Parallel parking method based on three-order arctan function model

Abstract

The invention provides a parallel parking method based on a three-order arctan function model. The invention provides a method for planning an arctan type route with three-order disturbance. The method comprises the following steps: calculating a constraint space according to vehicle kinematics, calling for a ga function by a tool kit of a genetic algorithm in MATLAB, calling for an objective function taking barrier constraint, vehicle parameter constraint, parking initial point and end point position constraint in a parking process as a locus function and taking the minimal horizontal inclined angle between the vehicle at the parking end point and the parking space as a fitness function, thereby solving an optimal parameter of the locus function and confirming the optimal parallel parking track. According to the method provided by the invention, the ratio of parking space length to vehicle length is about 1.315 and the effect is excellent.

Description

technical field [0001] The invention relates to the field of simulation technology, in particular to a parallel parking method based on a third-order arctangent function model. Background technique [0002] Cars are the most commonly used means of transportation in daily life, and private cars have almost become the standard equipment for every family. While the transportation is convenient, it also brings more problems, especially the problem of difficult parking is becoming more and more serious. How to improve the handling of automobiles, especially the inconvenience during parking, eliminate potential safety hazards, and quickly, accurately, and safely park automobiles at appropriate locations has gradually attracted people's attention. The emergence of automatic parking technology has greatly relieved the tension of the driver when parking, reduced the difficulty of parking, improved the comfort of driving, and improved the safety of the parking process. One of the key...

AI Technical Summary

Problems solved by technology

Xu Jin, Xie Ming and others proposed to conduct offline table lookup according to the size of the parking space and the information of surrounding obstacles to obtain a collision-free and continuous sinusoidal trajectory. This method has low requirements for real-time performance; while Jiang Hui proposed automatic parallel parking The path proposed by the research on the vehicle steering control strategy needs to change gears and gears continuously, which is not in line with the actual situation of the driver's operation; while the dual-radius method needs to change the steering angle when the vehicle speed is zero, which will cause greater damage to the vehicle; no constraints The planning path with the fifth-order polynomial as the parallel parking space requires a larger parking space; the improved fifth-order polynomial path planning method with the constraint space needs to introduce a fitness function with a penalty function when calling the genetic algorithm. It is not easy to control the penalty amount in the parking environment, and there will be certain errors

Images