ІНТЕЛЕКТУАЛЬНЕ УПРАВЛІННЯ МОБІЛЬНИМ РОБОТОМ ПРИ СЛІДКУВАННІ ЗА РУХОМИМ ОБ’ЄКТОМ

• Дата: 2025
• Автори: Sukhoruchkina , O.N., Progonnyi , N.V.
• Формат: Стаття
• Мова: English
• Опубліковано: V.M. Glushkov Institute of Cybernetics of NAS of Ukraine 2025
• Теми: мобільний робот; інтелектуальне управління; розпізнавання образів; візуальна навігація
• Онлайн доступ: https://jais.net.ua/index.php/files/article/view/698
• Назва журналу: Problems of Control and Informatics

The questions of the practical implementation of the mobile robot intelligent control in dynamic environment when it performs the mission of tracking a moving object are considered. Information about positions of the target object and other ones in the robot environment is generated as a result of the analysis of on-board camera images. In this case, the goal of the robot motion control is not to pursue the object as in the well-known formulation of problems in game theory, optimal control, etc. Also, the goals of this work do not cover analysis or development of new methods and algorithms of pattern recognition. In our case tracking implies the robot autonomous ability to collect data on the dynamics and trajectories of the target object relative to the model of the environment, and the image analysis subsystem is based on one of the well-known feature-oriented algorithms for detecting and recognizing objects, which can be replaced if necessary by any other one. The control system of the robot is responsible for determining such parameters of its motion so that the target object is kept mainly in the center of field of view of the on-board camera at a given distance from robot, and the robot trajectory is collision-free with the obstacles. Planning a safe trajectory of the robot’s motion is carried out to the nearest position from the set of the possible ones at which the robot’s camera can perceive the target object without significant overlap by other objects. Also, when the robot performs the main mission, the intelligent control system is able to determine and activate situationally relevant robot actions, such as self localization in the working room, searching for the target object when it is not in the camera’s field of view, etc. The main focus of the work is on the techniques for providing the sufficient information awareness for the intelligent control system of the mobile robot when it autonomously executes the mission «Track object». Illustrations that demonstrate the results of performing this mission by the robot are presented.