A fuzzy-genetic controller for the flexible pole-cart balancing problem

This paper investigates the applicability of developing a controller based on genetic algorithms combined with fuzzy logic to control the flexible pole-cart balancing problem. The genetic algorithm is used to obtain the values of the variables required by the fuzzy logic controller, removing the need for expert knowledge. The system employs genetic search to extract the fuzzy rules and membership functions using an objective function calculated from the fuzzy logic system evaluation function. The extracted rules are used in the fuzzy associative memory matrix entries so that the fuzzy logic system performance fits the desired behaviour. Results show that the controller developed is able to predict the desired output for the flexible pole-cart balancing problem with high accuracy