Three-dimensional positioning algorithm for converter station patrol inspection based on multi-sensor filtering

Abstract

In order to improve the three-dimensional positioning accuracy of sensor to converter station inspection robots in unknown environments, a three-dimensional positioning algorithm for converter station inspection based on multi-sensor filtering was studied. Construct a motion information sensing model for the inspection robot in the converter station based on correcting multiple sensors, and use laser radar sensors and IMU sensors to respectively sense the threedimensional coordinate information, angular velocity, and acceleration information of the inspection robot in the converter station; Use the multi sensor correction method based on neural networks to correct the drift error of perceptual information; Through the inspection 3D positioning algorithm based on Kalman filter, the corrected perceptual positioning information is fused and filtered, and the 3D coordinates of the inspection robot in the converter station are estimated to complete the auxiliary work of the inspection 3D positioning in the converter station. In the experiment, the algorithm can locate the dynamic three-dimensional coordinates of the inspection robot in the converter station, and the mean square error of the positioning results is less than 0.05.