Grid map marking method based on depth vision and single-line laser radar

Abstract

The embodiment of the invention provides a grid map marking method, system and device based on depth vision and a single-line laser radar and a computer readable storage medium. The method comprises the steps that laser radar data and depth vision data are acquired; in the laser processing layer, obstacle information is updated, meanwhile, obstacles are deleted according to the laser radar data, and the positions of all the deleted obstacles in the grid map are marked; in the depth visual data processing layer, obstacle information is updated, and meanwhile obstacles marked in the raster map in the depth visual field are removed according to the depth visual data; and the laser processing layer and the visual data processing layer are fused to form an obstacle layer with height information. In this way, the influence of three-dimensional obstacles can be more perfectly considered during path planning.

Description

technical field [0001] Embodiments of the present disclosure generally relate to the field of data processing, and more specifically, relate to a grid map marking method, system, device and computer-readable storage medium based on depth vision and single-line lidar. Background technique [0002] Most of the existing robot navigation and obstacle avoidance strategies on the market are based on laser radar information to mark obstacles on the grid map, and refer to the information on the grid map during navigation planning to achieve obstacle avoidance and obstacle avoidance. There are also some methods that add depth vision information to achieve three-dimensional obstacle avoidance. The method is to project the three-dimensional point cloud information of depth vision to a plane and convert it into the same two-dimensional information as lidar, ignoring its height information. [0003] Although the above method can achieve obstacle avoidance, the effect is not very good, an...

AI Technical Summary

Problems solved by technology

[0003] Although the above method can achieve obstacle avoidance, the effect is not very good, and a lot of navigation passability is sacrificed. The main problems are as follows:

[0004] like image 3 As shown, if the actual height of an obstacle is higher than the robot, but it is captured by the depth vision and directly marked on the grid map, the robot can pass through at this time, but due to the lack of another dimension (height) information, Therefore, the robot can only bypass or stop, and even some narrow places are directly impassable

[0005] At the same time, the current method of marking obstacles on the grid map does not have a perfect memory function (the memory function refers to the obstacle information outside the sensor's perspective should be retained), so in many cases the obstacle information that should not be cleared is also cleared, which will lead to unreasonable planned routes or even collisions

Images