Dangerous Driving Event Analysis System by a Cascaded Fuzzy Reasoning Petri Net

This paper applies a modified cascaded fuzzy reasoning Petri net (CFRPN) model to analyze dangerous driving events on a freeway. The dangerous driving events can be divided into two groups: (1) the interaction between a driver´s vehicle and the road environment, and (2) the interaction between a driver´s vehicle and nearby vehicles. These two classes of driving events may occur simultaneously and lead to certain serious traffic situations. The proposed system analyzes these two kinds of events and determines dangerous situations from data collected by various sensors. Since collecting real driving event data on freeway is dangerous and time consuming, a data generation system is developed to generate the experimental data. Such data can help evaluate the performance of the proposed analysis system. Finally, experimental results show that the proposed system is accurate and robust