Transportation Research Part C-Emerging Technologies最新文献_第7页

A line planning approach with passenger assignment considering cross-line operations and flexible train composition for a metro network 考虑跨线运营和灵活列车组成的地铁线路规划方法

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-11 DOI: 10.1016/j.trc.2025.105489

Zhikai Wang , Andrea D’Ariano , Shuai Su , Tao Tang , Boyi Su

As metro systems in most major cities evolve from single-line to network-level operations, passenger accessibility improves significantly. However, interchange stations experience increased pressure due to high transfer demand. Additionally, the non-equilibrium distribution of passenger demand poses significant challenges for operators. One effective strategy to mitigate transfer issues and improve operational flexibility is the implementation of cross-line operations. Furthermore, the flexible train composition mode provides a promising avenue to accommodate imbalanced passenger demand. In light of this, the study focuses on the line planning problem with passenger assignment, considering cross-line operations and the flexible train composition mode. Given that these operational modes require closer cooperation among trains, traditional line planning formulations become inadequate. To tackle this challenge, a novel mathematical model utilizing aggregated decision variables is developed to represent cross-line and flexible train coupling and decoupling operations. Subsequently, we formulate the passenger assignment problem as a multi-commodity flow problem, which effectively captures passenger movements within the metro network. To enhance computational efficiency, this study first employs the Dantzig-Wolfe decomposition method to transform the original formulation into a path-based model. Next, a branch-and-Benders cut approach is proposed to solve the problem. To strengthen the Benders cuts, we further develop a linear programming problem to generate the closest Benders cuts. The proposed approach is validated using a real-world case from the Beijing metro network, which comprises seven operating lines and 14 interchange stations. The computational results demonstrate that our proposed algorithms significantly outperform the commercial optimizer CPLEX. Moreover, the proposed operational modes reduce operating costs by up to 47.56 %, while passenger traveling costs decrease by as much as 4.34 %. The number of used train units decreases by up to 71.48 %.

随着大多数主要城市的地铁系统从单线发展到网络级运营，乘客的可达性显著提高。然而，由于换乘需求高，换乘站的压力增加。此外，乘客需求的不均衡分布给运营商带来了重大挑战。缓解转移问题和提高操作灵活性的一个有效策略是实施跨线操作。此外，灵活的列车组成模式为适应不平衡的乘客需求提供了一条有希望的途径。鉴于此，研究重点是考虑到跨线运营和灵活的列车组成模式，考虑乘客分配的线路规划问题。考虑到这些运营模式需要列车之间更紧密的合作，传统的线路规划公式变得不足。为了解决这一挑战，开发了一种利用聚合决策变量的新型数学模型来表示跨线和灵活的列车耦合和解耦操作。随后，我们将乘客分配问题制定为一个多商品流问题，有效地捕捉地铁网络中的乘客运动。为了提高计算效率，本研究首先采用dantzigg - wolfe分解方法将原始公式转化为基于路径的模型。其次，提出了一种分支弯管切割方法来解决这一问题。为了加强弯曲切口，我们进一步发展了一个线性规划问题，以产生最接近的弯曲切口。该方法通过北京地铁网络的实际案例进行了验证，该网络包括7条运营线路和14个换乘站。计算结果表明，我们提出的算法明显优于商用优化器CPLEX。此外，所提出的运营模式降低了高达47.56%的运营成本，而乘客出行成本降低了高达4.34%。使用的火车数量减少了71.48%。

{"title":"A line planning approach with passenger assignment considering cross-line operations and flexible train composition for a metro network","authors":"Zhikai Wang , Andrea D’Ariano , Shuai Su , Tao Tang , Boyi Su","doi":"10.1016/j.trc.2025.105489","DOIUrl":"10.1016/j.trc.2025.105489","url":null,"abstract":"<div><div>As metro systems in most major cities evolve from single-line to network-level operations, passenger accessibility improves significantly. However, interchange stations experience increased pressure due to high transfer demand. Additionally, the non-equilibrium distribution of passenger demand poses significant challenges for operators. One effective strategy to mitigate transfer issues and improve operational flexibility is the implementation of cross-line operations. Furthermore, the flexible train composition mode provides a promising avenue to accommodate imbalanced passenger demand. In light of this, the study focuses on the line planning problem with passenger assignment, considering cross-line operations and the flexible train composition mode. Given that these operational modes require closer cooperation among trains, traditional line planning formulations become inadequate. To tackle this challenge, a novel mathematical model utilizing aggregated decision variables is developed to represent cross-line and flexible train coupling and decoupling operations. Subsequently, we formulate the passenger assignment problem as a multi-commodity flow problem, which effectively captures passenger movements within the metro network. To enhance computational efficiency, this study first employs the Dantzig-Wolfe decomposition method to transform the original formulation into a path-based model. Next, a branch-and-Benders cut approach is proposed to solve the problem. To strengthen the Benders cuts, we further develop a linear programming problem to generate the closest Benders cuts. The proposed approach is validated using a real-world case from the Beijing metro network, which comprises seven operating lines and 14 interchange stations. The computational results demonstrate that our proposed algorithms significantly outperform the commercial optimizer CPLEX. Moreover, the proposed operational modes reduce operating costs by up to 47.56 %, while passenger traveling costs decrease by as much as 4.34 %. The number of used train units decreases by up to 71.48 %.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105489"},"PeriodicalIF":7.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145732482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Statistical inference of boarding and alighting counts in transit systems with incomplete data 数据不完全情况下交通系统上下车次数的统计推断

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-11 DOI: 10.1016/j.trc.2025.105484

