吉林大学学报(工学版) ›› 2026, Vol. 56 ›› Issue (8): 2067-2076.doi: 10.13229/j.cnki.jdxbgxb.20250035

• 交通运输工程·土木工程 • 上一篇    

考虑多维属性的混合路网路径选择行为预测

王艳丽1(),王晨曦2,赵欣然1,吴兵1   

  1. 1.同济大学 交通学院,上海 201804
    2.湖北省智慧交通研究院有限公司 产业战略研究中心,武汉 430050
  • 收稿日期:2025-01-10 出版日期:2026-08-01 发布日期:2026-09-02
  • 作者简介:王艳丽(1985-),女,高级工程师,博士.研究方向:交通运输规划与管理.E-mail:wangyanli@tongji.edu.cn
  • 基金资助:
    国家自然科学基金面上项目(52172331)

Prediction of route selection behavior for mixed road network considering multi⁃class attributes

Yan-li WANG1(),Chen-xi WANG2,Xin-ran ZHAO1,Bing WU1   

  1. 1.College of Transportation,Tongji University,Shanghai 201804,China
    2.Industry Strategy Research Center,Hubei Intelligent Transportation Research Institute Co. ,Ltd,Wuhan 430050,China
  • Received:2025-01-10 Online:2026-08-01 Published:2026-09-02

摘要:

为探究大城市混合路网中路径利用不均衡的深层原因,采用行为(RP)与意向(SP)联合调查,系统收集了驾车出行者在混合路网中的出行特征及路径选择数据。结合多维路径属性和个人出行特征,基于随机后悔理论构建了路径选择模型,并引入尺度效应以提升模型的预测精度。结果表明,距离、红绿灯数量、过路费、历史平均时间、拥堵时的额外时间及其发生可能性等路径属性是路径选择的显著影响因素,个人出行频率和历史路径偏好对决策行为具有关键作用。改进后只考虑路径属性的模型中率为0.703,融入个人出行特征后模型中率提高到0.872,在拟合效果和预测能力上显著优于传统模型。本文研究结果可为城市交通精细化管理策略提供量化依据,也可为个性化导航服务的优化设计提供实用参考。

关键词: 交通运输规划与管理, 路径选择行为预测, 随机后悔最小化模型, 混合路网, 出行特征, 路线属性

Abstract:

To explore the underlying causes of uneven path utilization in urban mixed road networks, revealed preference (RP) and stated preference (SP) joint surveys were adopted to systematically collect data on drivers' attributes and path choices in urban mixed road networks. Path choice models based on random regret theory were developed, incorporating multidimensional path attributes and individual travel characteristics, with scale effects introduced to enhance predictive accuracy. The results show that path attributes such as distance, number of traffic lights, tolls, historical average travel time, additional time during congestion, and the likelihood of congestion significantly influence path selection. Personal travel frequency and historical path preferences also play critical roles in decision-making. The improved model considering path attributes achieves a hit rate of 0.703, and the improved model integrated drivers' attributes has a hit rate of 0.872, demonstrating superior fitting performance and predictive capability compared to traditional models. The study results provides a quantitative basis for refined urban traffic management strategies and practical insights for optimizing personalized navigation services.

Key words: transportation planning and management, route selection behavior prediction, stochastic regret minimization model, mixed road network, travel characteristics, route attributes

中图分类号: 

  • U491.2

图1

数据获取流程图"

表1

问卷设计"

类别问题类别问题
社会经济特征性别历史出行特征一周驾车出行频率
驾龄工作日日均驾车出行频率
年龄段周末日均驾车出行频率
家庭汽车总数节假日日均驾车出行频率
受教育程度出行目的
月均收入预估时间差异
家庭总人数历史单程出行距离
家庭年收入最近高/快速路出入口距离
高/快速路选择比例

图2

实际情景参考"

表2

场景路径属性水平"

属性类别距离/km道路类型红绿灯数量/个费用/元发生拥堵可能性/%路线历史平均时间/min发生拥堵时额外所需时间/min属性水平编号

属性

水平

20 km

以下

8.5高快速路+普通地面道路250204041
10普通地面道路330453292
12高快速路140703663

20 km

以上

20高快速路14104540151
22普通地面道路5007054102
30高快速路+普通地面道路2252045123

图3

问卷情景示例"

表3

问卷情景示例"

路线距离/km道路类型过路费/元红绿灯数量

发生拥堵

概率/%

路线历史平均

时间/min

发生拥堵时额外所需时间/min
120高快速路1014454015
222普通地面道路050705410
330高快速路+普通地面道路522204512

图4

数据描述性统计"

表4

数据编码情况"

