机器学习—动力学耦合车辆跟驰模型

交通运输系统工程与信息 ›› 2017, Vol. 17 ›› Issue (6): 33-39.

• 智能交通系统与信息技术 • 上一篇下一篇

机器学习—动力学耦合车辆跟驰模型

丁点点*^{1, 2}，孙磊^{1, 2}，陈松^{1, 2}

1. 宿州学院资源与土木工程学院，安徽宿州234000；2.安徽省煤矿勘探工程技术中心，安徽宿州234000

收稿日期:2017-04-24 修回日期:2017-09-17 出版日期:2017-12-25 发布日期:2017-12-25
作者简介:丁点点（1989-），男，安徽淮北人，讲师，博士生.
基金资助:
安徽省自然科学基金青年项目/ Natural Science Foundation of Anhui Provincial-Youth Project (17080885QE125)；宿州学院教授（博士）科研启动基金/Suzhou University Professor (PhD) Research Start Foundation (2016jb05).

A Car-following Model Coupling Machine Learning and Dynamic

DING Dian-dian^{1, 2}, SUN Lei ^{1, 2}, CHEN Song^{1, 2}

1. School of Resources and Civil Engineering, Suzhou University, Suzhou 234000, Anhui, China; 2. Coal Mine Exploration Engineering Center of Anhui Province, Suzhou 234000, Anhui, China

Received:2017-04-24 Revised:2017-09-17 Online:2017-12-25 Published:2017-12-25

摘要/Abstract

摘要：

目前，跟驰模型的建立主要基于动力学方法和机器学习算法，将两者耦合起来建立跟驰模型的研究还没有.以线性组合预测为基础，对最优加权法中的目标函数进行改进，将经典的Gipps 模型和基于BP 神经网络的跟驰模型(BP Car-following Model, BP)耦合起来，建立线性组合车辆跟驰模型(Linear Combination Car-following Model, LC-CF).结果表明：BP 模型的预测结果更加贴近真实值，Gipps 模型的预测结果更加贴近安全值； LC-CF模型可以通过调整参数，来控制BP模型和Gipps 模型在LC-CF模型中的权重，进而达到控制预测速度的真实性和安全性的目的.

关键词: 智能交通, 道路运输, 线性组合预测, 动力学模型, BP神经网络, 车辆跟驰

Abstract:

So far, the car- following model is mostly built by dynamic and machine learning algorithms, there remains no researches on the building of car- following model by coupling the two methods. On the basis of the linear combination forecast, this paper improves the objective function of the optimal weighting method and coupled the Gipps model and BP model based on back propagation neural network to establish the linear combination car- following model (LC- CF). The results show that the speed forecasted by BP model peforms better in accuracy and the speed forecasted by the Gipps model peforms better in security. LCCF model can achieve the purpose of controlling the accuracy and security of the speed forecasting by adjusting the parameters and controlling the weight of BP model and Gipps model in the LC-CF model.

Key words: intelligent transportation, road transportation, linear combination forecasting, dynamic model, BP-neural network, car-following

中图分类号:

U491.2

丁点点，孙磊，陈松. 机器学习—动力学耦合车辆跟驰模型[J]. 交通运输系统工程与信息, 2017, 17(6): 33-39.

DING Dian-dian, SUN Lei, CHEN Song. A Car-following Model Coupling Machine Learning and Dynamic[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(6): 33-39.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract19517.shtml

http://www.tseit.org.cn/CN/Y2017/V17/I6/33

参考文献

[1] GAZIS D C, HERMAN R, ROTHERY R W. Nonlinear follow-the-leader models of traffic flow[J]. Operations Research, 1961, 9(4): 545-567.

[2] GIPPS P G. A behavioural car- following model for computer simulation[J]. Transportation Research Part B: Methodological, 1981, 15(2): 105-111.

[3] WIEDEMANN R. Simulation of road traffic in traffic flow[J]. University of Karlsruhe, 1974, 3(4): 1387-1395.

[4] 贾洪飞, 隽志才, 王晓原. 基于神经网络的车辆跟驰模型的建立[J]. 公路交通科技, 2001, 18(4): 92-94. [JIA H F, JUAN Z C, WANG X Y. Development of a Carfollowing model based on artificial neural networks[J]. Journalof Highwayand Transportation Researchand Development, 2001, 18(4): 92-94.]

