Development and research of an automatic terrain surveillance system using UAVs
Students Name: Fedunyshyn Roman Vasylovych
Qualification Level: magister
Speciality: Computerized Control Systems and Automatics
Institute: Institute of Computer Technologies, Automation and Metrology
Mode of Study: full
Academic Year: 2022-2023 н.р.
Language of Defence: ukrainian
Abstract: Thanks to the revolution in the field of lithium-ion batteries and the cheapening of microelectronics, many businesses and organizations have the prospect of using unmanned aerial vehicles to improve the productivity and efficiency of business activities. Unmanned aerial vehicles (UAVs) are one of the most popular information collection systems today, which can collect various information about the environment, such as photos, videos, using cameras sensitive to different wavelengths, information about pressure, humidity, and the concentration of certain gases. UAV systems can be used for both civilian and military purposes. The object of the study is algorithms for planning the route of UAVs for collecting photo and video data, as well as algorithms for automatic control of UAVs. The subject of the study is a system of automatic photo and video surveillance of the area using UAVs. The purpose of the study is the analysis of UAVs and base stations available on the market, the analysis of the management principles of fixed-wing UAVs and quadcopters, the development of a new low-cost automatic terrain surveillance system capable of independent photo and video recording. In this master’s thesis, the main types of UAVs present on the public consumer market are researched, analyzed and structured. The theory of control of fixed-wing drones and quadcopters was studied. Also important are the types of base stations that provide control over the UAV, exchange messages between the UAV and the operator, and collect telemetry data. A general architectural system of automatic terrain surveillance using unmanned 7 aerial vehicles was developed. Based on the analysis of the received data, the software of the base station was developed for the planning and execution of automated missions for monitoring the terrain. The single-board computer Raspberry Pi 3 B+ was used as the basis for the development of the base station. To demonstrate the operation of the software in practice, the Tello quadcopter from Ryze Technology was used. The communication interface with the Tello quadcopter (Tello SDK) was investigated. Thanks to the combination of a base station and a drone, a system of automatic surveillance of the area has been created. After successful development, the surveillance system was tested in practice and showed its practicality and reliability. The main problems that arose during the implementation of this system were analyzed and ways to solve them were proposed. In addition, Wi-Fi technology, IP and UDP protocols were investigated and applied as a means of information exchange between the base station and the UAV. The developed system of automatic monitoring of the terrain allows users to easily adjust the mode of operation of a certain area of the terrain, which can significantly help certain enterprises in the field of agricultural production, stop them from needing regular and stable data to identify problem areas of fields, forecast yields, and conduct research activities on large areas. crops Also, this system can be useful for nature protection organizations, after which they can organize constant monitoring of areas of forests that are under threat of destruction. In addition to this, security companies can use this system to protect objects with a large area, the following image from an unmanned aerial vehicle can be analyzed additionally with the help of artificial intelligence. The separation of the system at both the hardware and software levels allows for faster expansion of the platform’s potential, in particular, the base station can be easily modified for in-depth analysis of photo and video materials using an artificial intelligence system, like the Raspberry Pi itself using artificial intelligence accelerators (such as Google 8 Coral), as well as using cloud computing technologies. In order to use the needs of end users in planning automatic scheduled launches that occur cyclically, for example, at the same time, it was first tested, and then the utility for Linux operating systems - cron was used. This utility has demonstrated its reliability especially for such complex tasks. Keywords: terrain surveillance, UAV autopilot, UAV route planning, UAV automation, drone, quadcopter. List of used literary sources: 1. M. A. Lukmana and H. Nurhadi, "Preliminary study on Unmanned Aerial Vehicle (UAV) Quadcopter using PID controller," 2015 International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA), 2015, pp. 34-37, doi: 10.1109/ICAMIMIA.2015.7507997. 2. T. Huynh-The, Q. -V. Pham, T. -V. Nguyen, D. B. D. Costa and D. -S. Kim, "RF-UAVNet: High-Performance Convolutional Network for RF-Based Drone Surveillance Systems," in IEEE Access, vol. 10, pp. 49696-49707, 2022, doi: 10.1109/ACCESS.2022.3172787.