需求响应式公交关键技术综述、挑战与发展路径

陈景, 肖光年, 刘锴

清华大学学报(自然科学版) ›› 2026, Vol. 66 ›› Issue (11) : 2149-2167.

PDF(1506 KB)
PDF(1506 KB)
清华大学学报(自然科学版) ›› 2026, Vol. 66 ›› Issue (11) : 2149-2167. DOI: 10.16511/j.cnki.qhdxxb.2026.26.045
需求响应定制公交

需求响应式公交关键技术综述、挑战与发展路径

  • 陈景1, 肖光年2, 刘锴3
作者信息 +

Demand-responsive transit: a review of key technologies, challenges and development pathways

  • CHEN Jing1, XIAO Guangnian2, LIU Kai3
Author information +
文章历史 +

摘要

需求响应式公交(demand-responsive transit,DRT)作为介于常规公交与出租车服务之间的灵活服务形态,凭借预约或即时需求以及动态路径优化,能够在低密度出行、低峰时段和“最后一公里”等场景下提升公共交通的可达性和效率。该文首先基于DRT领域国内外研究成果,总结出“数据感知—决策优化—系统集成与治理”3层技术框架,该框架以多源数据和不确定性刻画为输入,以滚动优化和调度求解为核心,以系统部署、运营规则和政策工具为约束和反馈,形成贯通预测、求解、实施和评估的闭环链路,从而有效弥合优化技术与实际应用之间的差距;随后,基于该框架,该文围绕需求预测、路径优化与车辆调度,以及智能化与自动驾驶等关键技术开展综述,并分析了DRT在需求侧、供给侧、智能化与自动驾驶融合,以及治理与可持续运营等方面面临的结构性挑战和发展路径。结果表明:DRT需求预测正由统计计量向机器学习、多源数据融合与不确定性量化协同演进;路径优化与车辆调度已形成精确算法、启发式算法和智能优化算法并行且深度融合的格局;智能化与自动驾驶为进一步降低DRT运营成本、提升服务稳定性提供了新的技术路径,但也带来了可解释性、安全性和治理等方面的问题。相较于DRT领域既有综述,该文将需求与服务的不确定性贯穿于需求预测、调度优化和系统集成全过程,并从技术和治理双重视角提出适应性分析、绩效导向补贴、人机协同智能调度等发展建议,以期为DRT试点和推广提供参考。