Xiaoxu Chen , Marc-Olivier Thibault , Martin Trépanier , Lijun Sun

Automatic passenger counting (APC) systems have been widely used in public transit systems to collect boarding and alighting counts, which are essential for understanding travel demand, optimizing transit operations, and improving transit service quality. However, missing boarding and alighting counts remain a pervasive problem due to APC deployment, hardware malfunctions, or operational disruptions. The reconstruction of these missing data is particularly challenging because boarding and alighting counts must satisfy real-world constraints, such as balance conditions and onboard passenger limits. To address this issue, we propose a probabilistic framework that integrates passenger travel behavior and operational constraints to estimate missing boarding and alighting counts. The framework builds a time-varying Poisson model to estimate boarding demand and employs a method to infer time-varying alighting probabilities. Further, the alighting counts are derived by assigning estimated boarding counts to downstream stops with time-varying alighting probabilities, ensuring that the reconstructed data meet operational constraints. We validate the proposed framework using real-world transit data. The results demonstrate the method’s accuracy and robustness in estimating missing APC data, while also providing valuable insights into time-varying passenger travel behaviors, including arrival rates and alighting probabilities. This framework offers a practical and interpretable solution for reconstructing incomplete boarding and alighting data, with significant implications for improving transit planning and operational decision-making.

乘客自动计数系统（APC）广泛应用于公共交通系统中，对乘客上下车数量进行统计，对了解出行需求、优化公交运营、提高公交服务质量具有重要意义。然而，由于APC部署、硬件故障或操作中断，登机和下飞机数量丢失仍然是一个普遍的问题。重建这些丢失的数据尤其具有挑战性，因为登机和下车数量必须满足现实世界的限制，例如平衡条件和机上乘客限制。为了解决这个问题，我们提出了一个概率框架，该框架集成了乘客出行行为和操作约束，以估计错过登机和下飞机的数量。该框架建立时变泊松模型来估计登机需求，并采用时变下客概率推断方法。此外，通过将估计的上车次数分配给具有时变下车概率的下游站点，从而获得下车次数，确保重构数据满足操作约束。我们使用真实的交通数据验证了提出的框架。结果表明，该方法在估计APC缺失数据方面具有准确性和鲁棒性，同时还提供了对时变乘客出行行为（包括到达率和下飞机概率）的宝贵见解。该框架为重建不完整的上车和下车数据提供了一个实用且可解释的解决方案，对改善交通规划和运营决策具有重要意义。

{"title":"Statistical inference of boarding and alighting counts in transit systems with incomplete data","authors":"Xiaoxu Chen , Marc-Olivier Thibault , Martin Trépanier , Lijun Sun","doi":"10.1016/j.trc.2025.105484","DOIUrl":"10.1016/j.trc.2025.105484","url":null,"abstract":"<div><div>Automatic passenger counting (APC) systems have been widely used in public transit systems to collect boarding and alighting counts, which are essential for understanding travel demand, optimizing transit operations, and improving transit service quality. However, missing boarding and alighting counts remain a pervasive problem due to APC deployment, hardware malfunctions, or operational disruptions. The reconstruction of these missing data is particularly challenging because boarding and alighting counts must satisfy real-world constraints, such as balance conditions and onboard passenger limits. To address this issue, we propose a probabilistic framework that integrates passenger travel behavior and operational constraints to estimate missing boarding and alighting counts. The framework builds a time-varying Poisson model to estimate boarding demand and employs a method to infer time-varying alighting probabilities. Further, the alighting counts are derived by assigning estimated boarding counts to downstream stops with time-varying alighting probabilities, ensuring that the reconstructed data meet operational constraints. We validate the proposed framework using real-world transit data. The results demonstrate the method’s accuracy and robustness in estimating missing APC data, while also providing valuable insights into time-varying passenger travel behaviors, including arrival rates and alighting probabilities. This framework offers a practical and interpretable solution for reconstructing incomplete boarding and alighting data, with significant implications for improving transit planning and operational decision-making.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105484"},"PeriodicalIF":7.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145732480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trustworthy vehicular trajectory prediction under observational attacks: an adaptive and generalized defense framework for deep learning models 观察攻击下可信赖的飞行器轨迹预测：深度学习模型的自适应和广义防御框架

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-10 DOI: 10.1016/j.trc.2025.105486

Jialei Hu , Geqi Qi , Avishai (Avi) Ceder , Dianchen Zhu

Accurately and reliably predicting vehicle trajectories is critical for safe downstream decision-making. State-of-the-art Deep Learning (DL) models typically rely on historical trajectories recorded by onboard sensors. However, the common assumption that transmitted trajectories match ground truth is often violated due to observational attacks, which mislead DL models with corrupted inputs. Existing Training-Augmentation (TA) approaches attempt to improve robustness by injecting attacked samples into training, but they suffer from confidence issues and poor generalizability across diverse attacks due to their stochastic nature and causal confusion. To address these limitations, we propose an adaptive, generalized defense framework compatible with any DL model and trained only on normal (attack-free) data. The core idea is intuitive: output multimodal predictions under high uncertainty and otherwise follow a deterministic trajectory. We quantify epistemic uncertainty induced by observational attacks using a Bayesian Neural Network with entropy decomposition, where epistemic uncertainty reflects a model’s knowledge boundary and sensitivity to rare or unseen cases. Our defense employs a two-phase trajectory generation mechanism. Phase 1 estimates epistemic uncertainty and determines whether Phase 2 is triggered. If uncertainty exceeds a predefined threshold, Phase 2 generates multimodal trajectories by updating distributional parameters using both learned knowledge and training-independent physical priors, improving adaptability to dynamic attacks. Experiments demonstrate strong generalizability across multiple DL models and attack types. Ablation studies highlight the contributions of each component and parameter setting. Finally, case studies visualize scenarios where only Phase 1 or both phases are activated, providing further insight into the defense behavior.

