• 代表性成果介绍

    近年成果 

    Section image

    基于深度强化学习的自适应交通信号系统研究

    Tao Wang; Zhipeng Zhu; Jing Zhang; Junfang Tian*; Wenyi Zhang.A large-scale traffic signal control algorithm based on multi-layer graph deep reinforcement learning. Transportation Research Part C: Emerging Technologies, 2024, 162, 104582.

    交叉口作为城市交通的主要瓶颈，优化其信号配时对于缓解交通拥堵、提高通行效率具有重要意义。本团队基于深度强化学习构建孤立交叉口与区域交叉口自适应交通信号控制模型, 包括: 基于深度强化学习与图神经网络，设计孤立交叉口自适应交通信号控制算法，解决几何结构信息提取困难、不同交通流量适应困难问题；基于深度强化学习与多层图神经网络，构建区域交叉口自适应交通信号控制算法，解决路网空间信息利用不足、模型扩展困难问题；最后通过交通仿真软件 SUMO，结合区域交通信号控制算法，实现真实城市道路网络的仿真，进一步验证所提信号控制算法在实际交通环境的应用。

    Section image

    港湾式车站公交车行为分析与建模研究

    Wang Tao; Huang Li; Tian Junfang*; Zhang Jing, Yuan Zijian; Zheng Jianfeng. Bus dwell time estimation and overtaking maneuvers analysis: A stochastic process approach. Transportation Research Part E: Logistics and Transportation Review 2024, 186, 103577.

    公交车在港湾式车站的并道行为导致了公交车、乘客、车站和相邻车道车流之间具有极其复杂的相互作用关系，使得公交车停留时间高度变化。本团队以概率理论和随机过程为理论基础，对公交车停留时间构成和影响因素进行分析, 构建了单泊位和双泊位港湾式车站的公交车停留时间模型以及考虑多泊位的港湾式车站公交车停留时间集成模型，系统分析了公交车服务时间、车站平均服务时间、司机超车意愿和超车概率的关系以及不同超车政策对排队延迟的抑制作用，为公交车的运营管理提供了科学支持。

    Section image

    交通拥堵的排放分析与测算框架研究

    Zhou Shirui; Tian Junfang*; Ge YingEn; Yu Shaowei; Jiang Rui*. Experimental features of emissions and fuel consumption in a car-following platoon. Transportation Research Part D: Transport and Environment, 2023, 121: 103823.

    基于团队的合肥机场25辆车和北京通州大圆环40辆车实验数据集，首先分析了不同交通拥堵条件下车队的排放能耗特征，发现能耗和排放沿着车队呈现凹增长的特性；其次还测试了当前通用的耦合能耗排放测算框架的性能，发现在个体（车辆）层面，能耗排放可以被准确预测，而在系统（车队）层面，预测结果存在定性和定量差异。这揭示了交通系统复杂性建模中的微观预测和宏观预测的不一致性。

    Section image

    年轻驾驶员的夜间分心驾驶研究

    Yan Yingying; Zhong Shiquan; Tian Junfang*; Li Tong. Driving distraction at night: The impact of cell phone use on driving behaviors among young drivers[J]. Transportation research part F: traffic psychology and behaviour, 2022, 91: 401-413.

    本团队关注年轻驾驶员在环境能见度与分心因素交互作用下的驾驶行为，设计了三种不同的手机分心任务（无分心、通话和短信）与两个时间段（日间和夜间）下的驾驶模拟器实验。研究发现，在无分心任务时，参与者在日间和夜间驾驶中的横向控制表现没有显著差异；然而，引入分心任务后，夜间驾驶的横向车道偏移标准差显著高于日间，并且该差异仅在直线路段和大半径弯道上具有显著性。本研究揭示了年轻驾驶员在夜间与日间驾驶表现上的差异性，为相关道路安全政策的制定提供了理论依据。 

    Section image

    自动驾驶背景下的出行方式选择行为研究

    Zhang Qianran; Ma Shoufeng; Tian Junfang*; John M. Rose; Jia Ning. Mode choice between autonomous vehicles and manually-driven vehicles: An experimental study of information and reward. Transportation Research Part A: Policy and Practice, 2022, 157: 24-39.

