ANFIS Controller for Non-holonomic Robots

Abstract

In this paper, a control strategy for a non-holonomic robot based on an Adaptive Neural Fuzzy Inference System is proposed. The neuro-controller makes it possible for the robot to track a given reference trajectory. After a short introduction about Adaptive Neural Fuzzy Inference System, the control strategy which is used on our virtual non-holonomic robot is described. And finally, the simulationsâ results where the robot has to pass into a narrow path and also the first validation results concerning the implementation of the proposed concepts on a real robot is given.