准确、可靠地预测车辆轨迹对于安全的下游决策至关重要。最先进的深度学习（DL）模型通常依赖于机载传感器记录的历史轨迹。然而，由于观测攻击，传输轨迹与地面真实相匹配的共同假设经常被违反，这会误导带有损坏输入的DL模型。现有的训练增强（TA）方法试图通过将被攻击的样本注入训练中来提高鲁棒性，但由于它们的随机性和因果混淆，它们在不同的攻击中存在置信度问题和较差的泛化性。为了解决这些限制，我们提出了一种自适应的通用防御框架，该框架与任何深度学习模型兼容，并且仅在正常（无攻击）数据上进行训练。核心思想是直观的：在高不确定性下输出多模态预测，否则遵循确定性轨迹。我们使用带有熵分解的贝叶斯神经网络来量化由观测攻击引起的认知不确定性，其中认知不确定性反映了模型的知识边界和对罕见或未见情况的敏感性。我们的防御系统采用两阶段轨迹生成机制。阶段1估计认知的不确定性，并确定阶段2是否被触发。如果不确定性超过预定义的阈值，阶段2通过使用学习到的知识和与训练无关的物理先验更新分布参数来生成多模态轨迹，从而提高对动态攻击的适应性。实验证明了跨多个深度学习模型和攻击类型的强泛化性。消融研究强调了各组分和参数设置的贡献。最后，案例研究可视化了只有阶段1或两个阶段被激活的场景，提供了对防御行为的进一步了解。

{"title":"Trustworthy vehicular trajectory prediction under observational attacks: an adaptive and generalized defense framework for deep learning models","authors":"Jialei Hu , Geqi Qi , Avishai (Avi) Ceder , Dianchen Zhu","doi":"10.1016/j.trc.2025.105486","DOIUrl":"10.1016/j.trc.2025.105486","url":null,"abstract":"<div><div>Accurately and reliably predicting vehicle trajectories is critical for safe downstream decision-making. State-of-the-art Deep Learning (DL) models typically rely on historical trajectories recorded by onboard sensors. However, the common assumption that transmitted trajectories match ground truth is often violated due to observational attacks, which mislead DL models with corrupted inputs. Existing Training-Augmentation (TA) approaches attempt to improve robustness by injecting attacked samples into training, but they suffer from confidence issues and poor generalizability across diverse attacks due to their stochastic nature and causal confusion. To address these limitations, we propose an adaptive, generalized defense framework compatible with any DL model and trained only on normal (attack-free) data. The core idea is intuitive: output multimodal predictions under high uncertainty and otherwise follow a deterministic trajectory. We quantify epistemic uncertainty induced by observational attacks using a Bayesian Neural Network with entropy decomposition, where epistemic uncertainty reflects a model’s knowledge boundary and sensitivity to rare or unseen cases. Our defense employs a two-phase trajectory generation mechanism. Phase 1 estimates epistemic uncertainty and determines whether Phase 2 is triggered. If uncertainty exceeds a predefined threshold, Phase 2 generates multimodal trajectories by updating distributional parameters using both learned knowledge and training-independent physical priors, improving adaptability to dynamic attacks. Experiments demonstrate strong generalizability across multiple DL models and attack types. Ablation studies highlight the contributions of each component and parameter setting. Finally, case studies visualize scenarios where only Phase 1 or both phases are activated, providing further insight into the defense behavior.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105486"},"PeriodicalIF":7.6,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145732489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Game-theoretic incentives for federated learning in traffic prediction: Balancing resource allocation and prediction accuracy via Stackelberg contracts 交通预测中联邦学习的博弈论激励：通过Stackelberg契约平衡资源分配和预测精度

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-06 DOI: 10.1016/j.trc.2025.105474

Guowen Dai , Dong Ngoduy , Jinjun Tang , Chuyun Zhao

Federated learning-based traffic flow prediction has attracted growing interest in the field. Federated Learning (FL) provides a novel solution for privacy-preserving distributed training. However, designing a fair and efficient incentive mechanism to encourage collaboration among diverse participants remains a key challenge. This paper proposes an incentive mechanism for FL based on contract theory and the Stackelberg game. More specifically, our proposed method quantifies and differentiates rewards for participant contributions through contract design while using the Stackelberg game to balance resource allocation and profit competition between the server and participants. Additionally, this paper integrates an efficient local prediction model, WL-Transformer (Weighted Layer Transformer), to enhance participants’ local data modeling capabilities, thereby improving the accuracy and adaptability of the global model in traffic flow prediction tasks. Finally, experiments on the License Plate Recognition (LPR) dataset from Changsha, China, demonstrate the effectiveness of the proposed incentive mechanism in achieving high-accuracy traffic flow prediction.

基于联邦学习的交通流量预测已经引起了人们越来越多的兴趣。联邦学习（FL）为保护隐私的分布式训练提供了一种新的解决方案。然而，设计一个公平有效的激励机制来鼓励不同参与者之间的合作仍然是一个关键的挑战。本文提出了一种基于契约理论和Stackelberg博弈的FL激励机制。更具体地说，我们提出的方法通过契约设计量化和区分参与者贡献的奖励，同时使用Stackelberg博弈来平衡服务器和参与者之间的资源分配和利润竞争。此外，本文还集成了一种高效的局部预测模型WL-Transformer (Weighted Layer Transformer)，增强了参与者的局部数据建模能力，从而提高了全局模型在交通流预测任务中的准确性和适应性。最后，在中国长沙的车牌识别（LPR）数据集上进行实验，验证了所提出的激励机制在实现高精度交通流预测方面的有效性。