    本团队采用多人协调博弈实验方法探究自动驾驶汽车下的出行方式选择行为。根据场景设定，自动驾驶能降低交通拥堵，但其成本相对较高。结果报名，更多的反馈信息将加剧对成本差的感知，减少自动驾驶选择。而奖励机制能有效诱导个体选择自动驾驶，提高社会总收益。通过改进的马尔科夫自适应学习模型，观察到个体决策行为的影响因素包括惯性、感知成本差和历史选择经验。研究结果为交通流量预测和理解个体决策机制提供了深入见解。 

    Section image

    驾驶行为随机性分析与建模研究

    Tian Junfang; Zhu Chenqiang; Chen Danjue; Jiang Rui*; Wang Guanying; Gao Ziyou. Car following behavioral stochasticity analysis and modeling: Perspective from wave travel time. Transportation Research Part B: Methodological 2021, 143: 160-176.

    基于团队的合肥机场25辆车和5辆车实验数据集，通过交通波传播时间分析了驾驶行为的随机性。首先，通过实测交通波传播时间序列发现其变化是随机的，且与前车的状态无明显联系；其次，证明了无论振荡是否完全发展，交通波传播时间的变化率都遵循均值回归过程；在此基础上，提出了随机Newell模型，分析推导了交通振荡的凹增长模式，并通过仿真表明，该模型较好地再现交通流演化的宏观特征和驾驶行为的微观特征。

  • 代表性成果列表 

    一、交通系统建模与仿真优化

    1. Wang, Tao; Huang, Li; Tian, Junfang*; Zhang, Jing; Yuan, Zijian; Zheng, Jianfeng. Bus dwell time estimation and overtaking maneuvers analysis: A stochastic process approach, Transportation Research Part E: Logistics and Transportation Review, 2024, 186, 103577
    2. Wang, Tao; Zhu, Zhipeng; Zhang, Jing; Tian, Junfang*; Zhang, Wenyi. A large-scale traffic signal control algorithm based on multi-layer graph deep reinforcement learning. Transportation Research Part C: Emerging Technologies, 2024,162: 104582
    3. Zhou, Shirui; Tian, Junfang*; Ge, Ying-En; Yu, Shaowei; Jiang*, Rui. Experimental features of emissions and fuel consumption in a car-following platoon[J]. Transportation Research Part D: Transport and Environment, 2023, 121: 103823.
    4. Zheng, Shi-Teng; Jiang, Rui*; Tian, Junfang*; Li, Xiaopeng; Treiber, Martin; Li, Zhen-Hua; Gao, Lan-Da; Jia, Bin. Empirical and experimental study on the growth pattern of traffic oscillations upstream of fixed bottleneck and model test [J]. Transportation Research Part C-Emerging Technologies, 2022, 140, 103729.
    5. Zheng, Shi-Teng; Jiang, Rui*; Tian, Junfang*; Zhang, H. M.; Li, Zhen-Hua; Gao, Lan-Da; Jia, Bin. Experimental study on properties of lightly congested flow [J]. Transportation Research Part B-Methodological, 2021,149: 1-19.
    6. Tian, Junfang; Zhu, Chenqiang; Chen, Danjue; Jiang, Rui*; Wang, Guanying*; Gao, Ziyou. Car following behavioral stochasticity analysis and modeling: Perspective from wave travel time [J]. Transportation Research Part B-Methodological, 2021,143: 160-176.
    7. Wang, Tao; Xu, Keyu; Tian, Junfang*; Zhang, Jing*; Gao, Ziyou; Li, Shubin. Boarding Time Estimation Using the Passenger Density Distribution on the Bus [J]. IEEE Transactions on Intelligent Transportation Systems, 2021:1-14.
    8. Tian, Junfang; Zhang, H. M.; Treiber, Martin; Jiang, Rui; Gao, Ziyou; Jia, Bin. On the Role of Speed Adaptation and Spacing Indifference in Traffic Instability: Evidence from Car-Following Experiments and Its Stochastic Model [J]. Transportation Research Part B-Methodological. 2019, 129(11):334-350.
    9. Tian, Junfang; Jia, Bin; Ma, Shoufeng; Zhu, Chenqiang; Jiang, Rui; Ding, Yaoxian. Cellular Automaton Model with Dynamical 2D Speed-Gap Relation [J]. Transportation Science. 2017, 51(3):807-822.
    10. Tian, Junfang; Jiang, Rui; Jia, Bin; Gao, Ziyou; Ma, Shoufeng. Empirical Analysis and Simulation of the Concave Growth Pattern of Traffic Oscillations [J]. Transportation Research Part B-Methodological. 2016, 93(A):338-354.
    11. Tian, Junfang; Li, Guangyu; Treiber, Martin; Jiang, Rui; Jia, Ning; Ma, Shoufeng. Cellular Automaton Model Simulating Spatiotemporal Patterns, Phase Transitions and Concave Growth Pattern of Oscillations in Traffic Flow [J]. Transportation Research Part B-Methodological. 2016, 93(8): 560-575.
    12. Tian, Junfang; Treiber, Martin; Ma, Shoufeng; Jia, Bin; Zhang, Wenyi. Microscopic driving theory with oscillatory congested states: model and empirical verification [J]. Transportation Research Part B: Methodological. 2015,71: 138-157.
    13. Tian, Junfang; Jia, Ning; Zhu, Ning; Jia, Bin; Yuan, Zhenzhou. Brake light cellular automaton model with advanced randomization for traffic breakdown [J]. Transportation Research Part C: Emerging Technologies. 2014,44:282-298.