Abstract

[Significance] Demand-responsive transit (DRT) has reemerged as a strategically important service model for public transportation systems seeking to enhance accessibility and operational efficiency amid limited resources. Positioned between traditional fixed-route transit and personalized travel options, DRT offers flexible service through prebooking or on-demand requests and dynamic route adjustments, providing particular advantages in low-density areas, during off-peak hours, and in last-mile or feeder scenarios where fixed routes often underperform. In these contexts, the main challenge is not only whether a dispatching algorithm can produce feasible routes but also whether the entire DRT system can deliver stable, equitable, and scalable performance despite highly variable demand and complex operational constraints. This challenge encourages a systems engineering approach that links demand sensing, real-time decision-making, and institutional design, rather than treating DRT as a standalone operational problem. Accordingly, this review aims to synthesize the technological landscape and clarify how methodological advances can facilitate sustainable deployment and governance pathways. [Progress] Based on an extensive review of the literature and comparative analysis, this paper organizes prior research into a three-layer technical framework (data perception, decision optimization, and system integration and governance). It uses this structure to synthesize major advances and outstanding issues. At the data perception layer, research has evolved from statistical and econometric modeling toward machine learning, multisource data fusion, and uncertainty-aware prediction. Econometric and discrete-choice approaches remain valuable for feasibility assessment and policy interpretation because they reveal the marginal effects of socioeconomic attributes, built environment, and service design on ridership responses. More recent machine learning and deep learning models have enhanced short-term predictive accuracy and timeliness when sufficient operational data are available. However, DRT demand is often characterized by low volumes and high volatility, making point forecasts fragile and highlighting the importance of probabilistic forecasting and uncertainty quantification so that dispatching decisions can explicitly account for risk and disturbances. Meanwhile, multisource data fusion and origin-destination inference have become increasingly prominent for capturing spatial structures and supporting stop or zone design and service layout under data sparsity conditions. At the decision optimization layer, the literature has expanded from traditional formulations toward a broader range of methodologies that balance optimality, scalability, and robustness. Exact algorithms, heuristic and metaheuristic methods, and intelligent optimization approaches are compared within a unified framework, with particular emphasis on real-time requirements, multiobjective trade-offs, and resilience under uncertainty. Exact methods provide solutions comparable to benchmarks for small-scale or offline problems but may lack responsiveness in real-time applications. Heuristic and metaheuristic strategies are widely used in practice because they can deliver high-quality solutions within strict time constraints and can be tailored to diverse operational constraints. Simultaneously, intelligent approaches are increasingly being examined as complementary tools, such as learning to generate parameters, heuristics, or quality initial solutions that speed up optimization while maintaining operational feasibility and interpretability. At the system integration and governance level, research underscores that DRT performance relies on the coevolution of technologies and institutional frameworks. This review goes beyond algorithms to explore how platform integration, organizational coordination, and policy instruments shape long-term outcomes. In particular, it discusses how emerging technologies such as artificial intelligence (AI), electrification, and automated driving can interact with operational structures, management rules, and regulatory tools, and why these interactions could be crucial for scaling DRT beyond pilot projects. Across these layers, the paper also identifies structural challenges related to demand patterns, supply-side operational constraints, the integration of AI and automated driving technologies, and governance and sustainability issues. These challenges emphasize the importance of closed-loop evaluation metrics that connect perception and optimization, as well as governance arrangements that prevent unintended incentives and improve system reliability. [Conclusions and Prospects] This review concludes that scaling DRT requires shifting the focus from just algorithm performance to overall system sustainability. Future research should strengthen the feedback loop between demand perception and operational optimization under uncertainty and promote deeper integration between DRT services and traditional bus networks to enhance reliability and network-level efficiency. Moreover, the adoption of AI-enabled techniques and emerging technologies (e.g., automation and advanced interaction tools) should proceed carefully and be supported by clear governance frameworks, accountability mechanisms, and evaluation systems to ensure long-term, equitable, and secure operations.

关键词

需求响应式公交 / 城市交通 / 需求预测 / 路径优化算法

Key words

demand-responsive transit / urban transportation / demand forecasting / routing optimization algorithms

引用本文

导出引用
陈景, 肖光年, 刘锴. 需求响应式公交关键技术综述、挑战与发展路径[J]. 清华大学学报(自然科学版). 2026, 66(11): 2149-2167 https://doi.org/10.16511/j.cnki.qhdxxb.2026.26.045
CHEN Jing, XIAO Guangnian, LIU Kai. Demand-responsive transit: a review of key technologies, challenges and development pathways[J]. Journal of Tsinghua University(Science and Technology). 2026, 66(11): 2149-2167 https://doi.org/10.16511/j.cnki.qhdxxb.2026.26.045
中图分类号: U492.2+2   

