基于神经网络滑模的智能车辆横向控制

以智能车辆为研究对象,针对车辆模型存在高度非线性动态特性、参数不确定性以及行驶时受外部干扰较多导致控制精度不高、鲁棒性差等问题,提出了采用径向基函数(RBF)神经网络滑模控制方法.建立2自由度线性车辆模型和自由度非线性整车模型,在传统2自由度车辆控制模型状态方程的基础上推导出新的状态方程并以此设计了相应控制器.利用李雅普诺夫(Lyapunov)稳定性理论推导出神经网络的权,并证明控制系统的稳定性.仿真结果表明:与传统的滑模控制方法相比,该方法控制精度高,有较强的鲁棒性.

Lateral control of intelligent vehicle based on neural networks sliding mode

The RBF neural networks sliding mode control method is proposed to solve the highly nonlinear dynamic characteristic and parametric uncertain properties of the intelligent vehicle model as well as the low control precision and poor robustness caused by massive external interference during driving.A two degrees of freedom(DOF) linear vehicle model is built along with a seven DOF non-linear vehicle model.A new state equation is derived based on traditional state equation of the two DOF vehicle control method and the corresponding controller is designed.The Lyapunov stability theory is involved to derive the weights of the neural network and the stability of the control system is verified.Simulation results show that the proposed method has higher control precision and stronger robustness compared with the traditional sliding mode control method.