{"title":"Game-theoretic incentives for federated learning in traffic prediction: Balancing resource allocation and prediction accuracy via Stackelberg contracts","authors":"Guowen Dai , Dong Ngoduy , Jinjun Tang , Chuyun Zhao","doi":"10.1016/j.trc.2025.105474","DOIUrl":"10.1016/j.trc.2025.105474","url":null,"abstract":"<div><div>Federated learning-based traffic flow prediction has attracted growing interest in the field. Federated Learning (FL) provides a novel solution for privacy-preserving distributed training. However, designing a fair and efficient incentive mechanism to encourage collaboration among diverse participants remains a key challenge. This paper proposes an incentive mechanism for FL based on contract theory and the Stackelberg game. More specifically, our proposed method quantifies and differentiates rewards for participant contributions through contract design while using the Stackelberg game to balance resource allocation and profit competition between the server and participants. Additionally, this paper integrates an efficient local prediction model, WL-Transformer (Weighted Layer Transformer), to enhance participants’ local data modeling capabilities, thereby improving the accuracy and adaptability of the global model in traffic flow prediction tasks. Finally, experiments on the License Plate Recognition (LPR) dataset from Changsha, China, demonstrate the effectiveness of the proposed incentive mechanism in achieving high-accuracy traffic flow prediction.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105474"},"PeriodicalIF":7.6,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Demand-driven timetabling and vehicle scheduling optimization for electric bus transit lines 电动公交线路需求驱动调度与车辆调度优化

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-06 DOI: 10.1016/j.trc.2025.105482

Jinpeng Liang , Chenghao Zhuang , Haitao Liu , Ziyou Gao

Electric buses (EBs) have experienced rapid global expansion due to their substantial environmental and economic benefits. However, this transition presents new challenges for bus timetabling and vehicle scheduling, primarily arising from limited battery capacity and frequent charging requirements. This paper presents an integrated optimization framework for demand-driven timetabling and vehicle scheduling in EB transit lines that explicitly considers both passenger flow dynamics and battery constraints. We formulate a comprehensive mixed-integer programming (MIP) model using a space-time network representation to simultaneously optimize departure times, vehicle schedules, and passenger assignments. The objective function minimizes total costs, which encompass vehicle procurement, operational expenses, and passenger waiting times. To enhance computational efficiency, we reformulate the original MIP model into a path-based formulation and employ column generation (CG) techniques to decompose the problem into a restricted master problem (RMP) and pricing subproblems (PSP), which are solved iteratively. To obtain integer solutions, we develop a BP algorithm that integrates the CG procedure within a branch-and-bound framework. Computational experiments on both synthetic scenarios and a real-world case study demonstrate that our integrated approach achieves substantial reductions in overall costs and passenger waiting times compared to conventional two-stage optimization approaches that solve timetabling and vehicle scheduling sequentially.

电动巴士由于其巨大的环境和经济效益，在全球范围内迅速扩张。然而，这一转变对公交车调度和车辆调度提出了新的挑战，主要是由于有限的电池容量和频繁的充电要求。本文提出了一个综合优化框架，用于EB运输线路的需求驱动调度和车辆调度，该框架明确考虑了客流动力学和电池约束。我们制定了一个综合的混合整数规划（MIP）模型，使用时空网络表示来同时优化出发时间、车辆调度和乘客分配。目标函数使总成本最小化，包括车辆采购、运营费用和乘客等待时间。为了提高计算效率，我们将原始的MIP模型重新表述为基于路径的公式，并采用列生成（CG）技术将问题分解为受限主问题（RMP）和定价子问题（PSP），并迭代求解。为了获得整数解，我们开发了一种BP算法，该算法将CG过程集成在分支定界框架内。综合场景和实际案例研究的计算实验表明，与传统的两阶段优化方法相比，我们的综合方法大大降低了总成本和乘客等待时间，而传统的两阶段优化方法是依次解决时间表和车辆调度问题。

{"title":"Demand-driven timetabling and vehicle scheduling optimization for electric bus transit lines","authors":"Jinpeng Liang , Chenghao Zhuang , Haitao Liu , Ziyou Gao","doi":"10.1016/j.trc.2025.105482","DOIUrl":"10.1016/j.trc.2025.105482","url":null,"abstract":"<div><div>Electric buses (EBs) have experienced rapid global expansion due to their substantial environmental and economic benefits. However, this transition presents new challenges for bus timetabling and vehicle scheduling, primarily arising from limited battery capacity and frequent charging requirements. This paper presents an integrated optimization framework for demand-driven timetabling and vehicle scheduling in EB transit lines that explicitly considers both passenger flow dynamics and battery constraints. We formulate a comprehensive mixed-integer programming (MIP) model using a space-time network representation to simultaneously optimize departure times, vehicle schedules, and passenger assignments. The objective function minimizes total costs, which encompass vehicle procurement, operational expenses, and passenger waiting times. To enhance computational efficiency, we reformulate the original MIP model into a path-based formulation and employ column generation (CG) techniques to decompose the problem into a restricted master problem (RMP) and pricing subproblems (PSP), which are solved iteratively. To obtain integer solutions, we develop a BP algorithm that integrates the CG procedure within a branch-and-bound framework. Computational experiments on both synthetic scenarios and a real-world case study demonstrate that our integrated approach achieves substantial reductions in overall costs and passenger waiting times compared to conventional two-stage optimization approaches that solve timetabling and vehicle scheduling sequentially.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105482"},"PeriodicalIF":7.6,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

VLM-MPC: Model predictive controller augmented vision language model for autonomous driving VLM-MPC：自动驾驶模型预测控制器增强视觉语言模型

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-05 DOI: 10.1016/j.trc.2025.105487

