Transportation Research Part C-Emerging Technologies最新文献

英文中文

Developing a personalised end-to-end optimisation algorithm for smart parking systems 为智能停车系统开发个性化的端到端优化算法

IF 8.3 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-02-06 DOI: 10.1016/j.trc.2026.105548

Jingshuo Qiu, Yuxiang Feng, Simon Dale, Mohammed Quddus, Mireille Elhajj, Washington Yotto Ochieng

引用次数: 0

Towards unified estimation and calibration in transport models: Integrating micro-level behaviour and macro-level performance 迈向运输模型的统一估计和校准：整合微观层面的行为和宏观层面的表现

IF 8.3 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-02-05 DOI: 10.1016/j.trc.2026.105514

Ali Najmi, Michel Bierlaire, Travis Waller, Taha H. Rashidi

引用次数: 0

An agent-based approach for travel mode choice equilibrium problem in MaaS considering heterogeneous users 考虑异构用户的MaaS中基于agent的出行方式选择均衡问题

IF 8.3 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-02-04 DOI: 10.1016/j.trc.2026.105534

Yifan Zhang, Meng Xu, Wenxiang Wu

引用次数: 0

Multi-agent reinforcement learning with a hybrid sequential reward feedback strategy for dynamic multi-modal traffic assignment 基于混合顺序奖励反馈策略的多智能体强化学习用于动态多模式交通分配

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

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-02-03 DOI: 10.1016/j.trc.2026.105545

Dongyue Cun , Muqing Du , Lin Cheng , Anthony Chen

Urbanization and the expansion of transportation modes have exacerbated the challenges of understanding travelers’ decision-making processes regarding route choice across various transportation modes. This paper proposes a novel macroscopic hybrid sequential game method using multi-agent reinforcement learning (MARL) to address issues of computational efficiency and behavioral complexity in multi-modal transportation network simulations. Specifically, agents’ perception behaviors are modeled as a sequential decision-making process considering road capacity constraints, which helps estimate travel time under congestion effects in the multi-modal traffic assignment. In addition, a hybrid reward framework is proposed, providing system-level reward to guide the multi-agent system towards different Nash equilibria, thereby reducing policy fluctuations. To simulate interactions between agents of different transportation modes, a multi-edge representation and reward structures designed for car, bus, priority bus, and metro modes are adopted to handle the mixed traffic flow through the same road. Furthermore, our approach uses a mean-field multi-agent deep Q-learning method to consider both mode and route choice, simplifying agent interactions through mean-field theory and clustering agents with the same origin–destination (OD) demands. Experimental results demonstrate that the hybrid sequential feedback strategy outperforms the simultaneous feedback strategy regarding convergence speed, agent reward distribution, and network flow distribution. Furthermore, the proposed method is tested on the Sioux-Falls network to verify its computational efficiency in three network change scenarios (disruption, road reconstruction, and new road construction). These findings highlight the potential of the proposed MARL method for large-scale multi-modal transportation network analysis, particularly under various incident scenarios, providing an effective tool for urban transportation planning and project evaluation.

城市化和交通方式的扩张加剧了理解旅行者在不同交通方式下的路线选择决策过程的挑战。本文提出了一种基于多智能体强化学习（MARL）的宏观混合序列博弈方法，以解决多式联运网络仿真中的计算效率和行为复杂性问题。具体而言，将智能体的感知行为建模为考虑道路容量约束的顺序决策过程，有助于在多模式交通分配中估计拥堵效应下的出行时间。此外，提出了一种混合奖励框架，提供系统级奖励，引导多智能体系统走向不同的纳什均衡，从而减少策略波动。为了模拟不同交通方式智能体之间的交互作用，采用针对汽车、公交、优先公交和地铁等交通方式设计的多边缘表示和奖励结构来处理通过同一道路的混合交通流。此外，我们的方法使用平均场多智能体深度q -学习方法来考虑模式和路径选择，通过平均场理论和具有相同起点-目的地（OD）需求的聚类智能体简化智能体交互。实验结果表明，混合顺序反馈策略在收敛速度、智能体奖励分配和网络流量分配方面都优于同步反馈策略。并在苏-福尔斯网络上进行了测试，验证了该方法在三种网络变化场景（中断、道路重建和新建道路）下的计算效率。这些发现突出了提出的MARL方法在大规模多式联运网络分析中的潜力，特别是在各种事件情景下，为城市交通规划和项目评估提供了有效的工具。

