CONTROL SYSTEM FOR GROUND MOBILE ROBOTS

Background. Сonsiders the main aspects of constructing spatial orientation and positioning systems for ground-based mobile robots using object detection algorithms. The aim of the work is to study the possibility of using neural network object detection algorithms in real time to control a technological transport platform that performs various operations outside buildings. Materials and methods. Application in robotics of specialized software created on the basis of software products and environments for development in robotics. Results and conclusions. Presents an analysis of the most suitable neural network algorithms for detecting objects in real time, which improve the quality of object detection, making the systems more efficient and accurate.