基于ANFIS及MPC的车辆转向换道控制系统设计  

Design of vehicle steering and lane changing control system based on ANFIS and MPC

作　　者：石振新 冯剑波 王衍学 SHI Zhenxin;FENG Jianbo;WANG Yanxue(Beijing University of Civil Engineering and Architecture,Beijing 100000,China)

机构地区：[1]北京建筑大学,北京100000

出　　处：《现代制造工程》2022年第2期70-78,共9页Modern Manufacturing Engineering

基　　金：国家重点研发计划资助项目(2017YFB0102600);国家自然科学基金项目(51875032);北京市百千万人才计划资助项目(2020A26);北京建筑大学市属高校基本科研业务专项资金资助项目(X20159)。

摘　　要：为提高智能车辆在高速工况下进行转向换道避撞时的行驶稳定性,设计了一种基于ANFIS及MPC的车辆转向换道控制系统。车辆转向换道控制系统是以模型预测控制(Model Predictive Control, MPC)算法为基础,结合五阶多项式换道路径和最小车距安全模型搭建的;以理想横摆角速度与实际横摆角速度的偏差及其变化率为双输入,利用自适应神经模糊系统(Adaptive Network-based Fuzzy Inference System, ANFIS)规则输出所需的附加横摆力矩,对车轮进行差动制动,以修正车身姿态,实现行车稳定。仿真结果对比表明,此车辆转向换道控制系统可显著提高车辆在高速工况下进行转向换道避撞时的行驶稳定性。In order to improve the driving stability of intelligent vehicle when it performs lane changing to avoid collision at high speed, a vehicle lane change control system based on ANFIS and MPC was designed.The lane-changing control system is based on Model Predictive Control(MPC) algorithm, combines which the five-order polynomial lane-changing path and the minimum distance safety model.Taking the deviation and change rate of the ideal yaw speed and the actual yaw speed as double inputs, the Adaptive Network-based Fuzzy Inference System(ANFIS) was applied to output the additional yaw moment required. To correct the attitude of the car body to achieve driving stability. The simulation results show that the steering and lane change control system can significantly improve the vehicle’s driving stability when steering lane change to avoid collision at high speed.

关 键 词：路径跟踪 转向换道 主动避障 模型预测控制 自适应神经模糊系统 

分 类 号：U461[机械工程—车辆工程] TP273.2[交通运输工程—载运工具运用工程]