参考文献

[1] BERRADA J, POULHÈS A. Economic and socioeconomic assessment of replacing conventional public transit with demand responsive transit services in low-to-medium density areas[J]. Transportation Research Part A: Policy and Practice, 2021, 150: 317-334.
[2] FADLELSEED S, SARHADI P, RAMALINGAM S, et al. Recent advances in demand responsive transport: Opportunities with autonomous bus service-a system-of-systems overview [J]. IEEE Access, 2025, 13: 107800-107831.
[3] MAGEEAN J, NELSON J D. The evaluation of demand responsive transport services in Europe[J]. Journal of Transport Geography, 2003, 11(4): 255-270.
[4] 南昌发布. 从“招手停”到“按需达”南昌一键“打公交” [J]. 人民公交, 2025(24): 192. Nanchangfabu. From “hail-and-ride” to “on-demand arrival”: Nanchang launches one-click “bus hailing”[J]. Urban Public Transport, 2025(24): 192. (in Chinese)
[5] ZHENG R, YANG H T, FAN W B, et al. Optimizing service design for the intercity demand responsive transit system: Model, algorithm, and comparative analysis[J]. Expert Systems with Applications, 2024, 254: 124180.
[6] WANG H F, GUAN H Z, QIN H M, et al. Towards a more flexible demand responsive transit service with compensation mechanism considering boundedly rational passengers[J]. IET Intelligent Transport Systems, 2023, 17(6): 1229-1246.
[7] VANSTEENWEGEN P, MELIS L, AKTAŞ D, et al. A survey on demand-responsive public bus systems[J]. Transportation Research Part C: Emerging Technologies, 2022, 137: 103573.
[8] ZHAO J, SUN S C, CATS O. Joint optimisation of regular and demand-responsive transit services[J]. Transportmetrica A: Transport Science, 2023, 19(2): 1987580.
[9] WANG L, CHIEN S, WIRASINGHE S C, et al. Joint optimization of zone area and headway for demand responsive transit service under heterogeneous environment[J]. KSCE Journal of Civil Engineering, 2022, 26(7): 3031-3042.
[10] ALONSO-GONZÁLEZ M J, HOOGENDOORN-LANSER S, VAN OORT N, et al. Drivers and barriers in adopting mobility as a service (MaaS): A latent class cluster analysis of attitudes[J]. Transportation Research Part A: Policy and Practice, 2020, 132: 378-401.
[11] LEONARDI P, TORRISI V, ARALDO A, et al. Data-driven assessment for the predictability of demand responsive transit[J/OL]. Transportmetrica A: Transport Science. (2026- 04-01) [2026-01-20]. https://doi.org/10.1080/23249935.2026. 2650136.
[12] CURRIE G, FOURNIER N. Why most DRT/micro-transits fail-what the survivors tell us about progress[J]. Research in Transportation Economics, 2020, 83: 100895.
[13] WANG H, LI J Y, WANG P L, et al. Adaptability analysis methods of demand responsive transit: A review and future directions[J]. Transport Reviews, 2023, 43(4): 676-697.
[14] NYGA A, MINNICH A, SCHLÜTER J. The effects of susceptibility, eco-friendliness and dependence on the consumers’ willingness to pay for a door-to-door DRT system [J]. Transportation Research Part A: Policy and Practice, 2020, 132: 540-558.
[15] ZAHEDI S, KOUTSOPOULOS H N, MA Z L. Improving demand responsive transit services: Insights from the London field test[J]. Journal of Public Transportation, 2024, 26: 100107.
[16] COUTINHO F M, VAN OORT N, CHRISTOFOROU Z, et al. Impacts of replacing a fixed public transport line by a demand responsive transport system: Case study of a rural area in Amsterdam[J]. Research in Transportation Economics, 2020, 83: 100910.
