Rear-End Collision detection based on GNSS/compass fusion and adaptive neuro fuzzy inference system

Abstract

Rear-End Collision has been considered as one of the most frequent accidents on roadways. In recent years, Global Satellite Navigation System (GNSS) with the merit of flexible and low cost, has exhibited the great potential for the rear-end Collision Avoidance Systems (CAS) for vehicles. Nevertheless, two main issues associated with the current rear-end CAS are: 1) accessing to high accuracy vehicle relative positioning and dynamic parameters; and 2) the reliable method to extract the car-following status from such information. This paper has developed a novel GNSS/compass fusion with the Adaptive Neuro Fuzzy Inference System (ANFIS) based algorithm for the real-time car-following status identification. The initial field test results have demonstrated the effectiveness of the proposed algorithms with the false alarm of 7.25% in the 10Hz output rate.