This paper studies the problem of adaptive observer-based radial basis function neural network tracking control for a class of strict-feedback stochastic nonlinear systems comprising an unknown input saturation, uncertainties, and unknown disturbances. To handle the issue of a non-smooth saturation input signal, a smooth function is chosen to approximate the saturation function and the state observer is used to estimate unmeasured states. By the so-called command filter method in the controller design procedure, the implementation complexity is reduced in the proposed backstepping method. Moreover, a radial basis function neural network is deployed to reconstruct the unknown nonlinear functions. In addition, the gains of all radial basis function neural networks are updated through one updating law leading to a minimal learning parameter which is independent of the number of neural nodes and the order of the system.Comparing with the existing results, the proposed approach can stabilize a constrained stochastic system more effectively and with less computational burden. Finally, a practical example shows the performance of the proposed controller design. K E Y W O R D Sadaptive neural network, command filter, input saturation, minimal learning parameter, observer, stochastic nonlinear systems 1 3296

No abstract

No abstract

Here, an adaptive radial basis function (RBF) neural network (NN) backstepping controller is proposed for a class of input‐constrained flexible joint robotic manipulators represented by strict‐feedback form with unknown terms, external stochastic disturbance, and output disturbance. The proposed approach is robust against both deterministic and stochastic uncertainties and disturbances and copes with the control input amplitude saturation. Moreover, by deploying the minimal learning parameter method and command filter technique, the computational burden of derivative terms and adaptive terms greatly decreases. Considering the mean‐value theorem assists us to avoid the need for having the input saturation bounds in prior. The suggested tracking control scheme mandates the closed‐loop system states to be semi‐globally bounded‐in‐probability. Also, a quartic Barrier Lyapunov function is utilized to force the tracking error to be confined within a pre‐chosen small region around the origin. Eventually, a numerical simulation of a flexible joint robot manipulator with a single link is performed to show the effectiveness and performance of the developed control method.