[17] HO S C, SZETO W Y, KUO Y H, et al. A survey of dial-a- ride problems: Literature review and recent developments [J]. Transportation Research Part B: Methodological, 2018, 111: 395-421.
[18] JITTRAPIROM P, VAN NEERVEN W, MARTENS K, et al. The Dutch elderly's preferences toward a smart demand- responsive transport service[J]. Research in Transportation Business & Management, 2019, 30: 100383.
[19] AVERMANN N, SCHLÜTER J. Determinants of customer satisfaction with a true door-to-door DRT service in rural Germany[J]. Research in Transportation Business & Management, 2019, 32: 100420.
[20] KUEHNEL N, ZWICK F, KUHLEN T E. Revealed demand patterns of people with disabilities in on-demand ridepooling [J]. European Journal of Transport and Infrastructure Research, 2025, 25(2): 33-58.
[21] 祁娟. 小猪巴士: 互联网定制化的“绿色先锋军”[J]. 运输经理世界, 2015(15): 64-66. QI J. Xiaozhu bus: The “green vanguard” of Internet-based customized services[J]. Transport Business China, 2015(15): 64-66. (in Chinese)
[22] 孙继伟, 江莉. 共享巴士商业模式比较:以飞路巴士、驿动汽车、小龙巴士为例[J]. 企业管理, 2019(2): 87-89. SUN J W, JIANG L. Comparison of business models for shared buses: A case study of Feilu Bus, Yidong Bus, and Xiaolong Bus[J]. Enterprise Management, 2019(2): 87-89. (in Chinese)
[23] 黄黎晨, 杨春喜, 郭长明. 需求响应公共汽车交通在雄安新区的实践[J]. 城市交通, 2024, 22(1): 62-67. HUANG L C, YANG C X, GUO C M. Demand-responsive transit in Xiong'an new area[J]. Urban Transport of China, 2024, 22(1): 62-67. (in Chinese)
[24] 柏聪, 曹荣晓, 王刚, 等. 重庆“响应公交”: 灵活路径需求响应公交模式的实践与探索[J]. 城市公共交通, 2025(4): 49-55. BAI C, CAO R X, WANG G, et al. “Xiangying Bus” in Chongqing: A practice and exploration of the flexible route demand-responsive transit model[J]. Urban Public Transport, 2025(4): 49-55. (in Chinese)
[25] SCHASCHÉ S E, SPOSATO R G, HAMPL N. The dilemma of demand-responsive transport services in rural areas: Conflicting expectations and weak user acceptance[J]. Transport Policy, 2022, 126: 43-54.
[26] ROSSOLOV O, GKAVRA R, SUSILO Y O. Will you still drive or are you ready to ride? Exploring readiness to use demand-responsive transport in the city of Vienna[J]. Research in Transportation Business & Management, 2025, 59: 101277.
[27] INTURRI G, GIUFFRIDA N, IGNACCOLO M, et al. Taxi vs. demand responsive shared transport systems: An agent- based simulation approach[J]. Transport Policy, 2021, 103: 116-126.
[28] MAYAUD J. On the role of microtransit in shaping new mobility patterns[J]. Travel Behaviour and Society, 2025, 41: 101065.
[29] BRUZZONE F, SCORRANO M, NOCERA S. The combination of e-bike-sharing and demand-responsive transport systems in rural areas: A case study of Velenje[J]. Research in Transportation Business & Management, 2021, 40: 100570.
[30] LU C C, LIANG J K. Estimating the willingness-to-pay of local residents and tourists for volunteer-model shared demand responsive transit services[J]. Transportation Planning and Technology, 2025, 48(6): 1147-1165.
[31] 刘锴, 王静, 王江波, 等. 考虑个体偏好异质性的定制公交选择行为[J]. 中国公路学报, 2024, 37(6): 279-287. LIU K, WANG J, WANG J B, et al. Study on customized bus choice behavior considering individual preference heterogeneity [J]. China Journal of Highway and Transport, 2024, 37(6): 279-287. (in Chinese)
[32] SULTANA Z, MISHRA S, CHERRY C R, et al. Modeling frequency of rural demand response transit trips[J]. Transportation Research Part A: Policy and Practice, 2018, 118: 494-505.
