Sensor-based assessment of the in-situ quality of human computer interaction in the cars : final research report.

Human attention is a finite resource. When interrupted while performing a task, this resource is split between two interactive tasks. People have to decide whether the benefits from the interruptive interaction will be enough to offset the loss of attention from the ongoing task. The issue of dealing with self-interruptions and external interruptions is particularly critical in driving situations. In general, interruptions result in a time lag before users resume their primary task, increase mental workload, and thus decrease primary task performance. Therefore, being able to identify when a driver is interruptible is critical for building systems that can mediate these interruptions. In order to identify situations in which drivers enter either low or high cognitive load states during naturalistic driving (i.e., opportune moments for driver interruption – e.g., more interruptible states vs. less interruptible states), the authors have examined a broad range of sensor data streams to understand real-time driver/driving states (e.g., motion capture, peripheral interaction monitoring, psycho-physiological responses, etc.), and presented a model-based driver/driving assessment by using machine learning technology.