Keke Long , Haotian Shi , Jiaxi Liu , Chaowei Xiao , Xiaopeng Li

Motivated by the emergent reasoning capabilities of Vision Language Models (VLMs) and their potential to improve the comprehensibility of autonomous driving systems, this paper introduces a closed-loop autonomous driving controller called VLM-MPC, which combines a VLM with Model Predictive Controller (MPC) to evaluate how model-based control could enhance VLM decision-making. The proposed VLM-MPC is structured into two asynchronous components: The upper level VLM generates driving parameters (e.g., desired speed, desired headway) for lower-level control based on front camera images, ego vehicle state, traffic environment conditions, and reference memory; The lower-level MPC controls the vehicle in real-time using these parameters, considering engine lag and providing state feedback to the entire system. Experiments based on the nuScenes dataset and Carla simulation validated the effectiveness of the proposed VLM-MPC across various environments (e.g., night, rain, fog, and intersections). The results demonstrate that the VLM-MPC consistently maintains Post Encroachment Time (PET) above safe thresholds, in contrast to some scenarios where the VLM-based control posed collision risks. Additionally, the VLM-MPC enhances smoothness compared to the real-world trajectories and VLM-based control. By comparing behaviors under different environmental settings, we highlight the VLM-MPC’s capability to understand the environment and make reasoned inferences. Moreover, we validate the contributions of two key components, the reference memory and the environment encoder, to the stability of responses through ablation tests.

基于视觉语言模型（VLM）的紧急推理能力及其提高自动驾驶系统可理解性的潜力，本文介绍了一种称为VLM-MPC的闭环自动驾驶控制器，该控制器将VLM与模型预测控制器（MPC）相结合，以评估基于模型的控制如何增强VLM决策。所提出的VLM- mpc结构分为两个异步组件：上层VLM根据前置摄像头图像、自我车辆状态、交通环境条件和参考存储器为下层控制生成驾驶参数（例如，期望速度、期望车头时距）；低级MPC使用这些参数实时控制车辆，考虑发动机滞后并向整个系统提供状态反馈。基于nuScenes数据集和Carla模拟的实验验证了所提出的VLM-MPC在各种环境（例如，夜晚、雨、雾和十字路口）中的有效性。结果表明，在某些情况下，VLM-MPC控制会造成碰撞风险，而VLM-MPC控制则会将后侵占时间（PET）保持在安全阈值以上。此外，与实际轨迹和基于vlm的控制相比，VLM-MPC提高了平滑度。通过比较不同环境下的行为，我们突出了VLM-MPC对环境的理解能力和推理能力。此外，我们还通过烧蚀测试验证了参考存储器和环境编码器这两个关键组件对响应稳定性的贡献。

{"title":"VLM-MPC: Model predictive controller augmented vision language model for autonomous driving","authors":"Keke Long , Haotian Shi , Jiaxi Liu , Chaowei Xiao , Xiaopeng Li","doi":"10.1016/j.trc.2025.105487","DOIUrl":"10.1016/j.trc.2025.105487","url":null,"abstract":"<div><div>Motivated by the emergent reasoning capabilities of Vision Language Models (VLMs) and their potential to improve the comprehensibility of autonomous driving systems, this paper introduces a closed-loop autonomous driving controller called VLM-MPC, which combines a VLM with Model Predictive Controller (MPC) to evaluate how model-based control could enhance VLM decision-making. The proposed VLM-MPC is structured into two asynchronous components: The upper level VLM generates driving parameters (e.g., desired speed, desired headway) for lower-level control based on front camera images, ego vehicle state, traffic environment conditions, and reference memory; The lower-level MPC controls the vehicle in real-time using these parameters, considering engine lag and providing state feedback to the entire system. Experiments based on the nuScenes dataset and Carla simulation validated the effectiveness of the proposed VLM-MPC across various environments (e.g., night, rain, fog, and intersections). The results demonstrate that the VLM-MPC consistently maintains Post Encroachment Time (PET) above safe thresholds, in contrast to some scenarios where the VLM-based control posed collision risks. Additionally, the VLM-MPC enhances smoothness compared to the real-world trajectories and VLM-based control. By comparing behaviors under different environmental settings, we highlight the VLM-MPC’s capability to understand the environment and make reasoned inferences. Moreover, we validate the contributions of two key components, the reference memory and the environment encoder, to the stability of responses through ablation tests.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105487"},"PeriodicalIF":7.6,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synthetic data generation for joint electric vehicle driving and charging events via deep generative networks 基于深度生成网络的电动汽车行驶与充电联合事件综合数据生成

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-05 DOI: 10.1016/j.trc.2025.105481

Zhi Li , Wei Ma , Monica Menendez , Zhibin Chen , Minghui Zhong

The rapid growth of the global electric vehicle (EV) market has generated vast amounts of real-time data through smart vehicle devices, capturing detailed EV behavioral patterns, including spatiotemporal charging distribution, electricity consumption, origin-destination (OD) driving trajectories, and parking dynamics. This data offers transformative potential for refining transportation policy, strategically deploying charging infrastructure, and facilitating vehicle-to-grid (V2G) energy integration.

Recent advances in generative modeling offer solutions by creating synthetic datasets that maintain data utility while protecting privacy. However, existing studies often lack detailed joint generation of driving and charging events and are less effective in handling highly dependent and constrained event variables. To address these gaps, we propose a joint EV driving and charging model for generating large-scale spatiotemporal behavior data by combining Transformer architecture and Gibbs sampling, leveraging 15 months of data from 3777 EVs in Shanghai, China. Our model effectively captures inter-feature and temporal dependencies, enabling scenario-based data generation while addressing privacy challenges. Our codebase, pre-trained model, and synthetic dataset are publicly available at: https://github.com/zhilee2023/EV-drive-charge-data-gen

