【作者】 苏野；

【导师】 洪伟；

【作者基本信息】 吉林大学 ， 系统工程， 2008， 硕士

【摘要】 在与长春一汽启明信息技术股份有限公司合作的吉林省科技厅项目《车载信息系统研制开发》及《基于浮动车的动态路径导航方法的研究》的研发背景下,本文主要对浮动车的动态信息提取和分析方面进行了相关的研究。在导航系统体系结构方面,研究了与传统自主导航体系结构不同的中心式导航模型,重点研究了其内部模块的功能以及在导航过程中起到的关键作用,并针对其各项功能进行了跑车实验。在交通流预测方面,本文根据卡尔曼滤波及Fuzzy回归方法的基本原理进行建模,并将模型进行改进,应用在智能交通系统中,从而通过对行程时间的预测来体现路段交通状况,仿真实验表明该方法能够有效地缓解在交通过程中发生的路段阻塞。在路径规划方面,在研究了静态路径规划的同时,采用了融入了预测信息的动态路径规划的方法,使得车辆在导航过程中能够更加准确实时的行驶。仿真实验表明,该方法提高了导航的稳定性和实时性。更多还原

【Abstract】 In recent years, along with the constant technological progress, the people’s living standards are improving, and thus led to a number of cars in life growing, not only for human travel has brought inconvenience, but also a serious impact on economic development. In order to effectively alleviate this problem, people of the intelligent transport system began to study in depth. Intelligent Transportation System, as the term suggests, is the total of satellite and ground control center, at the junction of testing equipment, computers and vehicles on the road, such as control systems, to link up to form a three-dimensional comprehensive transport system[18]. China’s ITS development started soon, some technical problems unresolved, the only local pilot, not a large practical.Based Intelligent Transportation System two different vehicle navigation model, the study of the autonomous vehicle navigation system, designed a more comprehensive function of the module more detailed division of labor to high-tech electronics and communications-based Centre for vehicle navigation system. And centre-axle vehicle navigation system, and gradually on a content analysis:1、Centre-navigation system. First of car navigation systems in the areas of Automotive Electronics core function of the vehicle navigation system through the module function MapX,VC + + and the development of a GIS (geographic information system) simulation environment, establishing a centre vehicles navigation system model the overall structure of the research centre of the various server module functions, including map-matching module, module path planning, forecasting modules, learning modules, GIS module, taking into account the various modules of the basic theory and principle of algorithm between functional modules and server links on the client side, mainly for vehicle navigation system to the traditional functions of the two new features: real-time traffic information map display, real-time travel and road condition enquiries. This is the main function of both its own unique software-based electronic map to complete, the section of the electronic map color changes to the traffic section of the state, through the Centre-powerful database records the history of road information. In addition, service-introduced on the transient traffic, as well as the estimated average state judge’s basic theory; floating on cars and real-time data center server communications, as well as the basic framework of the basic data-processing algorithm.2、Traffic flow forecasting. Initially on the areas of domestic and international traffic flow forecasting the basic methods, sets out the advantages and disadvantages of various methods from the general timing model start on the general timing modeling methods, including the general timing of the steady-state model of the process and Markov assumptions, as well as the timing model of reasoning: filtering, prediction, smoothing; on the Kalman filter theory in the field of traffic flow prediction applicability, which is derived from the Kalman filter principle applied to predict traffic flow in the field of mathematical model , and adopted the VC + + and MapX a car experiment in the other forecasting methods, based on the rapid return of Fuzzy Travel Time Prediction, including its forecast in the direction of traffic flow in the field of modeling methodologies, parameters identified with the improvement, and through sports simulation.3、Unexpected incidents research. Of unexpected events in the impact of traffic, as well as unexpected incidents occurred after the central server approach.4、Forecast information fusion center-vehicle navigation path planning. Analysis of the static model and path planning for the determination of target function; dynamic path planning on the path planning model, the objective function model, and simulation system in the model solution, which leads to a dynamic path planning in the forecast increase in information theory, forecast that the integration of dynamic path planning information. Through experiments in the car and come to the conclusion: the convergence of information after the forecast path planning dynamic than static and dynamic path planning path planning more crowded roads can reduce the number of users to reduce the average travel costs. Through this research and experimental demonstration against centre-vehicle navigation system, a set of perfect - client model, forecast in the navigation of the role of transient found the average forecast, traffic congestion and floating state judge Real-time vehicle information extraction and processing models and methods. Against traffic flow forecasting and found suitable for the field of traffic prediction method: Kalman filtering, Fuzzy regression analysis method, the algorithm can accurately predict the travel time and itinerary of speed, then pass the vehicle in the road and the average travelling time to judge Vehicle traffic conditions. Fusion forecast information on the dynamic path planning algorithm, according to the data filter to change the dynamic path planning function in the road resistance, thereby achieving more predictable vehicle navigation.更多还原