Automatic parking decision planning method and system

Abstract

The invention provides an automatic parking decision planning method and system. The method comprises the following steps: collecting the initial position of a vehicle, the position information of a parking space and the information of an obstacle between the parking space and the vehicle; and controlling the vehicle to move to a parking area based on the initial position of the vehicle, the parking space position information and the obstacle information. The attitude of the vehicle and the distance difference between the tail part of the vehicle and the left and right parking space lines are calculated in real time through an all-round camera of the vehicle, and the vehicle is controlled to be parked in the parking space. When automatic parking decision planning is carried out, the distance between the vehicle and the left and right parking space lines of the parking space is detected in real time through a camera or an ultrasonic radar installed on the vehicle, the distance data serve as input of decision planning, and track information of the next point of the vehicle is planned in real time, so that the precision error of a traditional APA decision algorithm is eliminated; the precision of automatic parking decision planning is improved.

Description

technical field [0001] The present invention relates to the field of automatic parking (APA, Auto Parking Assist, hereinafter referred to as APA), in particular to an automatic parking decision planning method. Background technique [0002] APA (Auto Parking Assist, automatic parking), as a low-speed automatic driving scenario, is an automatic driving product that can actually be implemented and is attractive in the current market. As a type of autonomous driving scenario, APA also includes four algorithms or modules based on perception, decision-making, execution and positioning. The APA perception algorithm is currently mainly based on vision (surround view camera) and ultrasonic radar. APA decision-making is mainly based on trajectory calculation algorithms, mostly one-time path calculation, or trajectory correction in the later stage of parking. APA control is mainly divided into lateral control and longitudinal control, in which lateral control mainly refers to steeri...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides an automatic parking decision-making planning method and system, which is used to solve the problem that the traditional APA decision-making algorithm has a large error in the accuracy of the parking trajectory generated by the decision-making plan when the coordinates are poor due to GNSS signal failure and other reasons.

Images