Path planning of an autonomous mobile robot using adaptive network based fuzzy controller

In recent years intelligent soft computing techniques such as fuzzy inference system (FIS), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are proven to be efficient and suitable when applied to a variety of systems. In this paper we intend to formulate an adaptive neuro-fuzzy inference system (ANFIS), a new sensor based navigation technique for mobile robot. The ANFIS controller uses different sensors based information such as front obstacle distance (FOD), right obstacle distance (ROD), left obstacle distance (LOD) and heading angle (HA) for choosing the optimal direction while moving towards target. The real time experiment has been carried out under different environmental scenarios to collect the data set for modeling ANFIS tool box. Using ANFIS tool box, the obtained mean of squared error (MSE) for training data set in the current paper is 0.031. We also have present the simulation experiments using MATLAB, showing that ANFIS consistently perform better results to navigate the mobile robot safely in a terrain populated by stationary obstacles.