Lane connecting line generation method, device, electronic device and storage medium

Abstract

The present application provides a lane connecting line generation method, device, electronic equipment and storage medium. Based on the method, the preset starting point parameters and preset ending point parameters of the lane connecting line to be generated are obtained first, and the connection type is determined, and then from the connection type Determine the target segmented line combination in the corresponding segmented line combination, set the length value range of each segmented line in the target segmented line combination and the curvature value range of the adjacent segmented line connection point, and then set the value of the respective length The range and curvature value range are selected in turn to generate multiple parameter combinations, and then multiple lane connection line trajectories are obtained based on multiple parameter combinations and preset starting point parameters, and are determined and preset from the trajectory end points of multiple lane connection line trajectories. The error value of the end point satisfies the target trajectory end point of the preset condition, and finally the target lane connection line is generated according to the target lane connection line trajectory corresponding to the target trajectory end point. In this application, the connecting line of the target lane is smoothly connected with other connecting lines of the lane.

Description

technical field [0001] The present application relates to the field of unmanned driving technology, and in particular to a method, device, electronic equipment and storage medium for generating lane connecting lines. Background technique [0002] High-precision maps are used to provide lane data and driving path planning for unmanned vehicles. Lane data, as the core data of high-precision maps, usually contain multiple lane connecting lines. The existing technology mainly uses A simple algorithm generates multiple lane connecting lines, such as Bezier curves, etc. However, each lane connecting line generated by this method can only ensure that its own curvature is continuous, and cannot guarantee that the connection point with the leading lane connecting line or the following lane connecting line The curvature is continuous, so that the lane connection lines of the entire map are prone to sudden curvature points, which are not smooth enough to facilitate the automatic drivin...

AI Technical Summary

Problems solved by technology

[0002] High-precision maps are used to provide lane data and driving path planning for unmanned vehicles. Lane data, as the core data of high-precision maps, usually contain multiple lane connecting lines. The existing technology mainly uses A simple algorithm generates multiple lane connecting lines, such as Bezier curves, etc. However, each lane connecting line generated by this method can only ensure that its own curvature is continuous, and cannot guarantee that the connection point with the leading lane connecting line or the following lane connecting line The curvature is continuous, so that the lane connection lines of the entire map are prone to sudden curvature points, which are not smooth enough to facilitate the automatic driving of unmanned vehicles

[0003] Therefore, the existing high-precision map has the technical problem that the overall lane connection line is not smooth enough, and needs to be improved

Images