[5] SIMONELLI F, BIFULCO G N, DE MARTINIS V, et al. Human-like adaptive cruise control systems through a learning machine approa- ch[M]//Applications of Soft Computing. Springer Berlin Heidelberg, 2009: 240-249.

[6] 王晓原, 张敬磊, 孟昭为. 微观交通流仿真跟车行为 ANN 模型研究[J]. 山东理工大学学报(自然科学版), 2004, 18(4): 1-6. [WANG X Y, ZHANG J L, MENG Z W. Artificial neural network (ANN) model for carfollowing simulation of microscopic traffic flow[J]. Journal of Shandong University of Technology (Science & Technology), 2004, 18(4): 1-6.]

[7] KHODAYARI A, GHAFFARI A, KAZEMI R, et al. A modified car-following model based on a neural network model of the human driver effects[J]. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 2012, 42(6): 1440-1449.

[8] COLOMBARONI C, FUSCO G. Artificial neural network models for car following: experimental analysis and calibration issues[J]. Journal of Intelligent Transportation Systems, 2014, 18(1): 5-16.

[9] GUIZZO E. How google’s self-driving car works[J]. IEEE Spectrum Online, October, 2011, 18(7): 1132- 1141.

[10] MARKOFF J. Google cars drive themselves in traffic[J]. The New York Times, 2010, 10(A1): 9.

[11] 谷歌公布无人驾驶车事故细节[OL], (2016-3-16) [2017- 4- 20]. http: // auto. sohu. com/ 20160316 / n440632416.shtml. [Google released unmanned car accident details [OL], (2016-3-16) [2017-4-20]. http:// auto.sohu.com/20160316/n440632416.shtml.]

[12] BATES J M, GRANGER C W J. The combination of forecasts[J]. OR, 1969: 451-468.

[13] 钱超, 许宏科, 徐娜. 高速公路交通量组合预测模型研究[J]. 计算机仿真, 2013 (4): 178-182. [QIAN C , XU H K, XU N. Study on combination prediction model of highway traffic[J]. Computer Simulation, 2013 (4): 178- 182.]

[14] 郑为中, 史其信. 基于贝叶斯组合模型的短期交通量预测研究[J]. 中国公路学报, 2005, 18(1): 85- 89. [ZHENG W Z, SHI Q X. Study of short term freeway traffic flow prediction based on BAYESIAN combined model [J]. China Journal of Highway and Transport, 2005, 18(1): 85-89.]

[15] 王建, 邓卫, 赵金宝. 基于改进型贝叶斯组合模型的短时交通流量预测[J]. 东南大学学报: 自然科学版, 2012, 42(1): 162-167. [WANG J , DENG W, ZHAO J B. Short-term freeway traffic flow prediction based on improved Bayesian combined model[J]. Journal of Southeast University (Natural Science Edition), 2012, 42 (1): 162-167.]

[16] 赵玲, 许宏科, 程鸿亮. 基于最优加权组合模型的道路交通事故预测[J]. 计算机工程与应用, 2013, 49(24): 81-89. [ZHAO L, XU H K, CHENG H L. Road traffic accidents prediction based on optimal weighted combined model[J]. Computer Engineering and Applications, 2013, 49(24): 81-89.]

[17] 邱小平, 刘亚龙. 基于支持向量机的车辆跟驰模型[J]. 重庆交通大学学报(自然科学版), 2015, 34(6): 128- 132. [QIU X P，LIU Y L. A car-following model based on support vector machine[J]. Journal of Chongqing Jiaotong University(Natural Science), 2015, 34(6): 128- 132.]

[18] GIPPS P G. A behavioral car- following model for computer simulation[J]. Transportation Research Part B: Methodological, 1981, 15(2): 105-111.

[19] 邱小平, 李娜. 基于最小二乘支持向量机的车辆跟驰行为模型[J]. 山东交通学院学报, 2016, 24(4): 52-57. [QIU X P，LI N. A car-following model based on Least squares support vector machine [J]. Journal of Shandong Jiaotong University, 2016, 24(4): 52-57.]

[20] K?RKOVÁ V. Kolmogorov's theorem and multilayer neural networks[J]. Neural Networks, 1992, 5(3): 501- 506.

[21] HAGAN M T, DEMUTH H B, BEALE M H, et al. Neural network design[M]. Boston: PWS Publishing company, 1996.

