网约车协同服务下综合客运枢纽定制公交接驳线路优化方法

程龙; 王宇轩; 肖光涵; 张明业; 杨敏

doi:10.19818/j.cnki.1671-1637.2026.146

网约车协同服务下综合客运枢纽定制公交接驳线路优化方法

doi: 10.19818/j.cnki.1671-1637.2026.146

程龙^{1, 2,},
王宇轩¹,
肖光涵¹,
张明业¹,
杨敏^{1, 2, ,}

1.
东南大学江苏省城市智能交通江苏省重点实验室，江苏南京 210096
2.
综合交通运输理论交通运输行业重点实验室(南京现代综合交通实验室)，江苏南京 211135

基金项目:

国家自然科学基金重点项目 52432011

国家自然科学基金面上项目 52372301

国家自然科学基金青年学生基础研究项目 524B2153

详细信息

作者简介:
程龙(1989-)，男，安徽淮北人，东南大学副研究员，工学博士，E-mail：longcheng@seu.edu.cn

通讯作者:
杨敏(1981-)，男，安徽池州人，东南大学教授，工学博士，E-mail：yangmin@seu.edu.cn

中图分类号: U121
计量
- 文章访问数: 8
- HTML全文浏览量: 3
- PDF下载量: 1
- 被引次数: 0
出版历程
- 收稿日期: 2025-07-31
- 录用日期: 2026-01-04
- 修回日期: 2025-12-30
- 刊出日期: 2026-02-28

Optimization method of customized bus feeder routes at comprehensive transport hubs under ride-hailing collaboration

CHENG Long^{1, 2
,},
WANG Yu-xuan¹,
XIAO Guang-han¹,
ZHANG Ming-ye¹,
YANG Min^{1, 2
, ,}

1.
Jiangsu Key Laboratory of Urban ITS, Southeast University, Nanjing 210096, Jiangsu, China
2.
Key Laboratory of Transport Industry of Comprehensive Transportation Theory (Nanjing Modern Multimodal Transportation Laboratory), Nanjing 211135, Jiangsu, China

Funds:

Key Program of National Natural Science Foundation of China 52432011

General Program of National Natural Science Foundation of China 52372301

Youth Student Basic Research Project of National Natural Science Foundation of China 524B2153

More Information

Corresponding author: YANG Min, professor, PhD, E-mail: yangmin@seu.edu.cn

Article Text (Baidu Translation)

摘要

摘要: 提出了网约车协同的综合客运枢纽定制公交接驳服务模式，研究了定制公交、网约车及旅客三方协同下的综合系统成本最小化问题，考虑旅客接驳出行需求分布、公交线路空间连通性、时间调度、客流分配及步行可达性等影响因素，建立了网约车协同服务下的定制公交接驳线路优化模型；提出了基于大邻域搜索的嵌入式优化算法，将混合整数线性规划模型嵌入大邻域搜索框架中，通过扰动-修复-精确优化的三步策略，实现对定制公交接驳线路的全局优化；开展了以南京禄口国际机场为例的实证研究，系统评估了协同服务模式与单一模式下的成本及运营效果。研究结果表明：所提模型能够有效满足旅客主要接驳出行需求并显著降低接驳系统总成本，优化后的接驳系统总成本较单一网约车模式和单一定制公交模式分别下降40.7%和18.8%；敏感性分析显示，定制公交运营速度的提升相较于网约车对系统总成本的影响更为显著，系统总成本对网约车票价变动的敏感性略高于定制公交票价，旅客出行成本是影响系统总成本变化的主要因素，在旅客可接受步行距离为700 m时，系统总成本最低。算法对比结果表明，基于大邻域搜索的嵌入式优化算法在迭代次数和求解结果上均优于遗传、模拟退火、蚁群和传统大邻域搜索算法，相较于上述算法，嵌入式优化算法能使系统总成本进一步降低9.6%~12.6%。
- 定制公交 /
- 枢纽接驳出行 /
- 网约车协同 /
- 线路优化 /
- 规划模型 /
- 大邻域搜索
Abstract: A ride-hailing coordinated customized bus feeder service mode for comprehensive passenger transport hubs was proposed. The minimization problem of total system cost under the coordination of customized buses, ride-hailing services, and passengers was studied. Influencing factors including the distribution of passenger feeder travel demand, spatial connectivity of bus routes, time scheduling, passenger flow assignment, and walking accessibility were considered. An optimization model for customized bus feeder routes under ride-hailing collaboration was established. An embedded optimization algorithm based on large neighborhood search was proposed. The mixed-integer linear programming model was embedded into the large neighborhood search framework. Global optimization of customized bus feeder routes was achieved through a three-step strategy consisting of perturbation, repair, and exact optimization. An empirical study was conducted with Nanjing Lukou International Airport as a case. The costs and operational performance under the coordinated service mode and single service modes were systematically evaluated. The results show that the proposed model can effectively satisfy passengers' main feeder travel demand and significantly reduce the total cost of the feeder system. Compared with the single ride-hailing mode and the single customized bus mode, the optimized total cost of the feeder system decreases by 40.7% and 18.8%, respectively. Sensitivity analysis shows that the improvement of customized bus operating speed has a more significant impact on the total system cost than ride-hailing speed. The total system cost shows slightly higher sensitivity to changes in ride-hailing fare than to customized bus fares. Passenger travel cost is the main factor influencing changes in total system cost. When the acceptable walking distance for passengers is 700 m, the total system cost reaches the minimum value. Algorithm comparison results indicate that the embedded optimization algorithm based on large neighborhood search is superior to genetic algorithms, simulated annealing algorithms, ant colony algorithms, and traditional large neighborhood search algorithms in both the number of iterations and solution quality. The embedded optimization algorithm further reduces the total system cost by 9.6% to 12.6%.
- customized bus /
- hub feeder travel /
- ride-hailing collaboration /
- route optimization /
- planning model /
- large neighborhood search

