Support Value-Based NFSMC for Wheeled Mobile Robot Path Tracking in Unknown Environments

Abstract

Mobile robot navigation is an obscure condition that plays a vital role in different applications such as military purposes, navy, etc. now a day's lot of problems occur during navigation. To solve the navigation problem an RGB-Depth sensor along with support value-based neuro-fuzzy sliding mode controller techniques (SVB-NFSMC) are proposed. The RGB-Depth sensor is used to estimate the depth map using the linear coefficients along with the bilateral filter. Then the angular and linear velocity is calculated to define the angular position and the object movement. Then the calculation of support value is based on the above angular and linear estimation values. Here the depth map and support value as a training data set input are given to the controller. Subsequently, the sliding mode controller provides the guiding commands in terms of guidance law, control law to the robot system. The ANFIS and the GWO algorithm are used to optimize the parameters is given to the controller then the Lyapunov function is used to analyze the stability of the system. Finally, compare the proposed work with the existing AKH-NFIS and the other SMC methods provides better outcomes.