{"title":"Multi-agent reinforcement learning with a hybrid sequential reward feedback strategy for dynamic multi-modal traffic assignment","authors":"Dongyue Cun , Muqing Du , Lin Cheng , Anthony Chen","doi":"10.1016/j.trc.2026.105545","DOIUrl":"10.1016/j.trc.2026.105545","url":null,"abstract":"<div><div>Urbanization and the expansion of transportation modes have exacerbated the challenges of understanding travelers’ decision-making processes regarding route choice across various transportation modes. This paper proposes a novel macroscopic hybrid sequential game method using multi-agent reinforcement learning (MARL) to address issues of computational efficiency and behavioral complexity in multi-modal transportation network simulations. Specifically, agents’ perception behaviors are modeled as a sequential decision-making process considering road capacity constraints, which helps estimate travel time under congestion effects in the multi-modal traffic assignment. In addition, a hybrid reward framework is proposed, providing system-level reward to guide the multi-agent system towards different Nash equilibria, thereby reducing policy fluctuations. To simulate interactions between agents of different transportation modes, a multi-edge representation and reward structures designed for car, bus, priority bus, and metro modes are adopted to handle the mixed traffic flow through the same road. Furthermore, our approach uses a mean-field multi-agent deep Q-learning method to consider both mode and route choice, simplifying agent interactions through mean-field theory and clustering agents with the same origin–destination (OD) demands. Experimental results demonstrate that the hybrid sequential feedback strategy outperforms the simultaneous feedback strategy regarding convergence speed, agent reward distribution, and network flow distribution. Furthermore, the proposed method is tested on the Sioux-Falls network to verify its computational efficiency in three network change scenarios (disruption, road reconstruction, and new road construction). These findings highlight the potential of the proposed MARL method for large-scale multi-modal transportation network analysis, particularly under various incident scenarios, providing an effective tool for urban transportation planning and project evaluation.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"185 ","pages":"Article 105545"},"PeriodicalIF":7.6,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102562","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 identification of cooperative perception necessity in road traffic scenarios 道路交通场景中协同感知必要性的实时识别

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

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-02-03 DOI: 10.1016/j.trc.2026.105547

Chengyuan Ma , Hangyu Li , Keke Long , Hang Zhou , Zhaohui Liang , Pei Li , Hongkai Yu , Xiaopeng Li

Cooperative perception (CP) has shown great potential in enhancing traffic safety with Vehicle-to-Everything (V2X) communications. However, its substantial communication burden makes resource-efficient CP crucial, especially when a single vehicle’s intelligence with adequate perception is sufficient to handle most traffic scenarios. Therefore, to reduce the resource consumption of CP, it is essential to identify the traffic conditions under which CP should be applied. This paper addresses this issue by identifying the necessity of CP among road users, and evaluating whether their sensory information is adequate for ensuring traffic safety. We propose a practical framework to assess CP necessity by leveraging bird’s-eye view data from roadside cameras. The framework begins with video-based object localization and tracking to identify the position and movement of each road user. Next, we use a stochastic motion prediction model to analyze the collision risks between pairs of road users. Simultaneously, pairwise perception analysis is used to assess the probability of one road user perceiving another, determining if a road user falls within a blind spot. Road users with both collision risk and potential perception blind spots are identified as requiring CP. Field tests are conducted using real-world scenarios at two complex intersections in Madison, WI, which include a diverse range of road users, such as various vehicles and vulnerable pedestrians and cyclists. The results demonstrate that the proposed framework can effectively identify the safety-challenging scenarios that require CP in complex traffic environments. With only 0.1% of situations in our field test requiring CP, implementing the proposed framework can save a significant amount of communication bandwidth and computational costs while ensuring the same level of safety. Our code and data will be made available upon the acceptance of this paper.

