Research On Automatic Parking System Of Irregular Parking Space

With the development of modern automobile technology,intelligent automobile is commonly used in automobile industry.As a key technology of the driverless system,automatic parking system has become a research focus.However,the existing automatic parking system is still unsatisfactory,such as difficult to park in a complex environment,search for parking space for a long time and so on.In order to improve the existing problems of automatic parking system,the improvement of irregular parking space recognition and path planning algorithm were studied,the intelligent degree of existing automatic parking system is improved.Firstly,based on the detection of complex environmental parameters by ultrasonic sensors,a space model of irregular parking space composed of obstacle vehicles was established,which can describe parking space more completely and output precise parking space type by fuzzy control.So as to realize the recognition of irregular parking space.Secondly,aiming at the identified parking space type,the improved RRT algorithm was designed and the path planning was studied.The sampling map was constructed by defining the situation,so that the sampling efficiency can be improved within the safe range of the starting point and the ending point of the path.The pre-processing method of sampling points was used to search the initial environment of the next cycle,according to the environment of the previous cycle,so as to improve the search efficiency of the path under different dynamic conditions.The cubic B-spline curve was used to optimize and smooth the successful path.The simulation experiment was carried out to verify the performance of the improved RRT algorithm,whether it can be applied to the environment of the irregular automatic parking system.Finally,in the MATLAB/Simulink simulation environment,the simulation analysis of the irregular parking system was carried out.Aiming at different types of irregular parking spaces,the influence factors of the two path algorithms in simulation times,success times,shortest path length,search time,number of sampling nodes was analyzed and compared.Then based on cubic B-spline curve,the generated path was optimized by using the path smoothing method.Through the experimental data,the improved RRT algorithm can significantly improve the speed of searching path,the convergence is faster and the path is better.