Model Predictive Control Method for Intelligent Vehicle Trajectory Tracking Based on Model Compensation

Abstract

The invention discloses a model prediction control method for intelligent vehicle trajectory tracking based on model compensation, which includes establishing a 2-degree-of-freedom vehicle dynamics model to simulate an intelligent vehicle; The differential form of the vehicle dynamics model is discretely linearized to obtain a linear error model, which is used as the prediction model of the model predictive controller, and finally the optimal control variable front wheel slip angle δ is obtained. _f0 ; Take the error e and the error change between the current trajectory and the expected trajectory of the vehicle as the input of the RBF neural network, and output δ _f1 is the front wheel slip angle compensated by the adaptive RBF neural network; the optimal control quantity output by the model predictive control system is the front wheel slip angle δ _f0 and the front wheel slip angle δ compensated by the adaptive RBF neural network _f1 The inputs δ that make up the final smart vehicle _f . This method is used to improve the precision of the intelligent vehicle tracking the desired trajectory.

Description

technical field [0001] The invention belongs to an intelligent vehicle trajectory tracking control method, in particular to a model compensation-based intelligent vehicle trajectory tracking model predictive control method. Background technique [0002] Intelligent vehicles, that is, vehicle intelligence, are the main development direction of future vehicle technology. They are the result of the integration of vehicle technology and control, information, artificial intelligence and other technologies. Manipulation. With the development of control theory, more and more control theories and control methods have been applied to the trajectory tracking control of intelligent vehicles. An efficient and stable trajectory tracking control system is a necessary condition for the realization of intelligence and practicality of unmanned vehicles. [0003] The goal of vehicle motion control is to generate control quantities according to the trajectory planned by the upper layer and th...

AI Technical Summary

Problems solved by technology

In the existing model predictive trajectory tracking controller, when the force on the tire changes, the cornering stiffness coefficient of the tire is still a constant quantity, which is not updated in real time, which will cause a mismatch between the vehicle model and the controller model

Images