Adaptive Active Disturbance Rejection Control for Path Tracking of Intelligent Vehicle

The path tracking controller often cannot maintain the lateral stability of vehicles on large curvy roads with low adhesion road, which is easy to cause vehicle instability. In this paper, an adaptive active disturbance rejection control (ADRC) is designed to generate a front wheel angle and an additional yaw moment at the same time to guarantee the vehicle tracking accuracy and vehicle stability at the same time. The vehicle two-degree-of-freedom reference model and the path tracking error model are built to derive the error dynamics state equation. The multiinput multioutput ADRC decoupling control is studied. The BP neural network is designed to online adjust the four output parameters that are difficult to be determined in the nonlinear state feedback to form an adaptive ADRC. The yaw moment distribution scheme is studied next. By the joint simulation and hardware-in-the-loop experiment, the results show that the proposed adaptive ADRC can obtain good vehicle tracking accuracy and vehicle stability at the same time not only on both high and low adhesion roads but on the road with large curvatures.