    二、交通行为与管理政策

    1. Yan Yingying, Zhong Shiquan, Tian Junfang*, Liang Song, Driving distraction at night: The impact of cell phone use on driving behaviors among young drivers[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2022, 91: 401-413.
    2. Zhang, Qianran; Ma, Shoufeng; Tian, Junfang*; Rose, John M.; Jia, Ning*. Mode choice between autonomous vehicles and manually-driven vehicles: An experimental study of information and reward[J]. Transportation Research Part A-Policy and Practice, 2022,157: 24-39.
    3. Yan Yingying, Zhong Shiquan, Tian Junfang*, Ning Jia, An empirical study on consumer automobile purchase intentions influenced by the COVID-19 outbreak [J] Journal of Transport Geography, 2022, 104: 103458.
    4. Yan Yingying, Zhong Shiquan, Tian Junfang*, Tong Li. Continuance intention of autonomous buses: An empirical analysis based on passenger experience[J]. Transport Policy, 2022, 126: 85-95.
    5. Dong, Hongming; Zhong, Shiquan; Xu, Shuxian; Tian, Junfang; Feng, Zhongxiang. The relationships between traffic enforcement, personal norms and aggressive driving behaviors among normal e-bike riders and food delivery e-bike riders [J]. Transport Policy, 2021(114):138-146. 3
    6. Dong, Hongming; Ma, Shoufeng; Jia, Ning; Tian, Junfang*. Understanding public transport satisfaction in post COVID-19 pandemic [J]. Transport Policy, 2021,101: 81-88.
    7. Dong, Hongming; Jia, Ning; Tian, Junfang*; Ma, Shoufeng. The Effectiveness and Influencing Factors of a Penalty Point System in China from the Perspective of Risky Driving Behaviors [J]. Accident Analysis and Prevention. 2019, 131(10):171-179.
    8. Liu, Xue; Ma, Shoufeng; Tian, Junfang*; Jia, Ning; Li, Geng. A system dynamics approach to scenario analysis for urban passenger transport energy consumption and CO2 emissions: A case study of Beijing [J]. Energy Policy. 2015,85: 253–270.
    Cookie的使用
    我们使用cookies来确保流畅的浏览体验。若继续，我们认为你接受使用cookies。
    了解更多