ABOUT ONE APPROACH TO THE ISSUE OF REGULATING THE BEHAVIOR OF A QUADCOPTER UNDER OVERLAND MONITORING

Abstract

For information support of the development of infrastructure and agriculture in fields characterized by mountainous and forested areas, in some cases ground monitoring using unmanned technologies is required. In this regard, an algorithm for the formation of a 3D quadcopter trajectory under overland piloting in a mountainous and wooded landscape is proposed, which implies autonomous maneuvering to overcome possible obstacles. As a basic model, a fuzzy inference system is used with input characteristics in the form of linguistic variables that reflect fuzzy sectors of space, within which the presence of obstacles and the distance to them are interpreted verbally, that is, in the form of terms. It is proposed to overcome obstacles based on fuzzy conclusions of this system, formulated as terms of output linguistic variables, which reflect changes in the angle of rotation in the horizontal plane, flight altitude and speed of the quadcopter. The article analyzes the results of the behavior of a quadcopter under various flight scenarios, which became the basis for the operational formation of the trajectory through neural network modeling.