一种利用粒子滤波的实时交通状态估计方法  

State Estimation of Real-time Motorway Traffic Based on Particle Filtering

作　　者：程松[1] 陈光梦[1] 

机构地区：[1]复旦大学电子工程系

出　　处：《微型电脑应用》2008年第2期13-17,4,共5页Microcomputer Applications

摘　　要：将粒子滤波理论和宏观随机交通流模型结合,对高速公路交通状态进行实时估计。在该方法中,高速公路被看作是由等距离的路段首尾相接而形成的模型,交通传感器通常设置在路段的交界处,而且数量远少于所需估计的交通状态。采用压缩状态空间的形式,将模型参数也作为交通状态而非常量进行估计。仿真结果表明粒子滤波方法能够有效地估计和跟踪交通状态的变化,并且与扩展卡尔曼滤波方法相比具有更高的精确度。An approach to the real-time estimation of the traffic state in motorway is developed based on particle filtering and macroscopic stochastic traffic flow model.The motorway stretch is divided into several segments one by one with the same length while the electronic sensors are usually placed between some segments and the measurements are less than states estimat- ed.This paper uses the compact state-space method and treats the model parameters as the traffic states.Simulation results prove that partic|e filtering can predict and track the state efficiently.It is also more accurate than EKF method.

关 键 词：非线性估计 贝叶斯估计 粒子滤波 宏观随机交通流模型 扩展卡尔曼滤波 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]