3D point cloud map fusion method and system for transformer substation inspection robot

Abstract

The invention discloses a 3D point cloud map fusion method and system for a transformer substation inspection robot, and the method comprises the following steps: carrying out the local region division of a to-be-inspected scene before the scanning of the inspection robot, and carrying out the scanning path planning of each local region; controlling the inspection robot to scan images of multiplelocal areas, each local area having a closed loop and detecting a loop, and the fused adjacent areas having a common part; sequentially importing a 3D point cloud map to be registered and a reference3D point cloud map, and manually selecting the same areas in the two maps; and carrying out coarse-to-fine matching on the same areas in the two selected maps through a preset fusion algorithm, and obtaining a fused map. According to the 3D point cloud map fusion method of the transformer substation inspection robot, the risk of global optimization failure can be avoided, multi-local 3D point cloud map high-precision fusion of a transformer substation scene of 100,000 levels or above is achieved, and the requirements for positioning and navigation of the inspection robot are met.

Description

technical field [0001] The invention relates to the technical field of intelligent robots, in particular to a 3D point cloud map fusion method and system for a substation inspection robot. Background technique [0002] SLAM is one of the core functions of wheeled intelligent inspection robots, and 3D laser SLAM has been a research hotspot in this field in recent years. It is also a trend in recent years to replace 2D laser SLAM. Substation intelligent inspection robots are one of its application carriers. 500KV and above substations have typical characteristics such as large scale, complex inspection routes, open space and large observation noise. The larger the environment, the longer the time required for data collection and map construction, and the greater the cumulative error; the more complex the inspection route, the higher the accuracy requirements for closed-loop detection; the sparse features, large observation noise, and the greater the matching error . The abov...

AI Technical Summary

Problems solved by technology

[0007] [4] CN110930495A, ICP point cloud map fusion method, system, device and storage medium based on multi-UAV cooperation. This method mainly uses SAC-IA to estimate the corresponding point pairs, and screens the point pairs, and then uses ICP for matching. When the transformation of the two maps is large, it is easy to fail the fusion

Images