Taking mobile robot as the research object

a sliding mode control（ SMC） algorithm based on backstepping kinematics control and radial basis function neural network（ RBFNN） minimum parameter learing method（ MPLM） is proposed

aiming at the uncertainty and nonlinearity of the robot system model. The RBFNN is used to approximate the uncertainties in the system

eliminate the influence of uncertain factors in the system and enhance the robustness of the system. Aiming at the defect that the weights in the RBFNN are difficult to adjust quickly

the minimum parameter learning method is used to design a single parameter to replace the weight in the neural network

so as to optimize the algorithm complexity and enhance the real-time characteristics of control. The convergence and stability of the system in a finite time are proved by the Lyapunov stability discriminant method.Experiments show that this method can simplify the structure of the controller

significantly improve the robustness and real-time performance of the controller

and it is easy to implement in practical applications.