Multi-sensor data fusion obstacle detection method for power line inspection unmanned aerial vehicle

Abstract

The invention discloses a multi-sensor data fusion obstacle detection method for a power line inspection unmanned aerial vehicle, which comprises a multi-sensor combined detection device connected with a flight controller in an unmanned aerial vehicle system, wherein the multi-sensor combined detection device comprises millimeter wave radar, a binocular vision sensor, an electromagnetic field sensor, an infrared sensor, a differential GPS and a data fusion processor, the millimeter wave radar, the binocular vision sensor, the electromagnetic field sensor, the infrared sensor and the differential GPS are connected with the data fusion processor, and fusion processing is performed on data collected by the sensors through the data fusion processor so as to obtain the accurate obstacle position, orientation and type and perform effective obstacle avoidance, thereby being capable of preventing an unmanned aerial vehicle from colliding with transmission lines and towers in operation and detecting obstacles such as hills, trees and buildings in the environment around the transmission lines so as to avoid property losses or casualties.

Description

technical field [0001] The invention relates to a multi-sensor data fusion obstacle detection method of an electric power line inspection UAV, which belongs to the technical field of UAV obstacle detection. Background technique [0002] With the development of technology, the application fields of drones are becoming more and more extensive, and there are more and more applications in power inspection. Due to the harsh environment of the power line inspection site, mountains, trees, buildings, etc. surround the transmission line, and the high-voltage and extra-high voltage power transmitted by the transmission line itself will also interfere with the normal operation of the drone. The special and complex environment of power line inspection puts forward higher requirements for UAV power line inspection, and the online high-precision detection of obstacles by UAV has become an urgent requirement. However, at present, domestic UAVs mostly use a single sensor to detect a singl...

AI Technical Summary

Problems solved by technology

[0003] 1) The complex environment of the power line inspection site is not comprehensively considered, and the obstacle detection method is too simple;

[0004] 2) The obstacle detection sensor used is relatively single or the combination of multiple sensors is unreasonable, and it is impossible to reliably detect obstacles in the power line inspection with high precision;

[0005] 3) The data fusion strategy adopted does not have a learning function, and the speed and reliability of obstacle identification are not high;

[0006] 4) The accuracy of the GPS used is not high, resulting in too large absolute position detection error of the UAV, which directly affects the reliability of the online learning algorithm;

[0007] 5) Unable to locate the obstacle type, which increases the difficulty of the obstacle avoidance algorithm

Images