Search Results

Objective tools that can assess the demands associated with in-vehicle human machine interfaces (HMIs) could assist automotive engineers designing safer interaction. This paper presents empirical evidence supporting one objective assessment approach, which compares the demand associated with in-vehicle tasks to the demand associated with “benchmarking” or “comparison tasks”. In the presented study, there were two types of benchmarking tasks-a modified surrogate reference task (SuRT) and a delayed digit recall task (n-back task) - representing different levels of visual demand and cognitive demand respectively. Twenty-four participants performed these two types of benchmarking tasks as well as two radio tasks while driving a vehicle on a closed-loop test track. Response measures included physiological (heart rate), glance metrics, driving performance (steering entropy) and subjective workload ratings.

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.