Comparative analysis for NN inverse model controller and back-stepping controller on mobile robots

摘要

This work addresses the design and implementation of a neural network based controller for the trajectory tracking of a differential drive mobile robot. A neural network based tracking control algorithm is proposed and simulation and experimental results are presented. The algorithm is a control structure that makes possible the integration of a back-stepping controller and a neural network (NN) computed-torque controller for a nonholonomic mobile robot. Integration of a neural network controller and the kinematic based controller gives the advantage of dealing with unmodeled and unstructured uncertainties and disturbances to the system. Comprehensive system modeling including robot kinematics, dynamics and actuator modeling has been done. The dynamic modeling is done Lagrangian methodologies for nonholonomic systems. Simulation of the robot model and different controllers has been done using Matlab and Matlab Simulink.