A neural genetic training for LQR controllers tuning applied to inverted pendulum

In this article is presented a method to design neural-genetic optimal controllers that are based on the fusion of a Recurrent Neural Network (RNN) and Genetic Algorithm (GA), these Computational Intelligence (CI) paradigms support the Linear Quadratic (LQR) design. The GA and RNN adaptation proprieties are the great advantage of the proposed approach, because all design is oriented to tune the optimal controller without inference of the human. A 4^th order model of an inverted pendulum is used to evaluate the training and control performance of the proposed method.