Unmanned aerial vehicles are widely used in various industries, such as aerospace, geodesy, cartography, remote environmental monitoring, and for military purposes. However, currently there are a number of factors that have a negative impact on the successful performance of special tasks of unmanned aerial vehicles due to the fact that currently remote-controlled means based on the «natural intellect» of the operator prevail in unmanned aerial vehicles and the lack of transition to the most autonomous actions, such as route planning, bypassing flight blocking zones, forecasting navigation situation, as well as search, recognition and classification of remote monitoring objects. To effectively perform tasks, it is necessary to develop intelligent algorithms to automate the process of planning and executing mission tasks. The article discusses the basic principles of neural networks and their application in the tasks of route planning and flight control for remote monitoring of an unmanned aircraft.

Remote monitoring, reinforcement learning, neural network, unmanned aerial vehicle

Gromov Yuri Yurievich,  ,  orcid.org/0000-0003-3313-2731,  Tambov State Technical University

Ishchuk Igor Nikolaevich,  ,  orcid.org/0000-0002-8140-3746,  Tambov State Technical University

Telnykh Bogdan Konstantinovich,  ,  orcid.org/0009-0001-1870-3738,  Tambov State Technical University