协同感知（CP）在车辆与万物（V2X）通信中显示出巨大的潜力，可以提高交通安全。然而，其巨大的通信负担使得资源高效的CP至关重要，特别是当单个车辆具有足够感知能力的智能足以处理大多数交通场景时。因此，为了减少CP的资源消耗，确定应用CP的交通条件是至关重要的。本文通过识别道路使用者CP的必要性，并评估他们的感官信息是否足以确保交通安全来解决这个问题。我们提出了一个实用的框架，通过利用路边摄像头的鸟瞰数据来评估CP的必要性。该框架从基于视频的对象定位和跟踪开始，以识别每个道路使用者的位置和运动。接下来，我们使用随机运动预测模型来分析道路使用者对之间的碰撞风险。同时，两两感知分析用于评估一个道路使用者感知另一个道路使用者的概率，确定道路使用者是否处于盲点内。同时存在碰撞风险和潜在感知盲点的道路使用者被确定为需要CP。在威斯康辛州麦迪逊的两个复杂十字路口，使用真实场景进行了现场测试，其中包括各种各样的道路使用者，如各种车辆、脆弱的行人和骑自行车的人。结果表明，该框架能够有效识别复杂交通环境中需要CP的安全挑战场景。在我们的现场测试中，只有0.1%的情况需要CP，实施提议的框架可以节省大量的通信带宽和计算成本，同时确保相同的安全水平。我们的代码和数据将在本文被接受后提供。

{"title":"Real-time identification of cooperative perception necessity in road traffic scenarios","authors":"Chengyuan Ma , Hangyu Li , Keke Long , Hang Zhou , Zhaohui Liang , Pei Li , Hongkai Yu , Xiaopeng Li","doi":"10.1016/j.trc.2026.105547","DOIUrl":"10.1016/j.trc.2026.105547","url":null,"abstract":"<div><div>Cooperative perception (CP) has shown great potential in enhancing traffic safety with Vehicle-to-Everything (V2X) communications. However, its substantial communication burden makes resource-efficient CP crucial, especially when a single vehicle’s intelligence with adequate perception is sufficient to handle most traffic scenarios. Therefore, to reduce the resource consumption of CP, it is essential to identify the traffic conditions under which CP should be applied. This paper addresses this issue by identifying the necessity of CP among road users, and evaluating whether their sensory information is adequate for ensuring traffic safety. We propose a practical framework to assess CP necessity by leveraging bird’s-eye view data from roadside cameras. The framework begins with video-based object localization and tracking to identify the position and movement of each road user. Next, we use a stochastic motion prediction model to analyze the collision risks between pairs of road users. Simultaneously, pairwise perception analysis is used to assess the probability of one road user perceiving another, determining if a road user falls within a blind spot. Road users with both collision risk and potential perception blind spots are identified as requiring CP. Field tests are conducted using real-world scenarios at two complex intersections in Madison, WI, which include a diverse range of road users, such as various vehicles and vulnerable pedestrians and cyclists. The results demonstrate that the proposed framework can effectively identify the safety-challenging scenarios that require CP in complex traffic environments. With only 0.1% of situations in our field test requiring CP, implementing the proposed framework can save a significant amount of communication bandwidth and computational costs while ensuring the same level of safety. Our code and data will be made available upon the acceptance of this paper.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"185 ","pages":"Article 105547"},"PeriodicalIF":7.6,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102561","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

Corrigendum to “A line planning approach with passenger assignment considering cross-line operations and flexible train composition for a metro network” [Transp. Res. Part C: Emerg. Technol. 183 (2026) 105489] “考虑地铁网络跨线运营和灵活列车组成的乘客分配的线路规划方法”的勘误表。C部分：紧急情况科技。183 (2026)105489]

IF 8.3 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-02-02 DOI: 10.1016/j.trc.2026.105544

