In this paper, a radial basis function (RBF) neural network is used to estimate the nonlinear functions of sliding mode control that is applied in trajectory tracking to control Omni-directional mobile robot. This is a holonomic robot that can operate easily in small and narrow spaces, due to the ability of flexible rotational and translational moving, simultaneously and independently. In this application, the RBF neural network is considered as an adaptive controller. The weights of the network are modified online due to the feedback from output signals of the plant. The adaptation law is derived using the Lyapunov method so that the stability of the entire system and the convergence of the weight adaptation are guaranteed. The simulation results in MATLAB Simulink show that the proposed algorithm is efficient, the response of the Omni-directional mobile robot in simulation model converge to reach the trajectory without steady-state error, and the setting time is about 0.3±0.001(s).