车载导航系统中动态交通信息提取与分析
|
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。
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.
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。
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.
引文
[1] 张其善,吴今培,杨东凯.智能车辆定位导航及应用.北京:科学出版社.2002.
[2] 高自友,任华玲.城市动态交通流分配模型与算法.人民交通出版社.2005.
[3] WEST GERMANY. Intersect ion Without Signals.[M ]. Proceeding of an Internat- -ional Work shop 16218 March, 1988. 30—40.
[4] 陈壁峰,陆昊娟,黄樟灿.车辆导航系统的动态最优路径搜索模型及算法.武汉理工大学学报:信息与管理工程版.第 24 卷第 3 期 2002 年 6 月.
[5] 苏永云,晏克非,黄翔,朱培康.车辆导航系统的动态最优路径搜索方法研究,系统工程, 2000 年 7 月,第 18 卷第 4 期(总第 till:期).
[6] Li Jing, Peng Guoxiong.Dynamic Drivers' under the Efect of Advanced Traveler Information and Guidance Systems.0-7803-7010-4/01/$10.0002001IEEE.
[7] 涂冰英,城市自动车辆导航系统关键技术研究:[硕士学位论文].武汉.武汉测绘科技大学.1999.
[8] 张可,车辆导航系统关键技术研究:[博士学位论文].北京工业大学.北京.2001.
[9] David Levinson “The value of advanced traveler information systems for route choice”Transportation Research Part C 11,pp75-87,2003.
[10] 陈建春.Visual C++开发 GIS 系统(第二版)电子工业出版社 2004 年 3 月.
[11] 田晶,杨玉珍.基于 VC 和 MapX 的停车诱导信息系统软件开发.北京工业大学 2006 年.
[12] 刘光,地理信息系统二次开发教程-组件篇[M].北京.清华大学出版社.2003.
[13] 赵亦林,车辆定位与导航系统.北京:电子工业出版社,1999.
[14] 王力,张海,等. 基于探测车技术的路段平均速度估计模型[J]. 交通运输系统工程与信息,2006.04(6):29-33.
[15] Boyce D, Kirson A , Schofer J . Design and implementation of advance [C] . IEEE Proceeding of 3rd Inter. Vehicle Navigation and Information Systems , 1993 : 415 -426.
[16] Richard Bishop. Floating car data projects worldwide : a selective review[C] . ITS America Annual Meeting , 2004.
[17] 秦玲,张剑飞,等. 浮动车交通信息处理与应用系统核心功能及实现[ J ] .公路交通科技(应用技术版) ,2006 , (11) :44 - 46.
[18] 董敬欣.基于GPSPGIS 的浮动车技术在城市路网分析与评价中的相关方法及应用研究[D] . 北京:北京交通大学,2005.
[19] 温慧敏,孙建平,郭继孚,邓小勇,陈锋,高永. 浮动车交通信息采集系统关键技术与实验验证研究[C].城市交通规划学会年会,2005.
[20] 孙建平,温慧敏,郭继孚. 浮动车交通信息采集系统建设框架研究[C] . 第一届中国智能交通年会,2005.
[21] 姜桂艳,江龙晖,王江锋,张晓东.信息融合技术在道路交通参数预测中的应用.吉林大学交通学院 2004 年 4 月.
[22] 戴施乐,周欣荣.Kalman滤波理论在短时交通预测上的应用.哈尔滨商业大学学报 Vol 21 No 6 Dec 2005.
[23] 李嘉,刘小兰.基于卡尔曼滤波理论的交通信息预测模型及其应用.中南公路工程 Vol 30 No 4 Dec 2005.
[24] 戴施乐,周欣荣.Kalman 滤波理论在短时交通预测上的应用.哈尔滨商业大学学报 Vol 21 No 6 Dec 2005.
[25] 贺国光,李宇,马寿峰.基于数学模型的短时交通流预测方法探讨[J].系统工程理论与实践,2000 (12).
[26] Makr Dougherty.A Reviewof Neural Network Applied to Transport [J].Transportation Research , 1996 : 151 – 166.
