In this research, we develop user-oriented RT service proposal system in Kukanchi. Kukanchi is interactive Human-Space Design and Intelligence. By carrying out data mining of user information, service history, sensor data, and object data, this system finds out those relationships and gives weight to each of them. As a result of experiment, this system came to be able to propose “Tsuide Service” (Additional RT service) that each user expects.

Human commonsense is required to improve quality of robotic application. However, to acquire the necessary knowledge, robot needs to evaluate the appropriateness of the data it has collected. This paper presents an evaluation method, by combining the weighting mechanism in commonsense databases with a set of weighting factors. The method was verified on our Basic-level Knowledge Network. We conducted questionnaire to collect a commonsense data set and estimate weighting factors. Result showed that, the proposed method was able to build Robot Technology (RT) Ontology for a smart “Bring something” robotic service. More importantly, it allowed robot to learn new knowledge when necessary. An intuitive human-robot interface application was developed as an example base on our approach.

This paper proposes our approach to disambiguate human pointing gesture by using commonsense knowledge. Pointing gesture is a natural way to specify the object that a user needs in the “Bring something” service. However, error in gesture recognition makes robot difficult to select the correct candidate object when there are multiple objects located closely together. To solve this problem, Robot Technology (RT) Ontology was used to make assumption about human activity and necessary objects for the activity. By combining this commonsense reasoning with the spatial constrain from human's pointing direction, robot is able to find appropriate object. Experiment showed the successful rate of object selection was improved, and therefore robotic service becomes more intuitive.

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.