ITS智能车辆横向运动模式空间构造算法研究

1． 山东大学控制科学与工程学院，山东济南250061；2． 山东理工大学计算机科学与技术学院，山东淄博255049；3． 天津大学电气与自动化工程学院，天津300072）摘要：针对ITS（intelligent transport system）智能车辆复杂的非线性结构和时变特性，提出了以空间代替时间建立IV（intelligent vehicle）横向运动模式空间的思想．通过改变车辆的各种参数，针对车体的数学模型采集车体在各种环境条件下的模拟运动控制信息．以模糊C均值算法（FCM）为基础，推导出车辆运动模式空间的构造算法．该构造算法能够客观地对测量数据进行有效聚类，聚类清晰，模式子空间划分清楚，从而为车辆运动模式空间的构造提供了一种理论依据．最后对样本数据的聚类和模式空间的构造算法进行了仿真，结果证明了算法的有效性和可行性

On intelligent vehicle transverse locomotion pattern space construction for intelligent transport system

In order to deal with the nonlinear and time-varying character of the IV,this paper presents a new idea that replace time with space to construct IV transverse locomotion pattern space.The simulative locomotion information is sampled based on the vehicle mathematical model by changing parameters in the various environments.The construction method has also been deduced based on FCM using the data.The method can cluster the sampled data set effectively.Clustering set is clear,and the subspace is divided distinctly.It provides a theoretical basis for IV locomotion pattern space construction.Finally,data clustering and pattern space construction are simulated.The simulation results show that the method is effective and feasible.