Airport inspection robot multi-scene autonomous navigation positioning method

Abstract

The invention discloses an airport wheeled inspection robot multi-scene autonomous navigation and positioning method. Visible light image information is collected through a camera, the pavement condition of a current scene is analyzed through target recognition, the open degree of the current scene is judged according to effective feature numbers extracted from images, the scene similarity is calculated through comparison of adjacent key frames, and the three points serve as the basis for selection of the navigation and positioning method of the inspection robot; when the open degree is high and the road surface is a standard road surface, a differential GPS and encoder combined visual autonomous navigation positioning method is adopted; when the open degree is high and the road surface isa gravel road surface, an autonomous navigation and positioning mode of combining a GPS with vision, an IMU and an encoder is adopted; and when the scene open degree is relatively low and the similarity is relatively low, a visual SLAM autonomous navigation positioning mode is adopted. The environment adaptability of the robot is improved, the defect of fusion of a large number of sensors is reduced, and the calculation pressure of a robot control system is reduced.

Description

technical field [0001] The invention belongs to the technical field of automatic inspection, and specifically relates to a multi-scene autonomous navigation and positioning method for an airport inspection robot. Background technique [0002] At present, the navigation and positioning of autonomous robots is mainly based on a specific environment. For example, the differential GPS method is mostly used in open areas, and the SLAM technology is mostly used in indoor or outdoor small-scale areas, which cannot meet multiple complex environments at the same time. Due to the large difference in the surrounding road conditions of most airports, some places have standard road conditions and are relatively open, some places have gravel roads with insufficient openness, and there are many buildings in the airport management area. The inspection robot cannot use a single technology to realize the autonomous inspection of the whole perimeter. Contents of the invention [0003] The p...

AI Technical Summary

Problems solved by technology

[0002] At present, the navigation and positioning of autonomous robots is mainly based on a specific environment. For example, the differential GPS method is mostly used in open areas, and the SLAM technology is mostly used in indoor or outdoor small-scale areas, which cannot meet multiple complex environments at the same time.

Due to the large difference in the surrounding road conditions of most airports, some places have standard road conditions and are relatively open, some places have gravel roads with insufficient openness, and there are many buildings in the airport management area. The inspection robot cannot use a single technology to realize the autonomous inspection of the entire perimeter

Images