Queueing Network Based Driver Model for Varying Levels of Information Processing

Abstract

With growing interest in the topic of smart computing and context-aware services, identifying driver's intention has become important in automotive industry. Among existing studies on driver assistance systems, few studies have used the concept of the levels of processing (LOP) to understand driver's information processing. This paper introduces experimental and computational studies that connect human behavior data to internal goal of a driver when an in-vehicle task involves visual search. In the case of consuming information displayed on a car instrument cluster, we considered two levels of information processing, perceptual and cognitive. Through an empirical study, we observed different human oculomotor behaviors that depend on the LOP by evaluating the reaction time (RT) and eye movement patterns. Further, we suggested different ways of information processing that can be represented as different routes in the underlying cognitive architecture of a queueing network. Simulation study demonstrated that trends in simulated oculomotor behavior were similar to those observed in the experiment, that is, RT at the cognitive LOP was shorter than that at the perceptual LOP, while eyes fixated for shorter duration and with lower frequency. In terms of application, this study reveals the possibility of using human-generated data for evaluating the innate purposes of drivers. Together with further development of sensors and invasive computing, the approach proposed in this paper could assist the realization of cognitive cars by understanding drivers’ intent using eye tracking technology.