[27] Brian L Smith , Michael J Demetsky.Traffic Flow Forecasting:Comparison of Modelling Approaches [J] .Journal of Transportation Engineering , 1997 : 261 – 266.
[28] Mohammad M Hamed , Hashem R AlOmasaeid , Zahi MBani Said1ShortOterm Prediction of Traffic Volume in Urban Arterials [J] .Journal of Transportation Engineering , 1995 : 249 – 2541.
[29] Mascha Der Voort , Mark Doughert , Susan Watson.Combining Kohonen Maps with ARIMA Time Series Models to Forecast Traffic Flow [J] .Transportation Research , 1996 : 307 – 318.
[30] 宫晓燕,汤淑明.基于非参数回归的短时交通流量预测与事件检测综合算法[J].中国公路学报, 2003 (1) : 82 – 86.
[31] 朱中,杨兆升.实时交通流量人工神经网络预测模型[J]. 中国公路学报, 1998 (4) : 89 – 92.
[32] 邓自立,郭一新.动态系统分析及其运用——建模、滤波、预报、控制的新方法和程序库 沈阳: 辽宁科学出版社, 1985.
[33] Danech-Pajouh, M., Aron, M., 1991. ATHENA, a method for short-term inter-urban traffic forecasting. Report 177,INRETS, Arcueil, Paris.
[34] Kwon, J., Coifman, B., Bickel, P.J., 2000. Day-to-day travel time trends and travel time prediction from loop detector data. In:Transportation Research Record, 1717, 120–129.
[35] Nicholoson, H., Swann, C., 1974. The prediction of traffic flow volumes based on spectral analysis. Transportation Research 8, 533–538.
[36] Park, D., Rilett, L., 1998. Forecasting multiple-period freeway link travel times using modular neural networks. In Transportation Research Record. no. 1617. Transportation Research Board, pp. 163–170.
[37] David Boyce, Nagui Rouphail and Allan Kirson. Estimation and measurement of link travel time inthe ADVANCE project. IEEE vehicle Navigation and Information Systems Conference. Ottaw a-VN IS, 1993.
[38] A bours S. Estimation of travel time from occupancy on an urban network: an experiment in Paris.
[39] France. Second International Conference on Road Traffic Control, Institution of Engineers, London,U K. 1986.
[40] 吴万铎,吴万钊.模糊数学与计算机应用[M].北京电子工业出版社.1988.
[41] Dailey D J1A Statistical Algorithm for Estimating Speed from Single Loop Volume and Occupancy Measurements[J ] Transportation Research B ,1999 (33) :313 – 3221.
[42] Nam D H ,D R Drew1Traffic Dynamics : Method for Estimating Freeway Travel Times in Real Time From Flow Measurements[J ] Journal of Transportation Engineering ,1989 (122) :185 – 1911.
[43] 刘桂生,城市快速路系统规划设计[J ].城市道桥与防洪.2000(1):11.
[44] 杨兆升,城市交通流诱导系统理论与模型[M].人民交通出版社.2000.1.
[45] 贺仲雄,模糊数学及其应用[M].天津科学技术出版社.1983.1.
[46] 苏永云,晏克非,黄翔,朱培康.车辆导航系统的动态最优路径搜索算法研究.系统工程第 18 卷第 4 期.
[47] 杨兆升,李全喜.基于城市交通控制系统的动态车辆行驶路线选择的方法.公路交通科技 Vol 16 No 1.
[48] Eiichi Taniguchi,Hiroshi Shimamoto “Intelligent transportation system based dynamic vehicle routing and scheduling with variable travel times” Transportation Research Part C12, 235-250,2004.
[49] 陈壁峰,陆昊娟,黄樟灿.车辆导航系统的动态最优路径搜索模型及算法.武汉理工大学学报·信息与管理工程版,第 24 卷第 3 期 2002 年 6 月.
[50] 苏永云,晏克非,黄翔,朱培康.车辆导航系统的动态最优路径搜索方法研究.系统工程.2000 年 7 月.第 18 卷第 4 期.
