Adaptive Neural Network Control for Mobile Robot with Mecanum Wheels: Experimental Validation

In this paper, neural network (NN) adaptive tracking control for uncertain nonlinear systems is proposed to attenuate the effects caused by unmodeled dynamics, disturbances and variable operating conditions of a wheeled mobile robot with mecanum wheels. A NN with basic sigmoid functions is used to compensate for the nonlinearity and variable operating conditions of the robot. There are two features in our approach. The first one is that the drive structure of a Mecanum wheeled mobile robot with four wheels has 3 degrees of freedom and four drive modules, it is an object of an over-actuated type, the missing moment is determined on the basis of the power balance of the drive systems. The second one is that experiments are performed to clarify the effectiveness and advantage of the proposed method.