全球电动汽车（EV）市场的快速增长，通过智能汽车设备产生了大量实时数据，捕获了详细的电动汽车行为模式，包括时空充电分布、用电量、始发目的地（OD）驾驶轨迹和停车动态。这些数据为完善交通政策、战略性部署充电基础设施和促进车辆到电网（V2G）能源整合提供了变革性的潜力。生成建模的最新进展通过创建合成数据集来提供解决方案，这些数据集在保护隐私的同时保持数据效用。然而，现有的研究往往缺乏详细的驾驶和充电事件的联合生成，并且在处理高度依赖和约束的事件变量方面效果较差。为了解决这些差距，我们提出了一个联合的电动汽车驾驶和充电模型，通过结合Transformer架构和Gibbs采样，利用中国上海3777辆电动汽车15个月的数据来生成大规模的时空行为数据。我们的模型有效地捕获了功能间和时间依赖性，在解决隐私挑战的同时，支持基于场景的数据生成。我们的代码库、预训练模型和合成数据集可以在https://github.com/zhilee2023/EV-drive-charge-data-gen上公开获取

{"title":"Synthetic data generation for joint electric vehicle driving and charging events via deep generative networks","authors":"Zhi Li , Wei Ma , Monica Menendez , Zhibin Chen , Minghui Zhong","doi":"10.1016/j.trc.2025.105481","DOIUrl":"10.1016/j.trc.2025.105481","url":null,"abstract":"<div><div>The rapid growth of the global electric vehicle (EV) market has generated vast amounts of real-time data through smart vehicle devices, capturing detailed EV behavioral patterns, including spatiotemporal charging distribution, electricity consumption, origin-destination (OD) driving trajectories, and parking dynamics. This data offers transformative potential for refining transportation policy, strategically deploying charging infrastructure, and facilitating vehicle-to-grid (V2G) energy integration.</div><div>Recent advances in generative modeling offer solutions by creating synthetic datasets that maintain data utility while protecting privacy. However, existing studies often lack detailed joint generation of driving and charging events and are less effective in handling highly dependent and constrained event variables. To address these gaps, we propose a joint EV driving and charging model for generating large-scale spatiotemporal behavior data by combining Transformer architecture and Gibbs sampling, leveraging 15 months of data from 3777 EVs in Shanghai, China. Our model effectively captures inter-feature and temporal dependencies, enabling scenario-based data generation while addressing privacy challenges. Our codebase, pre-trained model, and synthetic dataset are publicly available at: <span><span>https://github.com/zhilee2023/EV-drive-charge-data-gen</span><svg><path></path></svg></span></div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105481"},"PeriodicalIF":7.6,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimising toll prices based on a dynamic multi-region MFD SUE traffic model: formulation and a case study of Zealand, Denmark 基于动态多区域MFD SUE交通模型的收费价格优化：丹麦新西兰的公式和案例研究

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-04 DOI: 10.1016/j.trc.2025.105432

Lawrence Christopher Duncan , Thomas Kjær Rasmussen , David Paul Watling , Ravi Seshadri

Road use tolling is an effective way of alleviating congestion. Although many tolling models have been developed, there is gap in the research for a model that: i) is dynamic, ii) accounts for the impacts of tolls on travel demand and departure time choice, iii) accounts for stochasticity in travellers’ route choices, iv) is well-behaved, producing continuous outputs, and v) is computationally feasible to apply to real-life large-scale networks. This paper fills this gap, by developing a tolling model based on the dynamic multi-region Macroscopic Fundamental Diagram (MFD) Stochastic User Equilibrium (SUE) traffic model introduced in Duncan et al. (2025). We begin by extending the model to account for elastic demand and departure time choice. Then, we integrate the model within a toll-price optimisation framework, where the tolling scheme is travel-time-based and the objective function maximises social welfare. We first test the model in a small-scale example multi-region MFD system, and then apply it to estimate an optimal toll-price in a real-life large-scale and detailed case study of Zealand, Denmark. Experiments find that the model is well-behaved and produces smooth objective function surfaces with a unique maximum. Travel behaviour implications of tolling are also realistic, where some travellers opt not to travel by car, some change their departure time, and some change their route. Results suggest that tolling could instigate a positive change in travel behaviour to benefit society.

道路使用收费是缓解交通拥堵的有效途径。虽然已经开发了许多收费模型，但对于一个模型的研究存在空白：i)是动态的，ii)考虑了收费对旅行需求和出发时间选择的影响，iii)考虑了旅行者路线选择的随机性，iv)表现良好，产生连续输出，v)计算上可行，适用于现实生活中的大规模网络。本文填补了这一空白，通过开发基于Duncan等人（2025）引入的动态多区域宏观基本图（MFD）随机用户均衡（SUE）交通模型的收费模型。我们首先扩展模型以考虑弹性需求和出发时间选择。然后，我们将模型整合到收费优化框架中，其中收费方案是基于旅行时间的，目标函数是最大化社会福利。我们首先在一个小规模的多区域MFD系统中测试了该模型，然后将其应用于丹麦西兰的一个实际的大规模和详细的案例研究中来估计最优收费。实验结果表明，该模型性能良好，能产生具有唯一最大值的光滑目标函数曲面。收费对旅行行为的影响也是现实的，有些旅行者选择不开车旅行，有些人改变出发时间，有些人改变路线。研究结果表明，收费可以激发出行行为的积极变化，从而造福社会。

