Towards a Cognitive Load Ready Multimodal Dialogue System for In-Vehicle Human-Machine Interaction
Adjunct Proceedings of the 5th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, Eindhoven, page 49-52. (October 2013)Abstract
This position paper approaches one of the critical topics in the development of multimodal HMI for the automotive domain: keeping the driver's distraction low. However, the estimation of the cognitive load (CL), of which distraction is one symptom, is di�cult and inaccurate. Instead our research indicates that an approach to predict the e�ect of dialogue and presentation strategies on this is more promising. In this paper we discuss CL in theory and related work, and identify dialogue system components that play a role for monitoring and reducing driver distraction. Subsequently we introduce a dialogue system framework architecture that supports CL prediction and situation-dependent decision making & manipulation of the HMI.