Driving Manoeuvre Recognition

Abstract

This paper describes a system for the automatic recognition of driving manoeuvres in the automobile based on a model of driving behaviour in manoeuvres. Today’s automobile is equipped with various sensors which provide data about the vehicle, the driver’s actions and the driving environment. The variety of driving styles in which manoeuvres are performed and the uncertainty present in the available sensor data provide major obstacles to automatic manoeuvre recognition. A Bayesian model of the driving task is used as a basis for the probabilistic inference of the manoeuvre being performed from the uncertain evidence available.