ПРОЕКТИРОВАНИЕ СИСТЕМЫ УПРАВЛЕНИЯ И ОБЕСПЕЧЕНИЕ АВТОНОМНОСТИ ДЛЯ МОБИЛЬНОГО ДВУХКОЛЕСНОГО РОБОТА

Abstract

Model Predictive Control is an advanced process control method that used while meeting aset of constraints. From an engineering point of view, the MPC method of designing control systemsis attractive, because is relatively simple in design, including for solving complex productionproblems. This method is similar to the classical synthesis of a control system based on a linearquadraticcontroller (LQR). The key difference between MPC and LQR is that predictive controlsolves the optimization problem within a sliding time horizon, while the linear quadratic methodused to solve the same problem over a fixed time window. The paper considers a method for constructingtwo-wheeled mobile robot control system using Model Predictive Control. The process ofbuilding a mathematical model of the mechanical system of the robot is given, as well as the linearizationof the resulting model is performed. The basic principles of constructing a control systembased on MPC for linear systems without external disturbances, as well as using an observer toassess the state of the model under the influence of additive white Gaussian noises, are presented.A variant of the synthesis of a control system with imposed restrictions on the input signal is considered.Also presented is a method for determining the position of a two-wheeled robot in spaceusing a vision system, which is based on the use of a neural network. The architecture of the usedmodel is given, as well as a stereo camera, which used to build an image depth map. In addition tothe above, the work describes in detail the principle of the deep learning model – YOLOv3, whichbased on several blocks of input data processing. A detailed description of the implementation of astereo camera in conjunction with an artificial neural network model using the Python programminglanguage and libraries for working with video data and a stereo camera is presented.