Research on Intelligent Vehicle Trajectory Planning and Control Algorithm Based on Model Predictive Control

With the development of computer technology and semiconductor technology and the improvement of people’s living standards, automatic driving technology has attracted more and more attention from the industry. Compared with manual driving, able to drive vehicles can have higher perceived distance, higher operation accuracy and better compliance with traffic rules. As one of the key technologies in the field of intelligent driving, intelligent vehicle trajectory planning and control is the technical premise of realizing unmanned driving. Under the current technology, the complex coupling relationship between vehicle longitudinal and transverse motion limits the further rapid development of intelligent vehicle path tracking control. Scholars at home and abroad focus on the motion control of autopilot, which includes horizontal motion control, longitudinal motion control and multi vehicle cooperative control. Trajectory planning and tracking control are important parts to ensure the normal driving of intelligent vehicles. As the basic condition and key technology of realizing driverless vehicle, intelligent vehicle trajectory planning and control has important research significance. Therefore, it is of far-reaching research significance to formulate appropriate control methods to overcome the nonlinearity of vehicles and the complexity of driving conditions. In this paper, the Model Predictive Control, (MPC) theory is used to study the vehicle trajectory planning and control technology. Model predictive control has the ability to consider predictive information and deal with multiple constraints, which provides a new way for vehicle motion control with multiple application scenarios and multiple control targets. Therefore, it is of great significance to study the application of model prediction in vehicle tracking control to improve the tracking effect, driving stability and real-time solution of vehicles under multi-control targets. In the study, we will also consider the scenes that need to avoid parking, so that the trajectory planned by the algorithm is more in line with human driving habits, and can be applied to complex traffic scenes that need to avoid moving obstacles.