Abstract
A new multi-model predictive control (MMPC) algorithm was proposed and applied in an intelligent vehicle lateral tracking control system in this paper, which is better to adapt the intelligent vehicle lateral tracking control under complex multi-conditions. First, the Gustafson–Kessel algorithm was used for the cluster analysis based on the vehicle test data to obtain the clustering center and train the sample data of each typical steering condition. Then, a multi-model structure was constructed by least squares support vector machines, and the sub-models of each category were taken as the prediction model for the application of MPC. Hence, the objective function of multi-objective optimization can be established and the multi-objective optimization problem was solved by the non-dominated sorted genetic algorithm-II algorithm to obtain the optimal control quantity. Finally, the MMPC-based intelligent vehicle lateral tracking control system was used to control the vehicle lateral tracking under three steering conditions, including straight line, normal right turn, and U-turn, through a simulation study in the MATLAB/Simulink environment. By comparing the vehicle trajectory, steering wheel angle, lateral deviation, and lateral angle, the performance of the proposed control method was verified. The experimental analysis results show that the proposed method can track the steering wheel angle of the vehicle reference trajectory under various working conditions. The vehicle lateral deviation value can be controlled in the range of (−1.0 m, 0.5 m). The high-precision lateral tracking control ensures that the yaw rate of the vehicle can track the yaw velocity under the reference driving track and guarantees the driving stability of intelligent vehicles.
Highlights
Intelligent vehicle dynamics control mainly includes two aspects: the vehicle longitudinal tracking control technology and vehicle lateral tracking control technology
In order to solve the problem of Model predictive control (MPC) in the above aspects, an intelligent vehicle lateral tracking control method based on multimodel predictive control is proposed in this paper
Since the test data need to be normalized before the cluster analysis, the steering wheel angle, the upper limits, and lower limits of the steering wheel angle velocity are determined by searching the test data, which lays a foundation for constructing various multi-model predictive control (MMPC) model structures under complicated multi-conditions
Summary
“Electrical, intelligent, networked, and shared” are the four major development trends of the global automotive industry. Since 2015–2016, major internet companies have entered the automotive field and focused their research and development on the intelligent vehicles in order to solve the huge social and economic losses caused by the tragedy that nearly 13.5 × 106 people were killed and injured in traffic accidents every year. Kim et al proposed a nonlinear steering wheel angle control method for electronic power steering (EPS) self-correcting torque in the intelligent vehicle lateral control system. Han et al proposed a neural network proportion integral derivative (PID) controller that was established for lateral path tracking control based on the vehicle model and the steering system model.. The traditional control algorithm cannot achieve lateral tracking control in the complex road scenes due to the nonlinearity and parameter perturbation of the intelligent vehicle model. In order to solve the problem of MPC in the above aspects, an intelligent vehicle lateral tracking control method based on multimodel predictive control is proposed in this paper. A complex multi-model structure is built based on the existing model predictive control algorithm using least squares support vector machines (LS-SVMs) according to the actual driving conditions of intelligent vehicles. The effectiveness of the proposed algorithm is verified based on the simulation and experimental studies under various working conditions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
