Path planning method for automatic parallel parking based on two second-order Bezier curves

Abstract

The invention discloses an automatic parallel parking path planning method based on two second-order Bezier curves. The method determines the parking target position by obtaining the target parking space information, and establishes a global coordinate system with it as the origin to construct a parking space. The trajectory segmentation judgment model is used to determine the number of planned trajectory segments, plan the end position range of the first segment of the trajectory, determine the start and end points of each segment of the planned trajectory and the position of the control point, use the second-order Bezier curve for path planning, and monitor at regular intervals And use the method of dynamically adjusting the planned trajectory to adjust the planned trajectory. The present invention reduces the requirements for the initial pose of the vehicle to be parked, and improves the environmental adaptability of the path planning method; the vehicle can be artificially driven into the planned area through simple adjustments to reduce costs, and can be applied to middle and low-end vehicles; The control points of the vehicle trajectory planning are easy to determine, the trajectory generation algorithm is simple, and the path curvature is continuous; the difficulty of correcting the trajectory error is reduced, and the vehicle obstacle avoidance and parking efficiency are improved.

Description

technical field [0001] The invention relates to the technical field of automatic parking path planning, in particular to an automatic parallel parking path planning method based on two second-order Bezier curves. Background technique [0002] The automatic parking system reduces the driver's fatigue intensity and the risk of vehicle damage to a certain extent, saving the driver's time. The automatic parking trajectory planning problem is an important part of the automatic parking system. Its main task is to provide a series of speeds and steering wheel angles from the initial pose to the target pose for the intelligent driving vehicle in the parking scene. The trajectory planning The quality of the car directly determines the quality of the parking system. [0003] At present, a variety of methods have been studied for parking trajectory planning at home and abroad, including curve fitting methods such as helix and polar spline, and trajectory planning through simple geomet...

AI Technical Summary

Problems solved by technology

Among them, the parking trajectory planned by the third-order Bezier curve has problems such as difficult to find control points, complex trajectory generation algorithm, and inability to achieve effective obstacle avoidance for moving obstacles, and when there is an error between the actual trajectory and the planned trajectory. It is difficult to dynamically adjust the trajectory; the method of trajectory planning using geometric mapping methods has a small scope of application, is not flexible, and has problems such as sudden curvature changes

Therefore, accuracy, flexibility, simplicity and efficiency cannot be satisfied in parking trajectory planning at the same time.

Images