Engineering and Technology, Electrical Engineering, Electronic Engineering, Information Engineering, Control Engineering, Teknik, Elektroteknik och elektronik, Reglerteknik

Despite the successes in the use of artificial intelligence systems for image analysis, in certain critical applications, the final decision-making should remain with the human operator. To facilitate the working conditions of an unmanned aerial vehicle (UAV) pilot during prolonged missions, an auxiliary narrow-angle video camera is installed on board the UAV. This camera can be positioned independently of the main (navigation) video camera. A structural model of the electro-mechanical drives for the two-coordinate positioning system in terms of yaw and pitch angles is proposed, serving as a starting point for further physical modeling. Specific requirements and limitations existing during the operation on board the UAV, which define the development course of the motion controller, are formulated. Different types of controllers for this system are considered from the perspective of their compliance with the specified requirements and limitations. Based on the comparison of motion controller models, recommendations for the subsequent implementation of the physical model of the two-coordinate electro-mechanical drive system are developed. A concept of a new type of quasi-optimal controller is formulated, which utilizes ideas and methods of artificial intelligence to ensure the necessary characteristics. For the further design of such a motion controller based on machine learning, transfer functions and a flexible model of a brushless DC motor are proposed.