The assistance on demand concept offers a highly personalized and context-based approach by delivering assistance only when the driver actively asks for it. Using a speech interface enables the driver to keep her visual attention on the driving task while she and the system cooperatively solve the task.
In a simulator study with 24 participants, we evaluated the concept for an intersection monitoring assistant that can be requested when approaching a complex junction (Schömig, Maag, & Neukum, 2016). The driver may ask the assistant system to “check right”. The system will then detect traffic participants coming from the right and inform the driver. The driver can concentrate on the other directions and take the information from the system into account before entering the intersection. The assistance on demand concept was clearly preferred by the participants when they also had the choice of driving with a more conventional HUD system or without any assistance.
Personalization is the user-specific adaptation of a system towards individual capability, experience and preference. It can be based on assigning the user to one of a number of pre-specified categories or clusters. More flexible models of personalization may require larger sets of individual user data to allow a robust estimation of the users properties and preferences. Once user- specific characteristics have been measured, system components can be optimized like in the example of a car cockpit personalized to an individual laser scan.
Human-machine interaction (HMI) with intelligent assistant systems poses great challenges for the mutual understanding of goals, capabilities and mental models of interaction partners. Personalizing the interface can make the interaction more intuitive, i.e. better respecting the experiences and preferences of a user. Incremental learning approaches can be used for such a user-centric system adaptation. A key challenge is to create a user interface that allows a proper understanding of mutual learning progress and learned concepts.
For more information
N. Schömig, M. Heckmann, H. Wersing, C. Maag, A. Neukum, „Assistance-on-demand: A speech-based assistance system for urban intersections“,
Proc. 8th Int. Conf. Automotive User Interfaces and Interactive Vehicular Applications Adjunct., ACM, 2016.