{"title":"Optimising toll prices based on a dynamic multi-region MFD SUE traffic model: formulation and a case study of Zealand, Denmark","authors":"Lawrence Christopher Duncan , Thomas Kjær Rasmussen , David Paul Watling , Ravi Seshadri","doi":"10.1016/j.trc.2025.105432","DOIUrl":"10.1016/j.trc.2025.105432","url":null,"abstract":"<div><div>Road use tolling is an effective way of alleviating congestion. Although many tolling models have been developed, there is gap in the research for a model that: i) is dynamic, ii) accounts for the impacts of tolls on travel demand and departure time choice, iii) accounts for stochasticity in travellers’ route choices, iv) is well-behaved, producing continuous outputs, and v) is computationally feasible to apply to real-life large-scale networks. This paper fills this gap, by developing a tolling model based on the dynamic multi-region Macroscopic Fundamental Diagram (MFD) Stochastic User Equilibrium (SUE) traffic model introduced in Duncan et al. (2025). We begin by extending the model to account for elastic demand and departure time choice. Then, we integrate the model within a toll-price optimisation framework, where the tolling scheme is travel-time-based and the objective function maximises social welfare. We first test the model in a small-scale example multi-region MFD system, and then apply it to estimate an optimal toll-price in a real-life large-scale and detailed case study of Zealand, Denmark. Experiments find that the model is well-behaved and produces smooth objective function surfaces with a unique maximum. Travel behaviour implications of tolling are also realistic, where some travellers opt not to travel by car, some change their departure time, and some change their route. Results suggest that tolling could instigate a positive change in travel behaviour to benefit society.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105432"},"PeriodicalIF":7.6,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Early detection of traffic flow breakdown at highway bottleneck using section-based transitional instability 基于路段过渡不稳定性的公路瓶颈交通流故障早期检测

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-04 DOI: 10.1016/j.trc.2025.105483

Hyeyoung Tak, Hwasoo Yeo

Traffic flow breakdowns refer to abrupt transitions from free-flow to congested conditions, typically occurring at freeway bottlenecks. Due to their sudden onset and the complex interactions driving them, early detection remains a challenging task in traffic operations. These events are often preceded by a transitional state—referred to as the pre-breakdown state—during which traffic conditions exhibit growing instability. Most existing studies define breakdowns using threshold-based criteria such as a sudden shift in speed at a single detector. Although such point-based methods can capture local changes, they often fail to reflect broader spatial interactions across adjacent sections. This study proposes a section-based framework that jointly analyzes upstream and downstream conditions to capture the spatial heterogeneity within a segment. A composite metric, the Dynamic Instability Score (DIS), is introduced to quantify sectional instability based on short-term temporal responsiveness and spatial imbalance. The methodology includes traffic state identification, DIS computation, and early warning detection. The DIS is calibrated using ROC-based thresholding at the boundary between free-flow and transitional states, ensuring sensitivity to early instability while minimizing false alarms. Empirical evaluations on freeway segments with recurrent bottlenecks demonstrate that DIS serves as a reliable leading indicator. Compared to point-based measures, it achieves higher accuracy and lower false-alarm rates, while preserving practical lead times. These results highlight the importance of capturing transitional instability during the pre-breakdown state and support the use of section-based indicators for proactive congestion management.

交通流中断是指从自由流动到拥堵状态的突然转变，通常发生在高速公路的瓶颈处。由于其突发性和复杂的相互作用，在交通运行中早期检测仍然是一项具有挑战性的任务。在这些事件发生之前，通常会有一个过渡状态，即故障前状态，在此期间，交通状况表现出越来越大的不稳定性。大多数现有的研究使用基于阈值的标准来定义故障，例如单个检测器的速度突然变化。虽然这种基于点的方法可以捕捉局部变化，但它们往往不能反映相邻区域之间更广泛的空间相互作用。本研究提出了一个基于区域的框架，通过对上游和下游条件的联合分析来捕捉区域内的空间异质性。采用动态不稳定性评分（DIS）这一复合指标来量化基于短期时间响应性和空间不平衡的截面不稳定性。方法包括交通状态识别、DIS计算和早期预警检测。DIS在自由流动和过渡状态之间的边界使用基于roc的阈值进行校准，确保对早期不稳定的敏感性，同时最大限度地减少误报。对高速公路经常性瓶颈路段的实证评价表明，DIS可作为可靠的先行指标。与基于点的测量相比，它实现了更高的准确性和更低的误报率，同时保留了实际的交货时间。这些结果强调了在故障前状态捕捉过渡不稳定性的重要性，并支持使用基于路段的指标进行主动拥堵管理。

{"title":"Early detection of traffic flow breakdown at highway bottleneck using section-based transitional instability","authors":"Hyeyoung Tak, Hwasoo Yeo","doi":"10.1016/j.trc.2025.105483","DOIUrl":"10.1016/j.trc.2025.105483","url":null,"abstract":"<div><div>Traffic flow breakdowns refer to abrupt transitions from free-flow to congested conditions, typically occurring at freeway bottlenecks. Due to their sudden onset and the complex interactions driving them, early detection remains a challenging task in traffic operations. These events are often preceded by a transitional state—referred to as the pre-breakdown state—during which traffic conditions exhibit growing instability. Most existing studies define breakdowns using threshold-based criteria such as a sudden shift in speed at a single detector. Although such point-based methods can capture local changes, they often fail to reflect broader spatial interactions across adjacent sections. This study proposes a section-based framework that jointly analyzes upstream and downstream conditions to capture the spatial heterogeneity within a segment. A composite metric, the Dynamic Instability Score (DIS), is introduced to quantify sectional instability based on short-term temporal responsiveness and spatial imbalance. The methodology includes traffic state identification, DIS computation, and early warning detection. The DIS is calibrated using ROC-based thresholding at the boundary between free-flow and transitional states, ensuring sensitivity to early instability while minimizing false alarms. Empirical evaluations on freeway segments with recurrent bottlenecks demonstrate that DIS serves as a reliable leading indicator. Compared to point-based measures, it achieves higher accuracy and lower false-alarm rates, while preserving practical lead times. These results highlight the importance of capturing transitional instability during the pre-breakdown state and support the use of section-based indicators for proactive congestion management.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105483"},"PeriodicalIF":7.6,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Real-time traffic simulation and management for large-scale urban air mobility: Integrating route guidance and collision avoidance 大规模城市空中交通的实时交通模拟与管理：融合路线引导与避碰

