|Title of the article||
STUDY ON MODEL IDENTIFICATION METHOD AND CONTROL METHODS
Prokopyev Igor Vitalevich, doctor of technical sciences, leading researcher, Federal research center «Computer science and control» of RAS
This paper presents the results of nonlinear model identification of an unmanned vehicle in the Gazebo simulator based on a neural network autoregressive model. The dynamic characteristics of the control object can vary significantly that complicates the problem. Data on the movement along the spatial path of an unmanned vehicle for the training sample was obtained at the Robotics Center of the FRC CSC RAS. The model parameters were found by the particle swarm optimization method. Using the identified model, real-time control methods were experimentally compared. Control was carried out on the basis of the PID controller, model predictive control method and identifier based on artificial neural networks. In a comparative experiment, for a more accurate assessment of the identification method, the model was subjected to random disturbances, and the tracking path of the control object was significantly complicated.
identification, unmanned vehicle, path tracking.
1. L'yung L. Identifikatsiya sistem [System identification]. Moscow: Nauka, 1991, 432 p. [In Russian]
Дата обновления: 24.11.2020 16:20