Adaptation of a Fuzzy Controller’s Scaling Gains Using Genetic Algorithms for Balancing an Inverted Pendulum

This paper examines the development of a genetic adaptive fuzzy control system for the Inverted Pendulum. The inverted pendulum is a classical problem in Control Engineering, used for testing different control algorithms. The goal is to balance the inverted pendulum in the upright position by controlling the horizontal force applied to its cart. Because it is unstable and has a complicated nonlinear dynamics, the inverted pendulum is a good testbed for the development of nonconventional advanced control techniques. Fuzzy logic technique has been successfully applied to control this type of system, however most of the time the design of the fuzzy controller is done in an ad-hoc manner, and choosing certain parameters (controller gains, membership functions) proves difficult. This paper examines the implementation of an adaptive control method based on genetic algorithms (GA), which can be used on-line to produce the adaptation of the fuzzy controller’s gains in order to achieve the stabilization of the pendulum. The performances of the proposed control algorithms are evaluated and shown by means of digital simulation.