IF 7.6 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2025-12-04 DOI: 10.1016/j.trc.2025.105477

Canqiang Weng , Can Chen , Jingjun Tan , Tianlu Pan , Renxin Zhong

With a vision to expand transportation supply using low-altitude airspace, urban air mobility (UAM) has emerged as a promising alternative to provide point-to-point travel in congested areas. The rapid development of electric vertical take-off and landing vehicles is expected to make UAM a viable and sustainable transportation mode. Given the spatial heterogeneity of land use patterns in most cities, large-scale UAM deployments will likely focus on specific areas, such as intertransfer traffic between suburbs and city centers. However, large-scale UAM operations connecting multiple origin-destination pairs raise concerns about air traffic safety and efficiency due to potential conflict movements, particularly at major conflict points analogous to roadway junctions. To meet the safety and efficiency requirements of future UAM operations, this work proposes an air traffic management framework that integrates route guidance and collision avoidance. The route guidance mechanism optimizes aircraft distribution across both spatial and temporal dimensions by regulating their paths (composed of waypoints). Given the optimized paths, the collision avoidance algorithm generates collision-free aircraft trajectories between waypoints in the 3D space. To enable large-scale applications, we develop fast approximation methods for centralized path planning and adopt the velocity obstacle model for distributed collision avoidance. To our knowledge, this work is one of the first to integrate route guidance and collision avoidance for UAM. Simulation results demonstrate that the proposed framework enables efficient and flexible UAM operations, including air traffic assignment, local congestion mitigation, and dynamic no-fly zone management. Compared with a collision-free baseline strategy, the proposed framework achieves considerable improvements in traffic safety and efficiency, with increases in the average minimum separation (+98.2 %), the average travel speed (+70.2 %), and the trip completion rate (+130 %), along with a reduction in the energy consumption (-23.0 %). The proposed framework demonstrates its potential for real-time traffic simulation and management in large-scale UAM systems.

为了利用低空空域扩大交通运输供应，城市空中交通（UAM）已经成为在拥挤地区提供点对点交通的一种有前途的替代方案。电动垂直起降车辆的快速发展有望使UAM成为一种可行且可持续的交通方式。考虑到大多数城市土地利用模式的空间异质性，大规模的UAM部署可能会集中在特定区域，例如郊区和市中心之间的中转交通。然而，连接多个始发目的地对的大规模UAM操作，由于潜在的冲突运动，特别是在类似于道路路口的主要冲突点，引起了对空中交通安全和效率的担忧。为了满足未来UAM运营的安全和效率要求，本工作提出了一个集成路线引导和避免碰撞的空中交通管理框架。航线引导机制通过调节飞机的路径（由航路点组成）来优化飞机在空间和时间维度上的分布。给出优化后的路径，避碰算法生成3D空间中航路点之间的无碰撞飞机轨迹。为了实现大规模应用，我们开发了集中路径规划的快速逼近方法，并采用速度障碍模型进行分布式避碰。据我们所知，这项工作是首次将UAM的路线引导和避碰结合起来的工作之一。仿真结果表明，该框架能够实现高效灵活的UAM操作，包括空中交通分配、局部拥堵缓解和动态禁飞区管理。与无碰撞基线策略相比，所提出的框架在交通安全和效率方面取得了相当大的改善，平均最小间隔（+ 98.2%）、平均行驶速度（+ 70.2%）和行程完成率（+ 130%）均有所提高，同时能耗降低（- 23.0%）。所提出的框架展示了其在大规模UAM系统中实时交通模拟和管理的潜力。

{"title":"Real-time traffic simulation and management for large-scale urban air mobility: Integrating route guidance and collision avoidance","authors":"Canqiang Weng , Can Chen , Jingjun Tan , Tianlu Pan , Renxin Zhong","doi":"10.1016/j.trc.2025.105477","DOIUrl":"10.1016/j.trc.2025.105477","url":null,"abstract":"<div><div>With a vision to expand transportation supply using low-altitude airspace, urban air mobility (UAM) has emerged as a promising alternative to provide point-to-point travel in congested areas. The rapid development of electric vertical take-off and landing vehicles is expected to make UAM a viable and sustainable transportation mode. Given the spatial heterogeneity of land use patterns in most cities, large-scale UAM deployments will likely focus on specific areas, such as intertransfer traffic between suburbs and city centers. However, large-scale UAM operations connecting multiple origin-destination pairs raise concerns about air traffic safety and efficiency due to potential conflict movements, particularly at major conflict points analogous to roadway junctions. To meet the safety and efficiency requirements of future UAM operations, this work proposes an air traffic management framework that integrates route guidance and collision avoidance. The route guidance mechanism optimizes aircraft distribution across both spatial and temporal dimensions by regulating their paths (composed of waypoints). Given the optimized paths, the collision avoidance algorithm generates collision-free aircraft trajectories between waypoints in the 3D space. To enable large-scale applications, we develop fast approximation methods for centralized path planning and adopt the velocity obstacle model for distributed collision avoidance. To our knowledge, this work is one of the first to integrate route guidance and collision avoidance for UAM. Simulation results demonstrate that the proposed framework enables efficient and flexible UAM operations, including air traffic assignment, local congestion mitigation, and dynamic no-fly zone management. Compared with a collision-free baseline strategy, the proposed framework achieves considerable improvements in traffic safety and efficiency, with increases in the average minimum separation (+98.2 %), the average travel speed (+70.2 %), and the trip completion rate (+130 %), along with a reduction in the energy consumption (-23.0 %). The proposed framework demonstrates its potential for real-time traffic simulation and management in large-scale UAM systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"183 ","pages":"Article 105477"},"PeriodicalIF":7.6,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0