This invention aims at providing a method for realizing the automatic inspection of a high-speed railway box girder inspection robot, so as to solve the problems existing in the prior art. The method uses collected environment data and absolute position information of the robot to generate an environmental map, and combines the absolute position information of the robot with the environmental map to generate an inspection path for the robot based on a path planning algorithm.
The robot is controlled to move based on the inspection path and capture real-time images of the inside of the high-speed railway box girder, and uses a HED edge detection model to process the images to detect defects in the box girder.
The inspection robot is equipped with an NB-IOT – sensor, a panoramic camera, a laser radar and a synchronous controller. The panoramic camera includes a stereoscopic image sensor, and the laser radar includes a laser scanner and a laser scanning sensor.
– The image information collected in real time is transmitted to a server through the NB-IOT sensor, and the server generates a 3D spatial model of the high-speed railway box girder based on the image information.
