Surrogate safety measures as aid to driver assistance system design of the cognitive vehicle

Abstract

The driver assistance system part of the cognitive vehicle design can prevent rear, lateral and other collisions by using a collision warning system that integrates intelligent technology and human factors. To be effective, such a system should be able to analyse driving states including driver distraction and driver intent, assess the likelihood of collisions by working with surrogate safety measures and issue warnings to the driver. This study presents a longitudinal and lateral collision warning model that allows the inclusion of key surrogate safety measures such as distance between vehicles in longitudinal vehicle-following mode or envelopes of vehicles in the lateral direction during lane migration/change/merge movements. The model can take into account values of driver distraction and driver intent variables obtained on-line or from off-line devices. The formulation is also applicable to time-to-crash surrogate safety measure. A pattern recognition method is used for the identification of pre-crash condition while minimising false alarms. The surrogate safety model is presented and illustrative examples are provided. The surrogate safety measure-based warning system is mainly intended for on-line use in actual driving conditions. In addition, it can be used in driving simulators or for off-line safety studies in association with microsimulators of traffic.