A factory inspection UAV autonomous path cruising and intelligent obstacle avoidance method

Abstract

The invention discloses a rotor UAV based autonomous path cruise and intelligent obstacle avoidance method for factory safety touring. A camera shooting path mark line is used, and a sampling area isselected; Canny operation is carried out on a binary mark line, an edge of the mark line is obtained, and probability Hough transform is used to detect line segments in an image; the number of line segments is determined, if the number of line segments is 4, quarter band detection is entered, and otherwise, curve detection is entered; autonomous cruise is carried out according to different detection results; depth map data, obstacle distance data and supersonic wave data are used in the flight process to obtain obstacle data; and an incomplete artificial potential field method based on Follow-Wall behaviors is used to avoid obstacles autonomously. Different algorithms are used to process the images according practical shapes of the mark lines, and the path is tracked; and the incomplete artificial potential field method based on Follow-Wall behaviors can be used to avoid disadvantages of the artificial potential field, so that the UAV can move along the edge of the obstacle till a predetermined place when confronting with the obstacle.

Description

technical field [0001] The invention relates to the technical field of path cruising and intelligent obstacle avoidance, in particular to a method for autonomous path cruising and intelligent obstacle avoidance of a factory inspection drone. Background technique [0002] Safety inspection is the prerequisite to ensure the normal production of the factory. A qualified and reliable inspection system is a means to realize quantitative management of factory lines and equipment, and an important measure to realize enterprise information management. Traditional factory inspections have the following disadvantages: some inspection sites have harsh environments, which may cause physical and psychological impacts on personnel; manual input of manual inspection information has problems such as heavy workload, slow speed, error-prone, and inconvenient data management; Time inspections cause staff fatigue and reduce the quality of inspections. [0003] In order to solve the above probl...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned existing problems, the present invention provides an autonomous path cruising and intelligent obstacle avoidance method of a factory inspection drone. The drone cruises according to different path states, and adopts the incomplete artificial potential field method based on Follow-Wall behavior, which avoids the deficiency of the artificial potential field method, so that when the drone encounters an obstacle, it can move along the edge of the obstacle until it reaches the predetermined location In order to achieve this purpose, the present invention provides a factory inspection UAV autonomous path cruising and intelligent obstacle avoidance method, using machine vision technology and obstacle avoidance algorithm to carry out autonomous cruising and obstacle avoidance, including the following steps:

Images