Communicating spatial knowledge in Japanese for interaction with autonomous robots

In this work, our goal is to communicate spatial knowledge in Japanese with autonomous robots. We first describe the data collection scheme. We then conduct a study to investigate how Japanese describe spatial relations and what relations they prefer. Based on the observations, we formalize the knowledge by ontologies. With the help of an inference mechanism, our knowledge base is able to store commonsense and discover inexplicit knowledge. We model 16 spatial relations using geometry information. At the language level, we present a natural language interface to execute commands and answer questions. The integrated robotic system unifies visual and spatial information in concert with parsing of semantic interpretation of sentences. Finally, we describe two tasks for validation.