Search Results

The popularity of new Human-Machine-Interfaces (HMIs) comes with growing concerns for driver distraction. In part, this concern stems from a rising challenge to design systems that can make functions accessible to drivers while maintaining drivers’ ability to cope with the complex driving task. Therefore, engineers need assessment methods which can evaluate how well a user interface achieves the dual-goal of making secondary tasks accessible, while allowing safe driving. Most prior methods have emphasized measuring off-road glances during HMI use. An alternative to this is to consider both on-road and off-road glances, as done in Kircher and Ahlstrom’s AttenD algorithm [1]. In this study, we compared two types of prevalent visual-manual user interfaces based on AttenD. The two HMIs of interest were a touchscreen-based interface (already in production) and a remote-rotary-controller-based interface (a high-fidelity prototype).

The goal of this project was to investigate how to make driver distraction state classification more efficient by applying selected machine learning techniques to existing datasets. The data set used in this project included both overt driver behavior measures (e.g., lane keeping and headway measures) and indices of internal cognitive processes (e.g., driver situation awareness responses) collected under four distraction conditions, including no-distraction, visual-manual distraction only, cognitive distraction only, and dual distraction conditions. The baseline classification method that we employed was a support vector machine (SVM) to first identify driver states of visual-manual distraction and then to identify any cognitive-related distraction among the visual-manual distraction cases and other non-visual manual distraction cases.