[33] PARK J, CHOI S, KIM G, et al. Provision of metropolitan demand responsive transit and attitude’s role in mode choice [J]. Transportation Research Part D: Transport and Environment, 2025, 140: 104640.
[34] HU S G, LI C, WU W T, et al. Exploring the determinants of demand-responsive transit acceptance in China[J]. Transport Policy, 2025, 165: 150-163.
[35] KNIERIM L, SCHLÜTER J C. The attitude of potentially less mobile people towards demand responsive transport in a rural area in central Germany[J]. Journal of Transport Geography, 2021, 96: 103202.
[36] DŽUPKA P, GRÓF M, DRÁB R, et al. Beyond the bus: Unraveling DRT's potential—An ex ante WTP evaluation for replacing ineffective fixed route regional lines[J]. Research in Transportation Business & Management, 2025, 60: 101361.
[37] WANG J B, CAO X Y, LIU K, et al. Exploring the nonlinear effects of built environment characteristics on customized bus service[J]. Transportation Research Part D: Transport and Environment, 2023, 114: 103523.
[38] LEE J, CHOI Y, KIM J. A multi-task deep learning framework for forecasting sparse demand of demand responsive transit [J]. Expert Systems with Applications, 2024, 250: 123833.
[39] LEE E, CHOI H, KIM D G. PGDRT: Prediction demand based on graph convolutional network for regional demand-responsive transport[J]. Journal of Advanced Transportation, 2023, 2023(1): 7152010.
[40] LIU X, CHEN X H, POTOGLOU D, et al. Travel impedance, the built environment, and customized-bus ridership: A stop-to-stop level analysis[J]. Transportation Research Part D: Transport and Environment, 2023, 122: 103889.
[41] 刘华胜, 杨莎, 李津, 等. 基于出租车轨迹数据的需求响应式公交线路规划方法[J]. 科学技术与工程, 2025, 25(5): 2135-2145. LIU H S, YANG S, LI J, et al. Demand responsive transit route planning based on mining taxi trajectory data[J]. Science Technology and Engineering, 2025, 25(5): 2135- 2145. (in Chinese)
[42] WU F, ZHENG C J, DU M Q, et al. LLM4PT: A large language model-based system for flexible and explainable public transit demand prediction[J]. Computers & Industrial Engineering, 2025, 209: 111449.
[43] GUAN D Y, WU X F, WANG K, et al. Vehicle dispatch and route optimization algorithm for demand-responsive transit [J]. Processes, 2022, 10(12): 2651.
[44] WANG J B, LIU K, YAMAMOTO T, et al. Built environment as a precondition for demand-responsive transit (DRT) system survival: Evidence from an empirical study[J]. Travel Behaviour and Society, 2023, 30: 271-280.
[45] TEJERO-BETETA C, MOYANO A, SÁNCHEZ- CAMBRONERO S. Factors influencing the efficiency of demand-responsive transport services in rural areas: A GIS-based method for optimising and evaluating potential services[J]. ISPRS International Journal of Geo-Information, 2024, 13(8): 275.
[46] KAUFMAN B, LEUNG A, WILLCOX J. The tale of two networks: Leveraging digital twin inspired simulations to enhance on-demand transit services[J]. Transportation Planning and Technology, 2025, 48(7): 1530-1556.
[47] WU W T, ZOU H H, LIU R H. Prediction-failure-risk-aware online dial-a-ride scheduling considering spatial demand correlation via approximate dynamic programming and scenario approach[J]. Transportation Research Part C: Emerging Technologies, 2024, 169: 104801.
[48] ZIGRAND L, CALVO R W, TRAVERSI E, et al. A scalable combinatorial Benders decomposition for the stochastic dial-a-ride problem[J]. Transportation Research Part C: Emerging Technologies, 2024, 163: 104624.