HTML全文

图 1 网约车协同的定制公交接驳服务

Figure 1. Customized bus feeder service coordinated with ride-hailing

下载: 全尺寸图片幻灯片

图 2 机场到达客流目的地空间聚类分布

Figure 2. Spatial clustering distribution of airport arrival passenger destinations

下载: 全尺寸图片幻灯片

图 3 K值-SSE曲线

Figure 3. K value-SSE curve

下载: 全尺寸图片幻灯片

图 4 定制公交备选站点分布

Figure 4. Distributions of candidate customized bus stops

下载: 全尺寸图片幻灯片

图 5 统计结果与线路可视化

Figure 5. Statistical results and route visualization

下载: 全尺寸图片幻灯片

图 6 算法迭代曲线

Figure 6. Algorithm iteration curve

下载: 全尺寸图片幻灯片

图 7 关键参数敏感性分析

Figure 7. Sensitivity analysis of key parameters

下载: 全尺寸图片幻灯片

图 8 不同算法迭代曲线

Figure 8. Iteration curves of different algorithms

下载: 全尺寸图片幻灯片

表 1 网约车订单数据格式

Table 1. Format of ride-hailing order data

字段名称	字段含义
ID	订单编号
pas_arr_time	行程开始时间
arr_time	行程结束时间
dest_lat	目的地纬度
dest_lng	目的地经度
origin_lat	出发地纬度
origin_lng	出发地经度

下载: 导出CSV

表 2 部分站点间距离

Table 2. Distances between some stations km

站点	1	2	3	4	5	…	24	25
1	0.00	27.16	42.22	42.45	19.77	…	39.60	38.89
2	27.16	0.00	17.80	16.99	7.39	…	12.48	16.30
3	42.22	17.80	0.00	20.96	23.87	…	12.95	25.39
4	42.45	16.99	20.96	0.00	23.54	…	8.24	6.42
5	19.77	7.39	23.87	23.54	0.00	…	19.84	21.41
…	…	…	…	…	…	…	…	…
24	39.60	12.48	12.95	8.24	19.84	…	0.00	12.53
25	38.89	16.30	25.39	6.42	21.41	…	12.53	0.00

