<p>This paper presents a trajectory tracking approach of a four-wheeled omnidirectional mobile robot using computed torque (CT) control and radial basis function neural network (RBF NN). A dynamic model of a four-wheel omnidirectional mobile robot is developed and based on it, a CT control law is established. We estimate and compensate the parameters variations present in the dynamic model, Coriolis and centrifugal force components, friction components and unknown disturbances by using RBF NN. RBF NN is used to estimate the model uncertainty and disturbance present in the dynamic model and compensate it in the control force calculation. The effectiveness of the proposed method is compared with the CT control method via simulations and experiments. Experimental results show that the proposed method is more effective than CT control in the presence of model uncertainties and unknown disturbances. In particular, it is much more efficient in the case of coexisting model uncertainties and disturbances than in the presence of model uncertainties alone.</p>