Situated Delegation-Oriented Multimodal Presentation in SmartKom

One of the major scientific goals of SmartKom is to design a new human-machine interaction metaphor for a multimodal dialog system that combines speech, gesture, and mimics input with speech, gesture and graphics output. The system behavior is based on the new situated delegation-oriented dialog paradigm (SDDP) in the sense that a communication assistant, realized as an animated life-like character, serves as the communication partner of the user. In this paper we focus on the multimodal output of SmartKom, showing how these highly ambitious tasks of the SmartKom system are managed and realized on the output side, i.e., how the communication assistant adapts its behavior to the available output media and modalities with respect to the current dialog situation.