下载: 导出CSV

表 3 定制公交各线路站点信息

Table 3. Stops information of each customized bus route

线路	站点顺序	站点	下车人数	到站后至目的地平均接驳距离/(km·人^-1)	到站后至目的地平均打车费用/(元·人^-1)
1	1→18→2→7	18	3	59.9	327.7
		2	130	1.3	19.1
		7	26	2.0	10.9
2	1→6→3	6	121	3.3	18.2
2	1→6→3	3	41	4.9	26.7
3	1→21→25→4→24	21	18	2.8	15.3
		25	72	4.7	25.9
		4	21	6.0	33.0
		24	70	3.8	20.7

下载: 导出CSV

表 4 定制公交各线路成本信息

Table 4. Cost information of each customized bus route 元

线路	定制公交运营成本	网约车运营成本	旅客出行时间成本	旅客出行经济成本	接驳系统总成本
1→18→2→7	285.3	650.3	5 343.3	2 141.9	8 420.8
1→6→3	393.2	1 301.3	5 942.4	3 161.7	10 798.6
1→21→25→4→24	404.4	1 689.0	7 716.7	3 893.0	13 703.0
各部分总成本/元	1 082.8	3 640.6	19 002.4	9 196.6	32 922.4

下载: 导出CSV

表 5 三种出行模式下的成本/收益对比

Table 5. Cost/benefit comparison of three travel modes 元

指标		单一网约车服务	单一定制公交服务	定制公交与网约车协同服务
旅客	时间成本	7 120.8	35 040.6	19 002.4
旅客	经济成本	26 827.2	3 614.4	9 196.6
定制公交	运营成本		1 874.7	1 082.8
定制公交	运营收益		3 614.4	3 602.2
网约车	运营成本	21 578.4		3 640.6
网约车	运营收益	26 827.2		5 594.4
接驳系统	运营总成本	55 526.4	40 529.7	32 922.4

下载: 导出CSV

表 6 算法求解结果对比表

Table 6. Comparison of algorithmic solution results

算法	定制公交运营成本/元	网约车运营成本/元	旅客出行成本/元	系统总成本/元	优化比例/%
遗传算法	480.0	4 358.7	34 041.0	38 879.7	30.0
模拟退火算法	449.1	4 837.3	34 631.8	39 918.2	28.1
蚁群优化算法	557.2	4 268.5	33 966.6	38 792.3	30.1
大邻域搜索算法	495.6	4 126.3	33 639.1	38 261.0	31.1
LNS-MILP算法(本研究)	1 082.8	3 640.6	28 119.0	32 922.4	40.7

下载: 导出CSV

参考文献(48)

