Behavior Decision Model With Situation Assessment for Intelligent Vehicles Based on Vehicle-to-Everything Information

Abstract

Under the application of cooperative vehicle infrastructure technology, vehicles can drive more safely and efficiently in urban traffic environments. This paper presents a behavior decision model composed of a situation assessment module and decision process module to make a decision on lane selection and velocity control. Different common traffic elements are considered, such as surrounding obstacles, traffic lights, lane lines, and road velocity limits, to ensure the model outputs safe and legal behaviors. A green-wave passage strategy is also proposed to allow vehicles to pass through traffic intersections at a smoother velocity and to improve driving efficiency. To verify the correctness and rationality of the model, a Prescan/Simulink co-simulation platform including multiple common urban driving scenarios is established. The results show that the model can output correct behaviors with safety and legitimacy in different scenarios and realize vehicles meeting at intersections, vehicle-following, queuing at intersections with traffic lights, lane-changing for obstacle avoidance, and so forth. Compared with the general decision model without the green-wave passage strategy, the driving time is reduced by an average of 8.53%, and the standard deviation of the driving velocity is reduced by an average of 65.42%, which means that the model can reduce the variation of velocity and improve driving efficiency. The model has a certain practical application value.