[51] 美国交通研究委员会.道路通行能力手册[M].任福田,译.北京建筑工业出版社,1985.
[2] 高自友,任华玲.城市动态交通流分配模型与算法.人民交通出版社.2005.
[3] WEST GERMANY. Intersect ion Without Signals.[M ]. Proceeding of an Internat- -ional Work shop 16218 March, 1988. 30—40.
[4] 陈壁峰,陆昊娟,黄樟灿.车辆导航系统的动态最优路径搜索模型及算法.武汉理工大学学报:信息与管理工程版.第 24 卷第 3 期 2002 年 6 月.
[5] 苏永云,晏克非,黄翔,朱培康.车辆导航系统的动态最优路径搜索方法研究,系统工程, 2000 年 7 月,第 18 卷第 4 期(总第 till:期).
[6] Li Jing, Peng Guoxiong.Dynamic Drivers' under the Efect of Advanced Traveler Information and Guidance Systems.0-7803-7010-4/01/$10.0002001IEEE.
[7] 涂冰英,城市自动车辆导航系统关键技术研究:[硕士学位论文].武汉.武汉测绘科技大学.1999.
[8] 张可,车辆导航系统关键技术研究:[博士学位论文].北京工业大学.北京.2001.
[9] David Levinson “The value of advanced traveler information systems for route choice”Transportation Research Part C 11,pp75-87,2003.
[10] 陈建春.Visual C++开发 GIS 系统(第二版)电子工业出版社 2004 年 3 月.
[11] 田晶,杨玉珍.基于 VC 和 MapX 的停车诱导信息系统软件开发.北京工业大学 2006 年.
[12] 刘光,地理信息系统二次开发教程-组件篇[M].北京.清华大学出版社.2003.
[13] 赵亦林,车辆定位与导航系统.北京:电子工业出版社,1999.
[14] 王力,张海,等. 基于探测车技术的路段平均速度估计模型[J]. 交通运输系统工程与信息,2006.04(6):29-33.
[15] Boyce D, Kirson A , Schofer J . Design and implementation of advance [C] . IEEE Proceeding of 3rd Inter. Vehicle Navigation and Information Systems , 1993 : 415 -426.
[16] Richard Bishop. Floating car data projects worldwide : a selective review[C] . ITS America Annual Meeting , 2004.
[17] 秦玲,张剑飞,等. 浮动车交通信息处理与应用系统核心功能及实现[ J ] .公路交通科技(应用技术版) ,2006 , (11) :44 - 46.
[18] 董敬欣.基于GPSPGIS 的浮动车技术在城市路网分析与评价中的相关方法及应用研究[D] . 北京:北京交通大学,2005.
[19] 温慧敏,孙建平,郭继孚,邓小勇,陈锋,高永. 浮动车交通信息采集系统关键技术与实验验证研究[C].城市交通规划学会年会,2005.
[20] 孙建平,温慧敏,郭继孚. 浮动车交通信息采集系统建设框架研究[C] . 第一届中国智能交通年会,2005.
[21] 姜桂艳,江龙晖,王江锋,张晓东.信息融合技术在道路交通参数预测中的应用.吉林大学交通学院 2004 年 4 月.
[22] 戴施乐,周欣荣.Kalman滤波理论在短时交通预测上的应用.哈尔滨商业大学学报 Vol 21 No 6 Dec 2005.
[23] 李嘉,刘小兰.基于卡尔曼滤波理论的交通信息预测模型及其应用.中南公路工程 Vol 30 No 4 Dec 2005.
[24] 戴施乐,周欣荣.Kalman 滤波理论在短时交通预测上的应用.哈尔滨商业大学学报 Vol 21 No 6 Dec 2005.
[25] 贺国光,李宇,马寿峰.基于数学模型的短时交通流预测方法探讨[J].系统工程理论与实践,2000 (12).
[26] Makr Dougherty.A Reviewof Neural Network Applied to Transport [J].Transportation Research , 1996 : 151 – 166.