[1]	SOGBE E, SUSILAWATI S, CURRIE G, et al. Exploring factors influencing first-mile and last-mile connections to public transport from car users' perspective: Evidence from Greater Accra, Ghana[J]. Journal of Transport Geography, 2025, 126: 104240. doi: 10.1016/j.jtrangeo.2025.104240
[2]	徐康明, 李佳玲, 冯浚, 等. 定制公交服务初探[J]. 城市交通, 2013, 11(5): 24-27. XU Kang-ming, LI Jia-ling, FENG Jun, et al. Discussion on subscription bus services[J]. Urban Transport of China, 2013, 11(5): 24-27.
[3]	马昌喜, 郝威, 沈金星, 等. 定制公交线路优化综述[J]. 交通运输工程学报, 2021, 21(5): 30-41. MA Chang-xi, HAO Wei, SHEN Jin-xing, et al. Review on customized bus route optimization[J]. Journal of Traffic and Transportation Engineering, 2021, 21(5): 30-41.
[4]	WANG Y T, HU Z Q, HUANG H, et al. Optimization for customized bus stop planning, order schedule, and routing design in on-demand urban mobility[J]. IEEE Internet of Things Journal, 2024, 11(6): 10239-10251. doi: 10.1109/JIOT.2023.3326486
[5]	CHEN X, WANG Y H, MA X L. Integrated optimization for commuting customized bus stop planning, routing design, and timetable development with passenger spatial-temporal accessibility[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(4): 2060-2075. doi: 10.1109/TITS.2020.3048520
[6]	ZHEN L, HE X T, WANG S A, et al. Vehicle routing for customized on-demand bus services[J]. IISE Transactions, 2023, 55(12): 1277-1294. doi: 10.1080/24725854.2023.2179139
[7]	GUO H N, WANG Y, SHANG P, et al. Customised bus route design with passenger-to-station assignment optimisation[J]. Transportmetrica A: Transport Science, 2024, 20(3): 2214631. doi: 10.1080/23249935.2023.2214631
[8]	李欣, 乔靖元, 李炎皓, 等. 环形放射状城市常规与需求响应公交联合优化研究[J]. 交通运输系统工程与信息, 2023, 23(4): 155-163. LI Xin, QIAO Jing-yuan, LI Yan-hao, et al. Joint optimization of conventional transit and demand responsive transit for ring-radial cities[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(4): 155-163.
[9]	HAN S, FU H, YAN K H, et al. Optimizing customized bus routes with integrated passenger guidance under stochastic travel times[J]. Expert Systems with Applications, 2026, 297: 129480. doi: 10.1016/j.eswa.2025.129480
[10]	YU H T, LV W F, LIU H G, et al. A dynamic line generation and vehicle scheduling method for airport bus line based on multi-source big travel data[J]. Soft Computing, 2020, 24(9): 6329-6344. doi: 10.1007/s00500-019-03987-4
[11]	WU P, WANG Q, BOSI T, et al. Joint optimization of multi-trip vehicle scheduling, passenger assignment, and timetable for on-demand customized bus services[J]. Transportation Research Part C: Emerging Technologies, 2025, 180: 105346. doi: 10.1016/j.trc.2025.105346
[12]	马昌喜, 王超, 郝威, 等. 突发公共卫生事件下应急定制公交线路优化[J]. 交通运输工程学报, 2020, 20(3): 89-99. MA Chang-xi, WANG Chao, HAO Wei, et al. Emergency customized bus route optimization under public health emergencies[J]. Journal of Traffic and Transportation Engineering, 2020, 20(3): 89-99.
[13]	许航, 李欣, 袁昀. 共享单车与需求响应公交耦合优化研究[J]. 华南理工大学学报(自然科学版), 2025, 53(8): 20-28. XU Hang, LI Xin, YUAN Yun. Research on the joint optimization of shared bikes and demand-responsive connector[J]. Journal of South China University of Technology (Natural Science Edition), 2025, 53(8): 20-28.
[14]	GUO Y H, AN K, MA W J. Customized bus routing problem considering co-opetition with taxis at transport hubs[J]. Transportation Research Part E: Logistics and Transportation Review, 2026, 205(C): 104502.
[15]	朱昌锋, 安醇, 唐兆鑫, 等. 基于时空网络的城际公交化列车开行方案优化[J]. 交通运输工程学报, 2025, 25(6): 157-168. doi: 10.19818/j.cnki.1671-1637.2025.06.014 ZHU Chang-feng, AN Chun, TANG Zhao-xin, et al. Optimization of intercity public transportation train operation plan based on spatio-temporal network[J]. Journal of Traffic and Transportation Engineering, 2025, 25(6): 157-168. doi: 10.19818/j.cnki.1671-1637.2025.06.014
[16]	LI Y H, LI X, QIAO J Y, et al. Optimal design of bimodal hierarchical transit systems: Tradeoffs between costs and CO₂ emissions[J]. Research in Transportation Economics, 2025, 109: 101496. doi: 10.1016/j.retrec.2024.101496
[17]	LI X, LI Y H, LIU W Y, et al. Optimal design of pure battery electric bus system on the grid network[J]. Transportmetrica A: Transport Science, 2024, 20(2): 2152298. doi: 10.1080/23249935.2022.2152298
[18]	DOU X P, MENG Q, LIU K. Customized bus service design for uncertain commuting travel demand[J]. Transportmetrica A: Transport Science, 2021, 17(4): 1405-1430. doi: 10.1080/23249935.2020.1864509
[19]	RIST Y, FORBES M A. A new formulation for the dial-a-ride problem[J]. Transportation Science, 2021, 55(5): 1113-1135. doi: 10.1287/trsc.2021.1044
[20]	SCHULZ A, PFEIFFER C. A branch-and-cut algorithm for the dial-a-ride problem with incompatible customer types[J]. Transportation Research Part E: Logistics and Transportation Review, 2024, 181: 103394. doi: 10.1016/j.tre.2023.103394
[21]	SCHULZ A, PFEIFFER C. Using fixed paths to improve branch-and-cut algorithms for precedence-constrained routing problems[J]. European Journal of Operational Research, 2024, 312(2): 456-472. doi: 10.1016/j.ejor.2023.07.002
[22]	XU X F, WANG C L, ZHOU P. GVRP considered oil-gas recovery in refined oil distribution: From an environmental perspective[J]. International Journal of Production Economics, 2021, 235: 108078. doi: 10.1016/j.ijpe.2021.108078
[23]	GALARZA MONTENEGRO B D, SÖRENSEN K, VANSTEENWEGEN P. A large neighborhood search algorithm to optimize a demand-responsive feeder service[J]. Transportation Research Part C: Emerging Technologies, 2021, 127: 103102. doi: 10.1016/j.trc.2021.103102
[24]	ASGHARI M, AL-E-HASHEM S M J M, REKIK Y. Environmental and social implications of incorporating carpooling service on a customized bus system[J]. Computers & Operations Research, 2022, 142: 105724.
[25]	李岩, 史旋, 南斯睿, 等. 设置排阵式预信号的干线交通信号协调控制优化[J]. 交通运输工程学报, 2024, 24(2): 243-253. doi: 10.19818/j.cnki.1671-1637.2024.02.017 LI Yan, SHI Xuan, NAN Si-rui, et al. Optimization of arterial traffic signal coordinated control with tandem pre- signal[J]. Journal of Traffic and Transportation Engineering, 2024, 24(2): 243-253. doi: 10.19818/j.cnki.1671-1637.2024.02.017
[26]	WU Y L, POON M, YUAN Z Z, et al. Time-dependent customized bus routing problem of large transport terminals considering the impact of late passengers[J]. Transportation Research Part C: Emerging Technologies, 2022, 143: 103859. doi: 10.1016/j.trc.2022.103859
[27]	HE P, JIN J G, SCHULTE F, et al. Optimizing first-mile ridesharing services to intercity transit hubs[J]. Transportation Research Part C: Emerging Technologies, 2023, 150: 104082. doi: 10.1016/j.trc.2023.104082
[28]	WANG X H, CHEN X Q, XIE C, et al. Coordinative dispatching of shared and public transportation under passenger flow outburst[J]. Transportation Research Part E: Logistics and Transportation Review, 2024, 189: 103655. doi: 10.1016/j.tre.2024.103655
[29]	HE P, JIN J G, SCHULTE F. The flexible airport bus and last-mile ride-sharing problem: Math-heuristic and metaheuristic approaches[J]. Transportation Research Part E: Logistics and Transportation Review, 2024, 184: 103489. doi: 10.1016/j.tre.2024.103489
[30]	WU X Y, MOUHRIM N, ARALDO A, et al. Joint design of conventional public transport network and mobility on demand[J]. Transportation Research Procedia, 2025, 86: 104-112. doi: 10.1016/j.trpro.2025.04.014
[31]	STIGLIC M, AGATZ N, SAVELSBERGH M, et al. Enhancing urban mobility: Integrating ride-sharing and public transit[J]. Computers & Operations Research, 2018, 90: 12-21.
[32]	BIAN Z Y, LIU X. Mechanism design for first-mile ridesharing based on personalized requirements part Ⅰ: Theoretical analysis in generalized scenarios[J]. Transportation Research Part B: Methodological, 2019, 120(C): 147-171.
