Research On Active Collision Avoidance Algorithm For Intelligent Vehicle Based On Improved Artificial Potential Field

With the development of vehicles industry,the vehicle ownership has increased year by year.Vehicle collision accident has become a problem.To improve vehicle safety,vehicle active collision avoidance system has an important area of research.Intelligent vehicles have put forward new requirements for active collision avoidance algorithm.This paper presents an active collision avoidance algorithm for intelligent vehicles based on improved artificial potential field method to provide a safe comfortable and efficient solution for active collision avoidance of intelligent vehicles.Firstly,the existing active collision avoidance systems are analyzed from three aspects: environment perception,decision making and control execution.Advantages and disadvantages of the existing research are analyzed and the scheme flow chart of intelligent vehicle active collision avoidance algorithm based on improved artificial potential field method is presented.Then,after analyzing vehicle sensor feature,the position of front traffic participants are revised by perturbation and steering factors to ensure the correct identification and judgment of collision risk.And then,a longitudinal safety distance model and a transverse safety distance model are designed.The hierarchical safety distance model is established to reflect the collision risk between vehicles and environmental traffic participants based on road and vehicle characteristics.Also,the transverse safety distance model is designed based on lane change time with constraints of centroid side angle,providing an efficient collision risk judgment during lane changing.And then,an intelligent vehicle active collision avoidance algorithm based on the improved artificial potential field method is established based on the analysis of vehicle driving environment,which represent the vehicle driving environment by global planning virtual gravity,intelligent vehicle lane-changing gravity,forward traffic participant repulsion,lateral traffic participant repulsion,traffic signal lamp repulsion and sensor occluded scenes repulsion.Carsim/Simulink simulation is used to verify the effectiveness and real-time performance of the algorithm.Finally,some experiments are conducted to further verify the superiority of the algorithm.Hardware and software of the active collision avoidance system controller are design.Also,the actuator hardware is designed.Results show that the algorithm designed has better comfort and safety.