[27] Brian L Smith , Michael J Demetsky.Traffic Flow Forecasting:Comparison of Modelling Approaches [J] .Journal of Transportation Engineering , 1997 : 261 – 266.
[28] Mohammad M Hamed , Hashem R AlOmasaeid , Zahi MBani Said1ShortOterm Prediction of Traffic Volume in Urban Arterials [J] .Journal of Transportation Engineering , 1995 : 249 – 2541.
[29] Mascha Der Voort , Mark Doughert , Susan Watson.Combining Kohonen Maps with ARIMA Time Series Models to Forecast Traffic Flow [J] .Transportation Research , 1996 : 307 – 318.
[30] 宫晓燕,汤淑明.基于非参数回归的短时交通流量预测与事件检测综合算法[J].中国公路学报, 2003 (1) : 82 – 86.
[31] 朱中,杨兆升.实时交通流量人工神经网络预测模型[J]. 中国公路学报, 1998 (4) : 89 – 92.
[32] 邓自立,郭一新.动态系统分析及其运用——建模、滤波、预报、控制的新方法和程序库 沈阳: 辽宁科学出版社, 1985.
[33] Danech-Pajouh, M., Aron, M., 1991. ATHENA, a method for short-term inter-urban traffic forecasting. Report 177,INRETS, Arcueil, Paris.
[34] Kwon, J., Coifman, B., Bickel, P.J., 2000. Day-to-day travel time trends and travel time prediction from loop detector data. In:Transportation Research Record, 1717, 120–129.
[35] Nicholoson, H., Swann, C., 1974. The prediction of traffic flow volumes based on spectral analysis. Transportation Research 8, 533–538.
[36] Park, D., Rilett, L., 1998. Forecasting multiple-period freeway link travel times using modular neural networks. In Transportation Research Record. no. 1617. Transportation Research Board, pp. 163–170.
[37] David Boyce, Nagui Rouphail and Allan Kirson. Estimation and measurement of link travel time inthe ADVANCE project. IEEE vehicle Navigation and Information Systems Conference. Ottaw a-VN IS, 1993.
[38] A bours S. Estimation of travel time from occupancy on an urban network: an experiment in Paris.
[39] France. Second International Conference on Road Traffic Control, Institution of Engineers, London,U K. 1986.
[40] 吴万铎,吴万钊.模糊数学与计算机应用[M].北京电子工业出版社.1988.
[41] Dailey D J1A Statistical Algorithm for Estimating Speed from Single Loop Volume and Occupancy Measurements[J ] Transportation Research B ,1999 (33) :313 – 3221.
[42] Nam D H ,D R Drew1Traffic Dynamics : Method for Estimating Freeway Travel Times in Real Time From Flow Measurements[J ] Journal of Transportation Engineering ,1989 (122) :185 – 1911.
[43] 刘桂生,城市快速路系统规划设计[J ].城市道桥与防洪.2000(1):11.
[44] 杨兆升,城市交通流诱导系统理论与模型[M].人民交通出版社.2000.1.
[45] 贺仲雄,模糊数学及其应用[M].天津科学技术出版社.1983.1.
[46] 苏永云,晏克非,黄翔,朱培康.车辆导航系统的动态最优路径搜索算法研究.系统工程第 18 卷第 4 期.
[47] 杨兆升,李全喜.基于城市交通控制系统的动态车辆行驶路线选择的方法.公路交通科技 Vol 16 No 1.
[48] Eiichi Taniguchi,Hiroshi Shimamoto “Intelligent transportation system based dynamic vehicle routing and scheduling with variable travel times” Transportation Research Part C12, 235-250,2004.
[49] 陈壁峰,陆昊娟,黄樟灿.车辆导航系统的动态最优路径搜索模型及算法.武汉理工大学学报·信息与管理工程版,第 24 卷第 3 期 2002 年 6 月.
[50] 苏永云,晏克非,黄翔,朱培康.车辆导航系统的动态最优路径搜索方法研究.系统工程.2000 年 7 月.第 18 卷第 4 期.
[51] 美国交通研究委员会.道路通行能力手册[M].任福田,译.北京建筑工业出版社,1985.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |