Laser map updating method based on grid detection, terminal and computer equipment

Abstract

The invention belongs to the technical field of unmanned vehicle positioning and maps, and particularly relates to a laser map updating method based on grid detection, a terminal and computer equipment. The updating method comprises the steps of collecting data of a local map area and an original map area, and performing area association; extracting a key frame of the local map, carrying out poseestimation, and aligning the key frame with the original map according to a matching algorithm; updating the grid position where the point cloud is transformed by adopting a grid detection mode; according to the invention, key frames of an original map part and a local map part are combined, so that an updated map is obtained; by comparing the grid conditions of the same position in different environments, processing the original map area and the local map area based on the grid comparison result, and combining the original map area and the local map area after processing is completed, laser map updating is completed, the situation that the environment of the unmanned vehicle working site is changed is effectively processed, and safe and stable operation of the vehicle is guaranteed.

Description

technical field [0001] The invention belongs to the technical field of unmanned vehicle positioning and maps, and is suitable for updating local maps of laser maps, in particular to a method for updating laser maps based on grid detection, a terminal and computer equipment. Background technique [0002] In recent years, artificial intelligence technology has developed rapidly. With the continuous improvement of academic theories, various fields continue to explore its actual application scenarios. Unmanned vehicles deeply combine theory and practice, which can effectively liberate the labor force, improve production efficiency, enhance driving safety, and improve the quality of life. Therefore, autonomous driving technology has attracted more and more attention. The realization of autonomous driving of unmanned vehicles mainly relies on positioning, perception, decision-making and control technologies, among which positioning technology is the basis for realizing unmanned dr...

AI Technical Summary

Problems solved by technology

This solution has high requirements for vehicle perception ability, and it needs to be able to complete the accurate classification and cutting of temporary object models, and the update error cannot be guaranteed

In addition, if the permanent part is not updated, there is a greater risk. The removal of fixed screens, fixed containers, or installation of construction guardrails are common maintenance tasks in the park

[0009] The above two update methods are not conducive to parks or campuses and other environments with lush vegetation and more building road maintenance; and both methods require high perception capabilities, and perception errors cannot be eliminated, resulting in map update errors that cannot be guaranteed

Images