[49] ZHENG Y, LI W Q, QIU F. A slack arrival strategy to promote flex-route transit services[J]. Transportation Research Part C: Emerging Technologies, 2018, 92: 442-455.
[50] PARK S, PARK S, CHOI H, et al. Data-driven approach to evaluate the level of service (LOS) of demand-responsive transport for the disabled (DRTD) with an ANFIS algorithm [J]. Journal of Advanced Transportation, 2024, 2024(1): 7312690.
[51] 孙洁, 靳文舟, 张永. 考虑乘客出行选择的需求响应公交调度方法[J]. 深圳大学学报(理工版), 2025, 42(2): 192-204. SUN J, JIN W Z, ZHANG Y. Demand responsive transit scheduling method considering passenger travel choice [J]. Journal of Shenzhen University (Science and Engineering), 2025, 42(2): 192-204. (in Chinese)
[52] 赫雪婷, 镇璐. 需求响应式公交中考虑即时订单的线路重调度优化[J]. 中国管理科学, 2023, 31(3): 113-123. HE X T, ZHEN L. Optimization of route rescheduling considering real-time orders in demand-responsive transit [J]. Chinese Journal of Management Science, 2023, 31(3): 113-123. (in Chinese)
[53] HUANG D, GU Y, WANG S A, et al. A two-phase optimization model for the demand-responsive customized bus network design[J]. Transportation Research Part C: Emerging Technologies, 2020, 111: 1-21.
[54] HE X T, YANG Z Y, FAN T Y, et al. Branch and price algorithm for route optimization on customized bus service [J]. Annals of Operations Research, 2024, 335(1): 205-236.
[55] 靳文舟, 杜昊, 巫威眺. 基于ALNS-TS算法的半灵活型需求响应公交调度问题[J]. 深圳大学学报(理工版), 2023, 40(4): 425-434. JIN W Z, DU H, WU W T. Semi-flexible demand responsive transit scheduling based on ALNS-TS algorithm [J]. Journal of Shenzhen University (Science and Engineering), 2023, 40(4): 425-434. (in Chinese)
[56] 靳文舟, 张永, 孙洁. 基于模型预测控制的需求响应公交动态调度[J]. 华南理工大学学报(自然科学版), 2025, 53(6): 77-90. JIN W Z, ZHANG Y, SUN J. Dynamic scheduling of demand responsive transit based on model predictive control[J]. Journal of South China University of Technology (Natural Science Edition), 2025, 53(6): 77-90. (in Chinese)
[57] 沈子康, 靳文舟, 郑亚晶. 站点可变型需求响应式公交车辆调度优化研究[J]. 深圳大学学报(理工版), 2024, 41(6): 691-702. SHEN Z K, JIN W Z, ZHENG Y J. Vehicle scheduling optimization for demand responsive transit with flexible stops[J]. Journal of Shenzhen University (Science and Engineering), 2024, 41(6): 691-702. (in Chinese)
[58] 徐伟汉, 李欣, 王天奇. 基于生态驾驶的常规和需求响应公交混合调度方法[J]. 交通运输系统工程与信息, 2025, 25(2): 227-240. XU W H, LI X, WANG T Q. Hybrid scheduling method for conventional bus and demand-responsive transit based on eco-driving technology[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 227- 240. (in Chinese)
[59] 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 X, QIAO J Y, LI Y H, 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. (in Chinese)
[60] 李欣, 林小敬, 许航, 等. 需求响应公交网络化运营优化模型[J]. 计算机应用, 2023, 43(S1): 288-292. LI X, LIN X J, XU H, et al. Optimization model of networked operation for demand-responsive transit[J]. Journal of Computer Applications, 2023, 43(S1): 288-292. (in Chinese)
[61] 孙倩, 胡大伟, 钱一之, 等. 考虑车辆随机到站时间的动态需求响应型接驳公交线路优化[J]. 交通运输系统工程与信息, 2022, 22(5): 196-204, 292. SUN Q, HU D W, CHIEN S, et al. Dynamic bus routing optimization for demand-responsive feeder transit considering stochastic bus arrival time[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(5): 196-204, 292. (in Chinese)
[62] 陆百川, 黄镜轶, 张冬梅, 等. 站点需求响应式公交调度系统优化研究[J]. 重庆理工大学学报(自然科学), 2021, 35(2): 34-43. LU B C, HUANG J Y, ZHANG D M, et al. Research on optimization of station demand-responsive public transit dispatching system[J]. Journal of Chongqing University of Technology (Natural Science), 2021, 35(2): 34-43. (in Chinese)
[63] KIM T W, CHAE M, YU J W. Optimization and implementation framework for connected demand responsive transit (DRT) considering punctuality[J]. Sustainability, 2025, 17(3): 1079.
[64] ZHOU X M, ZHANG Y B, GUO H W. Scheduling method of demand-responsive transit based on reservation considering vehicle size and mileage[J]. Applied Sciences, 2024, 14(19): 8836.
[65] LI H L, KIM S K. Efficient route planning for real-time demand-responsive transit[J]. Computers, Materials & Continua, 2024, 79(1): 473-492.
[66] SONG C Y, WANG H L, CHEN L, et al. An optimized two- phase demand-responsive transit scheduling model considering dynamic demand[J]. IET Intelligent Transport Systems, 2024, 18(5): 853-871.
[67] 黄迪, 刘子煜, 刘月, 等. 数据驱动的需求响应型定制公交线路规划[J]. 清华大学学报(自然科学版), 2026, 66(3): 638-650. HUANG D, LIU Z Y, LIU Y, et al. Data-driven route planning for demand-responsive customized bus services[J]. Journal of Tsinghua University (Science and Technology), 2026, 66(3): 638-650. (in Chinese)
[68] LI X, GUAN Y, HUANG J G, et al. Robust service and charging plan for dynamic electric demand-responsive transit systems[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(12): 15930-15947.
[69] SUN Q, CHIEN S, HU D W, et al. Optimizing multi-terminal customized bus service with mixed fleet[J]. IEEE Access, 2020, 8: 156456-156469.
[70] WU W T, ZHU Y C, LIU R H. Dynamic scheduling of flexible bus services with hybrid requests and fairness: Heuristics- guided multi-agent reinforcement learning with imitation learning[J]. Transportation Research Part B: Methodological, 2024, 190: 103069.
[71] WANG H F, GUAN H Z, QIN H M, et al. Assessing the sustainability of time-dependent electric demand responsive transit service through deep reinforcement learning[J]. Energy, 2024, 296: 130999.
[72] 高虹, 刘锴, 姚恩建. 站点需求响应的电动模块公交车重组调度优化[J]. 中国公路学报, 2024, 37(4): 24-36. GAO H, LIU K, YAO E J. Formation and scheduling optimization of electric modular buses with station-based demand-responsive model[J]. China Journal of Highway and Transport, 2024, 37(4): 24-36. (in Chinese)
[73] PATRICIO A S, SANTOS G G D, ANTUNES A P. Assessing the introduction of regional driverless demand-responsive transit services through agent-based modeling and simulation [J]. Transportation, 2025, 52(3): 1091-1118.
[74] DEVUNURI S, QIAM S, LEHE L J. ChatGPT for GTFS: benchmarking LLMs on GTFS semantics… and retrieval[J]. Public Transport, 2024, 16(2): 333-357.
[75] MAKSOUD N, ALJASSMI H, ALI L, et al. Applications of large language models and generative AI in transportation: A systematic review and bibliometric analysis[J]. Transportation Research Interdisciplinary Perspectives, 2025, 34: 101699.
[76] RAHIMI M, AMIRGHOLY M, GONZALES E J. System modeling of demand responsive transportation services: Evaluating cost efficiency of service and coordinated taxi usage[J]. Transportation Research Part E: Logistics and Transportation Review, 2018, 112: 66-83.
[77] HU J, DONG Y X, ZHANG Z H, et al. A dispatching method for demand responsive transit with passengers’ hidden preference exploitation capability[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(8): 12501- 12517.
