Integrating Miscommunication Analysis in Natural Language Interface Design for a Service Robot

Natural language user interfaces for robots with cognitive capabilities should be designed to reduce the occurrence of miscommunication in order to be perceived as providing a smooth and intuitive interaction to its users. This paper describes how miscommunication analysis is integrated in the design process. Observations from 12 user sessions revealed that users misunderstand the robot´s functionality; and that feedback sometimes is ill-timed with respect to the situation. We provide a set of design implications to prevent errors from occurring, to influence or adapt to users´ behavior