In recent years, with the spread of the household robots, the necessity to enhance the communication capabilities of those robot to people has been increasing. The objective of this study is to build a framework for a dialogue system dealing with multimodal information that a robot observes. We have applied partially observable Markov Decision Process to modeling multimodal interaction between a human and a robot. Through the experiments, we have confirmed that our proposed framework functions properly and achieves effective multimodal interaction with a robot.
展开▼