[78] SÖRENSEN L, BOSSERT A, JOKINEN J P, et al. How much flexibility does rural public transport need?-Implications from a fully flexible DRT system[J]. Transport Policy, 2021, 100: 5-20.
[79] AMIRGHOLY M, GONZALES E J. Demand responsive transit systems with time-dependent demand: User equilibrium, system optimum, and management strategy[J]. Transportation Research Part B: Methodological, 2016, 92: 234-252.
[80] 刘锴, 王静, 连芝锐, 等. 考虑公平性的定制公交路径规划及系统评估[J]. 科技导报, 2024, 42(3): 89-96. LIU K, WANG J, LIAN Z R, et al. Customized bus path planning and system evaluation considering equity[J]. Science & Technology Review, 2024, 42(3): 89-96. (in Chinese)
[81] HAN S W, MOON S, KIM D K. Multi-objective optimization of demand responsive transit operations based on dynamic passenger requests using maximum time delay rate[J]. Journal of Public Transportation, 2024, 26: 100108.
[82] PERERA S, HO C, HENSHER D. Resurgence of demand responsive transit services-Insights from BRIDJ trials in Inner West of Sydney, Australia[J]. Research in Transportation Economics, 2020, 83: 100904.
[83] ZHANG Y X, FARBER S, YOUNG M. Eliminating barriers to nighttime activity participation: The case of on-demand transit in Belleville, Canada[J]. Transportation, 2022, 49(5): 1385-1408.
[84] OH S, SESHADRI R, LE D T, et al. Evaluating automated demand responsive transit using microsimulation[J]. IEEE Access, 2020, 8: 82551-82561.
[85] GOLBABAEI F, PAZ A, YIGITCANLAR T, et al. Navigating autonomous demand responsive transport: Stakeholder perspectives on deployment and adoption challenges[J]. International Journal of Digital Earth, 2024, 17(1): 2297848.
[86] ZHAO C L, XUE M T, HAMIDI Z. Potential of demand responsive transport for young people in Sweden[J]. Transportation Research Part A: Policy and Practice, 2024, 184: 104093.
[87] CAVALLARO F, NOCERA S. Flexible-route integrated passenger-freight transport in rural areas[J]. Transportation Research Part A: Policy and Practice, 2023, 169: 103604.
[88] 贺韵竹, 贾鹏, 李海江, 等. 新型需求响应公交发车时刻和票价优化[J]. 系统工程理论与实践, 2022, 42(4): 1060- 1071. HE Y Z, JIA P, LI H J, et al. Optimization of the departure time and fare of new demand responsive transit systems[J]. Systems Engineering-Theory & Practice, 2022, 42(4): 1060- 1071. (in Chinese)
[89] JOKINEN J P, SIHVOLA T, MLADENOVIC M N. Policy lessons from the flexible transport service pilot Kutsuplus in the Helsinki Capital Region[J]. Transport Policy, 2019, 76: 123-133.
[90] BROWN A, MANVILLE M, WEBER A. Can mobility on demand bridge the first-last mile transit gap? Equity implications of Los Angeles' pilot program[J]. Transportation Research Interdisciplinary Perspectives, 2021, 10: 100396.
[91] LAWS R, ENOCH M, ISON S, et al. Demand responsive transport: A review of schemes in England and Wales[J]. Journal of Public Transportation, 2009, 12(1): 19-37.
[92] 何宇, 章姗迟. 上海定制公交“首席运营官”上线[N]. 中国交通报, 2025-05-22(8). HE Y, ZHANG S C. “Chief operating officer” launched for Shanghai customized bus service[N]. China Transportation News, 2025-05-22(8). (in Chinese)
[93] KOH K, NG C, PAN D, et al. Dynamic bus routing: A study on the viability of on-demand high-capacity ridesharing as an alternative to fixed-route buses in Singapore[C]// Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC). Maui, USA: IEEE, 2018: 34-40.

基金

国家自然科学基金面上项目(72471045, 52472323)

PDF(1506 KB)

Accesses

Citation

Detail

段落导航
相关文章

/

〈 〉