Feedback Control of an Inverted Pendulum with the use of Artificial Intelligence

An inverted pendulum represents a simple device which is excellent for demonstrating the use of feedback control of an unstable system with different kinds of control strategies. In this work feedback control of a physical model of an inverted pendulum is investigated from the point of view of a state space model of the system. First a pole placement algorithm is thoroughly explored. After this an artificial intelligence (AI) method is investigated to better cope with the nonlinearities of the physical model. The technique used is based on a hybrid system combining the qualities of a neural network with those of a genetic algorithm.