属性列名编码情况变量形式
个体编号受访者编号个体标识
场景编号一个路径选择即为一个场景,共计48个场景场景标识
路径编号该条路径在场景中的编号,对应1、2、3路径标识
选择行为选择该条路径编码为1,否则为0选择标识
路径属性(共7列)道路类型(只包含高快速路则为1;包含高快速路和地面普通道路为2;只包含地面普通道路为3)、分类变量
距离、红绿灯数量、过路费、发生拥堵可能性、路线历史平均时间、发生拥堵时额外所需时间连续变量
社会经济特征(共8列)性别、驾龄、年龄段、家庭汽车总数、受教育程度、月均收入、家庭总人数、家庭年收入分类变量
历史出行特征(共9列)一周驾车出行频率、工作日日均驾车出行频率、周末日均驾车出行频率、节假期日均驾车出行频率、出行目的、时间预估差异、历史单程出行距离、与高/快速路出入口距离、高/快速路选择比例分类变量

表5

考虑路径属性时模型结果"

变量和评价指标RRM-CRRMMNL
系数p系数p系数p
距离-1.4060.2260.0260.4160.0350.666
高快速路-13.8390.000-0.4870.000-0.9670.278
高快速路和普通地面道路-6.2060.000-0.2440.006-0.4490.261
红绿灯数量-0.1620.239-0.0400.000-0.0740.250
过路费-96.9120.000-0.0320.459-0.0520.455
路线历史平均时间-8.1150.000-0.0150.174-0.0200.491
发生拥堵时额外所需时间-2.1500.000-0.0420.118-0.0660.170
发生拥堵可能性-0.2620.032-1.6130.000-2.3450.003
功率因数γ0.9590.000----
Mcfadden R20.2200.2160.189
去掉不显著变量后Mcfadden R20.2150.2060.188
HitR0.7030.4950.495
HitR10.7580.2420.242
HitR20.7970.7970.797
HitR30.5550.4450.445

表6

融入出行特征时群体的模型结果"

