Summary: This study focuses on the examination and comparison of selected behavioural and environmental indicators that predict the intention to change lanes. These indicators were chosen from previous driving studies and driver models. The data were gathered in a field study with an instrumented car that can log data from the driver, the car, and the environment. The collected data were analysed and modelled with the help of a "knowledge discovery framework" (Georgeon, Mille, & Bellet, 2006). The first analysis of all lane changes caused by a slow leading vehicle focuses on the following indicators: glance to the left outside mirror, turn signal, and lane crossing. It is shown that the glance to the left outside mirror could serve as a predictor with a high potential to get information about the intention to change lanes in a very early stage. However, it is important to combine this predictor with additional predictors to avoid a high false alarm rate.

Summary:Approximately one quarter of all accidents outside city limits occur while driving around curves, where assistance systems could prevent the driver from negotiating curves with excessive speed. This study argues that the parameterizing of a Driving Assistant System could be realized with data from realistic, noncritical driving behavior offered by Naturalistic Driving Studies. The Driver Performance Database presented in this study provides a tool for observing normal, noncritical driving behavior. The Database contains results from road tests with an instrumented vehicle that were carried out on public road traffic on a predetermined route, which was precisely measured in advance. In addition to vehicle state parameters, we also collected data concerning the driving environment and physiological information. With the Driver Performance Database it is possible to generate different facets of human driving behavior in a descriptive and normative way, which is illustrated by driver behavior in curve negotiation.

No abstract

No abstract

No abstract