Design And Experimental Research On Intelligent Vehicle Transverse Motion Control System

Intelligent Vehicles(IV), which are a crucial problem of the Intelligent Transportation System(ITS), have attracted more and more attentions. As one of most critical part in the field of IV research, the research of vehicle lateral control system is meaningful and significant to enhance the road traffic operating and reduce the traffic accidents caused by driver factors more effectively.Bicycle model was established in the first to analyze impacts of parameters uncertainties for vehicle dynamic characteristic, vehicle speed was confirmed as more important factors for lateral controller design. Because IV is the non-holonomic motion constraint, highly nonlinear dynamic characteristics and parametric uncertain system. To cope with these problems above, multiple model theory and fuzzy logic are used for the design of vehicle lateral strategy. Vehicle model is divided into four local models based on the speed region, and local fuzzy controllers are built respectively. Then, by using a weighted integration of the four local outputs through a fusion module, a global control output is obtained so as to ensure the global performance.To verify the robustness and effectiveness of the proposed multi-model fuzzy controller, Simulation tests of lane changing and lane keeping are verified in the Matlab/Simulink environment. Moreover, the stability of this system, which is taken in the co-simulation using AMESim and Matlab/Simulink, is proofed with lane tracking of real route. The proposed controller can not only regulate the vehicle fitting in with the road curvature, but also achieve a lateral stability of lane keeping process.Computer vision is studied also to obtain real-time vehicle pose information for lateral controller. Based on rapid control prototype, a vehicle platform is built for experimental research. The practical feasibility of proposed controller and the reliability of the intelligent vehicle platform are verified in real-time vehicle lateral control experiments, which pave the way for the future research.