An extensible dialogue script for robot based on unification of state transition models

In this paper, we propose an extension-by-unification method to improve reusability and flexibility in the incremental development of state-transition models. The dialogue engine SEAT (Speech Event-Action Translator) has been developed to realize continuous development of statetransition models in order to give robots dialogue capability that can cope with various kinds of speech inputs in various tasks. SEAT has a flexible adaptor mechanism that can connect to many types of robotic interfaces, and the developer can accumulate the scripts by using the script management server, which has a function to propose existing reusable scripts to the developer. We have confirmed that the application of SEAT to the development of three robots has significantly improved development efficiency.