This report summarizes research to date concerned with identification of drowsy drivers from information contained in steering wheel and lane position data. Data analysed in this report was obtained from a Rockwell-Collins van driven on interstate and state highways in Iowa. Key results in this paper include the following: The type of steering wheel sensor can influence some of the more popular statistics promoted for drowsy driver identification. Weather conditions have a strong influence on the same statistics. Stochastic characterizations of steering wheel and lane position processes appear to have strong similarities. (Author/publisher)
Abstract