Quantized Fuzzy Lateral Control of Networked Autonomous Vehicle Against Unknown Disturbance Based on Adaptive Neural Network Observer

This paper contributes to establishing a quantized fuzzy lateral control scheme for the networked autonomous vehicle (NAV) with external disturbance and actuator fault. In order to ensure the robustness of the NAV system, Gaussian function is used as the radial basis of the neural network (NN) to approximate the unknown nonlinear disturbance signal. In addition, the quantization mechanism of measurement output is introduced to reduce communication overhead and simplify state observation procedure. Considering the difficulty of obtaining the state of moving vehicle, an adaptive NN observer is presented to estimate the unknown system state. Furthermore, the convergence analysis is carried out regarding the designed state observer and the weight updating law of NNs, which promotes the derivation of sufficient boundedness conditions for the NAV system. Finally, we provide an example to illustrate the effectiveness and performance of the designed NN-based control and observation strategy.