变量RRM-CRRMMNL
系数p系数p系数p
距离-0.3960.0000.7800.0001.1390.017
高快速路-4.0430.000-0.3020.000-0.5310.000
高快速路和普通地面道路-2.3690.000-0.0960.005-0.1640.056
红绿灯数量-4.3390.000-0.3790.000-0.6880.000
过路费-0.1530.000-0.0640.111-0.1070.112
路线历史平均时间×出行频率-1.1430.0000.0040.3500.0050.291
发生拥堵时额外所需时间-0.6690.000-0.0810.023-0.1180.003
发生拥堵可能性×高/快速路选择比例-0.5410.000-0.0110.886-0.0230.863
功率因数γ0.9890.000----
Mcfadden R20.2220.2010.173
去掉不显著变量后Mcfadden R20.2220.1950.178
HitR0.8720.6150.417
HitR10.8080.5940.192
HitR20.8740.6140.126
HitR30.9340.6370.934
[1] Zhai Ben, Wu Bing, Wang Yan-li, et al. Dist-ributed coordinated control of mixed expressway and urban roads: a sensitivity-based approach[J]. Journal of Intelligent Transportation Systems, 2025, 29(6): 579-592.
[2] Wang Yan-li, Wang Chen-xi, Wu Bing.Analysis of factors influencing travelers' route choice for expr-essway and urban ordinary road[C]∥Proceedings of the 2024 International Conference on Intelligent Driv-ing and Smart Transportation, Guangzhou, China, 2024: 56-62.
[3] 唐歆琳,黄锦锋.基于SEM的客车出行者出行路径选择行为研究[J].交通工程, 2023, 23(4): 83-87, 93.
Tang Xin-lin, Huang Jin-feng. Study on travel route choice behaviour of passenger drivers based on SEM[J]. Journal of Transportation Engineering, 2023, 23(4): 83-87, 93.
[4] 徐媛,刘凯,卢珂.后悔视角下考虑出行者路径熟悉度的交通流分配模型[J].系统管理学报, 2024, 33(4): 1471-1482.
Xu Yuan, Liu Kai, Lu Ke. A traffic assignment mod-elbased on regret perspective considering travellers' route familiarities[J]. Journal of Systems & Man-agement, 2024, 33(4): 1471-1482.
[5] Ahmad F, Alfagih L, Hess S, et al. Travel behaviour and game theory: a review of route choice modeling behaviour[J]. Journal of Choice Modelling, 2024, 50: No.100472.
[6] de Palma A, Picard N. Route choice decision under travel time uncertainty[J]. Transportation Research Part A: Policy and Practice, 2005, 39(4):295-324.
[7] Ben-Elia E, Avineri E. Response to travel information: a behavioural review[J]. Transport Reviews, 2015, 35(3): 352-377.
[8] Hensher D A, Rose J M, Greene W H. Applied Choice Analysis: a Primer[M]. Cambridge: Cambridge University Press, 2005.
[9] Samal S R, Mohanty M, Gorzelańczyk P. Exploring lane changing dynamics: a comprehensive review of modeling approaches, traffic impacts, and future directions in traffic engineering research[J]. Transactions on Transport Sciences, 2024, 15(2): 54-68.
[10] Simon H A. Models of Man: Social and Rational: Mathematical Essays on Rational Human Behavior in a Social Setting[M]. New York: Wiley, 1957.
[11] Hocine A, Kouaissah N, Lozza S O, et al. Modelling de-novo programming within Simon's satisficing theory: methods and application in designing an optimal offshore wind farm location system[J]. European Journal of Operational Research, 2024, 315(1): 289-306.
[12] Mahmassani H S, Chang G L. On boundedly rational user equilibrium in transportation systems[J]. Transportation Science, 1987, 21(2): 89-99.
[13] 凃强, 程琳, 林芬, 等. 考虑出行者风险态度的最优路径搜索[J]. 吉林大学学报: 工学版, 2019, 49(3): 720-726.
Tu Qiang, Cheng Lin, Lin Fen, et al. Finding shortest path considering traveler's risk attitude[J]. Journal of Jilin University (Engineering and Technology Edition), 2019, 49(3): 720-726.
[14] Chorus C G, Arentze T A, Timmermans H J P. A random regret-minimization model of travel choice[J]. Transportation Research Part B: Methodological, 2008, 42(1): 1-18.
[15] Belgiawan P F, Dubernet I, Schmid B, et al. Context-dependent models (CRRM, MuRRM, PRRM, RAM) versus a context-free model (MNL) in transportation studies: a comprehensive comparisons for Swiss and German SP and RP data sets[J]. Transportmetrica A: Transport Science, 2019, 15(2): 1487-1521.
[16] Li Meng-jie, Chen Fu-jian, Lin Qin-ze. Random regret minimization model for variable destination-orie-nted path planning[J]. IEEE Access, 2020, 8: 163646-163659.
[17] Zhu Min-qing, Shi Peng, Cui Hong-jun, et al. Modeling the traveler's route choice behavior under unexpected accidents[J]. Journal of Advanced Transportation, 2023(1): 1-10.
[18] Chorus C G. A new model of random regret minimization[J]. European Journal of Transport and Infrastructure Research, 2010, 10(2): 182-196.
[19] Guilford J P. A generalized psychophysical law[J]. Psychological Review, 1932, 39(1): 73-85.
[1] 谢坤,董宏辉,卢玲玉,耿庆桥,李鹏辉,董春娇. 基于CFSFDP-BP的车辆出行群体分类及识别方法[J]. 吉林大学学报(工学版), 2026, 56(3): 725-733.
[2] 刘康琳,张泽宇,蒋婧雯,宫洵,陈垚. 基于分布鲁棒优化的无人机配送设施选址分配问题[J]. 吉林大学学报(工学版), 2026, 56(2): 464-472.
[3] 张毅,陈莎雯,陈艳,范翔宇,王思祺,吴欢,焦鹏飞. 高速公路机电设备动态运维评价及预测性维护[J]. 吉林大学学报(工学版), 2026, 56(1): 170-182.
[4] 孙峣,白东轩,姚宝珍,白子建. 基于渗流理论的港城交通网络特征分析[J]. 吉林大学学报(工学版), 2026, 56(1): 199-208.
[5] 贾洪飞,庄博,罗清玉,刘玲,黄秋阳. 积水条件下城市路网性能恢复决策优化[J]. 吉林大学学报(工学版), 2025, 55(9): 2969-2977.
[6] 王东,李宇暄,吴欢,宗芳. 基于随机森林的智能网联汽车开放测试道路评级算法[J]. 吉林大学学报(工学版), 2025, 55(9): 2998-3006.
[7] 徐慧智,郝东升,徐小婷,蒋时森. 基于深度学习的高速公路小目标检测算法[J]. 吉林大学学报(工学版), 2025, 55(6): 2003-2014.
[8] 何庆龄,裴玉龙,侯琳,刘静,潘胜. 混合策略改进WOA-BiLSTM的快速路出口匝道车速预测[J]. 吉林大学学报(工学版), 2025, 55(6): 2038-2049.
[9] 吴文静,邓淳淳,贾洪飞,孙舒航. 内涝影响下路网畅通可靠度评估及关键路段识别[J]. 吉林大学学报(工学版), 2025, 55(4): 1250-1257.
[10] 岳昊,常笑,刘建业,曲秋莳. 引入车辆窗的定制公交线路优化[J]. 吉林大学学报(工学版), 2025, 55(4): 1266-1274.
[11] 孟祥海,王国锐,张明扬,田毕江. 基于选择集成的山区高速事故预测模型[J]. 吉林大学学报(工学版), 2025, 55(4): 1298-1306.
[12] 高天洋,胡大伟,姜瑞森,吴雪,刘慧甜. 基于模块化车辆的区域灵活接驳公交线路优化[J]. 吉林大学学报(工学版), 2025, 55(2): 537-545.
[13] 李昱燃,汪飞,朱才华,韩飞,李岩. 污染天气居民通勤模式选择影响因素的链式效用[J]. 吉林大学学报(工学版), 2025, 55(2): 577-590.
[14] 马书红,张俊杰,陈西芳,廖国美. 利用出租车时序数据识别城市功能区[J]. 吉林大学学报(工学版), 2025, 55(2): 603-613.
[15] 曲大义,戴守晨,陈意成,崔善柠,杨宇翔. 基于轨迹数据的车辆博弈切出及汇入行为建模[J]. 吉林大学学报(工学版), 2025, 55(10): 3208-3220.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!