than conventional approach using Internet data.

This paper presents a novel approach for RT Ontology development, including ontology learning and evolution mechanism. In service robotics systems, understanding the relationship between everyday objects and user intention is the key feature to provide suitable services according to context. RT Ontology has shown to be an efficient technique to represent this relationship. In the proposed method, text corpus grabbed from search engines and lightweight natural language processing techniques were used for term extraction and enabling RT Ontology automatic creation. On the other hand, ontology evolution mechanism is introduced. With these learning and evolution capabilities, the presented RT Ontology model may adapt dynamically to the changes of environment and human activities. This will help to improve the robustness of current RT service generation systems, while reduce much of required labor work for ontology development. Experiments were conducted to show the effectiveness of proposed method.

No abstract