[33]	姚恩建, 张茜, 张锐. 公共交通票价对通勤走廊出行结构的影响[J]. 交通运输工程学报, 2017, 17(6): 104-114. doi: 10.3969/j.issn.1671-1637.2017.06.012 YAO En-jian, ZHANG Qian, ZHANG Rui. Impact of public transport fare on travel mode structure of commuting corridor[J]. Journal of Traffic and Transportation Engineering, 2017, 17(6): 104-114. doi: 10.3969/j.issn.1671-1637.2017.06.012
[34]	GU Q P, LIANG J L. Algorithms and computational study on a transportation system integrating public transit and ridesharing of personal vehicles[J]. Computers & Operations Research, 2024, 164: 106529.
[35]	BEZA A D, DEMISSIE M G, KATTAN L. Equity implications of emerging mobility services and public transit coopetition: A review[J]. Transportation Research Part D: Transport and Environment, 2025, 144: 104751. doi: 10.1016/j.trd.2025.104751
[36]	CHENG L, CAI X M, LEI D, et al. Arrival information-guided spatiotemporal prediction of transportation hub passenger distribution[J]. Transportation Research Part E: Logistics and Transportation Review, 2025, 195(C): 104011.
[37]	CHENG L, CAI X M, LIU Z, et al. Characterising travel behaviour patterns of transport hub station area users using mobile phone data[J]. Journal of Transport Geography, 2024, 116: 103855. doi: 10.1016/j.jtrangeo.2024.103855
[38]	KUMAR P, KHANI A. An algorithm for integrating peer-to-peer ridesharing and schedule-based transit system for first mile/last mile access[J]. Transportation Research Part C: Emerging Technologies, 2021, 122: 102891. doi: 10.1016/j.trc.2020.102891
[39]	WU Y T, LAI M H, YANG R L, et al. Integrating one-to-many peer-to-peer ridesharing and public transit for morning commute on a mobility-as-a-service platform[J]. Transportmetrica A: Transport Science, 2024: 2393226.
[40]	SHANG H Y, CHANG Y, HUANG H J, et al. Integration of conventional and customized bus services: An empirical study in Beijing[J]. Physica A: Statistical Mechanics and Its Applications, 2022, 605: 127971. doi: 10.1016/j.physa.2022.127971
[41]	张昱, 刘学敏, 张红. 城市慢行交通发展的困境与思路[J]. 城市发展研究, 2014, 21(6): 113-116. ZHANG Yu, LIU Xue-min, ZHANG Hong. Dilemmas and strategies for the development of urban non-notorized travel[J]. Urban Development Studies, 2014, 21(6): 113-116.
[42]	MA W J, GUO Y H, AN K, et al. Pricing method of the flexible bus service based on cumulative prospect theory[J]. Journal of Advanced Transportation, 2022, 2022: 1785199.
[43]	WU M, YU C H, MA W J, et al. Joint optimization of timetabling, vehicle scheduling, and ride-matching in a flexible multi-type shuttle bus system[J]. Transportation Research Part C: Emerging Technologies, 2022, 139: 103657. doi: 10.1016/j.trc.2022.103657
[44]	吴同政. 多源数据驱动下的都市新区定制公交线路优化研究[D]. 西安: 长安大学, 2023. WU Tong-zheng. Research on optimization of customized bus routes in new urban areas driven by multi-source data[D]. Xi'an: Chang'an University, 2023.
[45]	UMARGONO E, SUSENO J E, VINCENSIUS GUNAWAN S K. K-means clustering optimization using the elbow method and early centroid determination based on mean and median formula[C]//ISSTEC. Proceedings of the 2nd International Seminar on Science and Technology (ISSTEC 2019). Dordrecht: Atlantis Press, 2020: 121-129.
[46]	王正武, 向健, 喻杰. 响应型接驳公交系统基于关键点的动态路径优化[J]. 长沙理工大学学报(自然科学版), 2020, 17(3): 51-61. WANG Zheng-wu, XIANG Jian, YU Jie. Dynamic route optimization based on key points for responsive feeder transit system[J]. Journal of Changsha University of Science & Technology (Natural Science), 2020, 17(3): 51-61.
[47]	彭巍, 周和平, 高攀. 面向城际轨道交通的定制化接驳公交线路优化[J]. 长沙理工大学学报(自然科学版), 2017, 14(4): 49-54, 82. PENG Wei, ZHOU He-ping, GAO Pan. The route optimization research of customized feeder transit system oriented on intercity railway system[J]. Journal of Changsha University of Science & Technology (Natural Science), 2017, 14(4): 49-54, 82.
[48]	雷永巍, 林培群, 姚凯斌. 互联网定制公交的网络调度模型及其求解算法[J]. 交通运输系统工程与信息, 2017, 17(1): 157-163. LEI Yong-wei, LIN Pei-qun, YAO Kai-bin. The network scheduling model and its solution algorithm of Internet customized shuttle bus[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(1): 157-163.