[22] 杨达, 蒲云, 杨飞, 等. 基于最优间距的车辆跟驰模型及其特性[J]. 西南交通大学学报, 2012, 47(5): 888- 894. [YANG D, PU Y, YANG F, et al. Car-following model based on optimal distance and its characteristics analysis[J]. Journal of Southwest Jiaotong University, 2012, 47(5): 888-894.]

[23] PUNZO V, SIMONELLI F. Analysis and comparison of microscopic traffic flow models with real traffic microscopic data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2005 (1934): 53-63.

[24] BROCKFELD E, KÜHNE R, WAGNER P. Calibration and validation of microscopic models of traffic flow[J]. Transportation Research Record: Journal of the Transportation Research Board, 2005 (1934): 179-187.

[25] 邱小平, 刘亚龙, 马丽娜, 等. 基于贝叶斯网络的车辆换道模型[J]. 交通运输系统工程与信息, 2015, 15(5): 67- 73. [QIU X P，LIU Y L，MA L N, et al. A lane change model based on Bayesian networks[J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(5): 67-73.]

机器学习—动力学耦合车辆跟驰模型

A Car-following Model Coupling Machine Learning and Dynamic

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	郭烈, 胥林立, 秦增科, 王旭. 自动驾驶接管影响因素分析与研究进展[J]. 交通运输系统工程与信息, 2022, 22(2): 72-90.
[2]	徐猛, 刘涛, 钟绍鹏, 姜宇. 城市智慧公交研究综述与展望[J]. 交通运输系统工程与信息, 2022, 22(2): 91-108.
[3]	程君, 张立炎, 陈启宏. 一种基于地图辅助的自动驾驶视-惯融合定位方法[J]. 交通运输系统工程与信息, 2022, 22(2): 117-126.
[4]	王国栋, 刘立, 孟宇, 马智萍, 郑淏清, 顾青, 白国星. 一体式车辆避撞轨迹规划与跟踪控制[J]. 交通运输系统工程与信息, 2022, 22(2): 127-136.
[5]	马东方, 陈曦, 吴晓东, 金盛. 基于强化学习的干线信号混合协同优化方法[J]. 交通运输系统工程与信息, 2022, 22(2): 145-153.
[6]	许波桅, 王玲玲, 李军军. 自动化码头多级作业超网络延误传导特性研究[J]. 交通运输系统工程与信息, 2022, 22(2): 280-289.
[7]	张英贵, 肖杨, 雷定猷, 陆强. 长大货物多式联运网络风险传播动力学仿真[J]. 交通运输系统工程与信息, 2022, 22(1): 14-23.
[8]	田会娟, 刘嘉伟, 翟佳豪, 邓琳琳. 基于多入侵线的视频车速检测方法[J]. 交通运输系统工程与信息, 2022, 22(1): 49-56.
[9]	贾彦峰, 曲大义, 赵梓旭, 王韬, 宋慧. 基于安全势场的网联自主车辆跟驰行为决策及模型[J]. 交通运输系统工程与信息, 2022, 22(1): 85-97.
[10]	刘文, 汪文博. 基于秩最小化矩阵去噪的船舶轨迹重构方法[J]. 交通运输系统工程与信息, 2022, 22(1): 106-114.
[11]	赵建东, 陈溱, 焦彦利, 张凯丽, 韩明敏. 重点营运车辆的异常驾驶行为识别研究[J]. 交通运输系统工程与信息, 2022, 22(1): 282-291.
[12]	徐东伟, 彭航, 商学天, 魏臣臣, 杨艳芳. 基于图自编码-生成对抗网络的路网数据修复[J]. 交通运输系统工程与信息, 2021, 21(6): 33-41.
[13]	游峰, 梁健中, 曹水金, 肖智豪, 吴镇江, 王海玮. 面向多目标跟踪的密集行人群轨迹提取和运动语义感知[J]. 交通运输系统工程与信息, 2021, 21(6): 42-54.
[14]	王福建, 俞佳浩, 赵锦焕, 梅振宇. 基于站点实时关联度的短时公交客流预测方法[J]. 交通运输系统工程与信息, 2021, 21(6): 131-144.
[15]	张毅, 姚丹亚, 李力, 裴华鑫, 晏松, 葛经纬. 智能车路协同系统关键技术与应用[J]. 交通运输系统工程与信息, 2021, 21(5): 40-51.