Adaptive Neural Network Control of Uncertain State-Constrained Nonlinear Systems

Abstract

In this paper, an adaptive neural network control scheme is developed for a class of uncertain nonlinear systems in strict-feedback form subject to the constraints on the full states and unknown system drift dynamics. The Integral Barrier Lyapunov Functionals (iBLF) are utilized to handle the state constraints directly, leading to the relax of the feasibility conditions compared with pure tracking errors based Barrier Lyapunov Function. The radial basis function neural networks (RBFNN) are adopted to approximate and compensate for the unknown continuous packaged functions composed of the unknown system nonlinearities. Novel adapting parameters are constructed to estimate the unknown bounds in neural networks approximation in real time. Based on backstepping design and Lyapunov synthesis, we show that the developed control scheme can guarantee that all signals are semi-globally uniformly ultimately bounded (SGUUB), all states remain in the predefined constrained state space and system output converges to a small neighborhood of the desired trajectory. A practical three-order example is provided to demonstrate the performance of proposed methods.