Curve target selection method, vehicle-mounted equipment and storage medium

Abstract

The embodiment of the invention relates to a curve target selection method, vehicle-mounted equipment and a storage medium, which are applied to an intelligent driving vehicle running in a curve. Themethod comprises the steps of obtaining first motion information and a target selection section of the intelligent driving vehicle, wherein the target selection section comprises an upper limit valueand a lower limit value; acquiring second motion information of a candidate target vehicle; determining a turning radius of the intelligent driving vehicle based on the first motion information; determining the distance between the candidate target vehicle and the starting point of the turning radius based on the second motion information and the turning radius; and determining a target vehicle based on the distance and the target selection section. According to the embodiment of the invention, the target vehicle is determined by determining the distance between the candidate target vehicle and the starting point the turning radius of the intelligent driving vehicle, the method is suitable for various types of sensors and sensor combinations, and the phenomenon that selection missing or wrong selection occurs when the candidate target vehicle is selected in a curve due to different performance expressions of different sensors is reduced.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of intelligent driving, and in particular to a method for selecting a curve target, a vehicle-mounted device, and a storage medium. Background technique [0002] At present, the sensors equipped with intelligent driving vehicles include visual sensors, ultrasonic sensors, millimeter-wave radars, and lidars. The intelligent driving system of the intelligent driving vehicle comprehensively collects and analyzes these sensor data, and correlates, matches and fuses them to obtain the information of multiple candidate target vehicles around the intelligent driving vehicle. However, limited by the longitudinal control algorithm of the intelligent driving system (such as the L2 level intelligent driving system), it is necessary to select a suitable front target vehicle from these candidate target vehicles for car-following. [0003] When the intelligent driving vehicle and the candidate targ...

AI Technical Summary

Problems solved by technology

[0004] Due to the different detection performance and performance of various types of sensors installed in intelligent driving vehicles, the information of candidate target vehicles obtained by detection is not necessarily accurate, and there is a certain deviation in the estimation of the trajectory of candidate target vehicles, which leads to the detection of candidate target vehicles in curves. It is easy to miss or make mistakes when choosing

Causes errors in the longitudinal control of the vehicle; may cause the intelligent driving vehicle to fail to effectively brake or decelerate incorrectly

Affect the driving safety of intelligent driving vehicles

[0005] Therefore, there is an urgent need to provide a curve target selection scheme to reduce the phenomenon of missing or wrong selection of candidate target vehicles in curves due to the different performances of different sensors.

Images