A New Algorithm for Lane Level Irregular Driving Identification

Abstract

Global Navigation Satellite Systems (GNSS) are used widely in the provision of Intelligent Transportation System (ITS) services. Today, there is an increasing demand on GNSS to support applications at lane level. These applications required at lane level include lane control, collision avoidance and intelligent speed assistance. In lane control, detecting irregular driving behaviour within the lane is a basic requirement for safety related lane level applications. There are two major issues involved in lane level irregular driving identification: access to high accuracy positioning and vehicle dynamic parameters, and extraction of erratic driving behaviour from this and other related information. This paper proposes an integrated algorithm for lane level irregular driving identification. Access to high accuracy positioning is enabled by GNSS and its integration with an Inertial Navigation System (INS) using filtering with precise vehicle motion models and lane information. The identification of irregular driving behaviour is achieved by algorithms developed for different types of events based on the application of a Fuzzy Inference System (FIS). The results show that decimetre level accuracy can be achieved and that different types of lane level irregular driving behaviour can be identified.