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

引用次数: 0

Corrigendum to “The VCG pricing policy with unit reserve prices for ride-sourcing is 3 4 -incentive compatibility” [Transp. Res. Part C: Emerg. Technol. 171 (2025) 104991] “以单位保留价格为乘车资源的VCG定价政策是34 -激励兼容”的勘误表[运输。C部分：紧急情况科技。171 (2025)104991]

IF 8.3 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-02-01 DOI: 10.1016/j.trc.2026.105543

Ruijie Li, Haiyuan Chen, Xiaobo Liu, Kenan Zhang

引用次数: 0

Vertical federated learning for transport mode detection using multi-modality data 使用多模态数据进行传输模式检测的垂直联合学习

IF 8.3 1区工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-02-01 DOI: 10.1016/j.trc.2026.105546

Ningkang Yang, Ramandeep Singh, Oleksandr Shtykalo, Iuliia Yamnenko, Constantinos Antoniou

引用次数: 0

NeuralMOVES: A lightweight and microscopic vehicle emission estimation model based on reverse engineering and surrogate learning NeuralMOVES：一种基于逆向工程和代理学习的轻型微观车辆排放估计模型

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

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-01-31 DOI: 10.1016/j.trc.2026.105530

Edgar Ramirez-Sanchez , Catherine Tang , Yaosheng Xu , Nrithya Renganathan , Vindula Jayawardana , Zhengbing He , Cathy Wu

The transportation sector accounts for nearly one-quarter of global greenhouse gas (GHG) emissions. Emerging technologies-such as eco-driving, connected vehicle control, and others-offer significant potential for emission reduction; however, officially validated, yet optimization-ready emission models are essential for guiding their design, deployment, and evaluation. The U.S. EPA’ Motor Vehicle Emission Simulator (MOVES) is the validated regulatory and industry standard for vehicle emissions in the U.S. Yet, its complexity, macroscopic focus, and high computational demands make it unsuitable and incompatible with control and optimization applications, and burdensome even for traditional analyses. Furthermore, its reliance on location-specific inputs limits its applicability beyond the U.S. As a result, researchers often resort to alternative models, leading to emission estimates that are neither comparable nor officially validated. To address this gap, we introduce NeuralMOVES, an open-source, lightweight surrogate model for CO₂ emissions with near-MOVES fidelity. NeuralMOVES transforms MOVES from a multi-software system requiring specialized expertise and hours of computation into a 2.4 MB Python package that runs in milliseconds and integrates seamlessly into optimization frameworks. Developed by reverse-engineering MOVES through over 200 million batch queries to generate a comprehensive microscopic emission dataset (MOVES_RE, 9.89 GB), NeuralMOVES uses machine learning to compress this dataset by over 4,000× while enabling continuous, differentiable, and real-time emission estimation. An extensive validation shows a mean absolute percentage error of 6.013% across over two million test scenarios, each representing a complete driving trajectory evaluated under specific environmental and vehicle conditions. We demonstrate NeuralMOVES in a dynamic eco-driving case study, showing that it integrates seamlessly into optimization pipelines, leads to different trajectories than alternative models, and captures parameter sensitivities that alternative models overlook. NeuralMOVES enables regulatory-grade, microscopic emission modeling for emerging transportation technologies worldwide and is available at: https://github.com/edgar-rs/neuralMOVES.

交通运输部门占全球温室气体排放量的近四分之一。新兴技术——如生态驾驶、联网车辆控制等——为减排提供了巨大的潜力；然而，官方验证的、可优化的排放模型对于指导它们的设计、部署和评估至关重要。美国环保署的汽车排放模拟器（move）是美国经过验证的汽车排放监管和行业标准，但其复杂性、宏观关注点和高计算需求使其不适合和不兼容控制和优化应用，即使是传统的分析也很繁琐。此外，它对特定地点输入的依赖限制了其在美国以外地区的适用性。因此，研究人员经常求助于其他模型，导致排放估算既不具有可比性，也无法得到官方验证。为了解决这一差距，我们引入了NeuralMOVES，这是一种开源、轻量级的二氧化碳排放替代模型，具有接近moves的保真度。NeuralMOVES将MOVES从需要专业知识和数小时计算的多软件系统转换为2.4 MB的Python包，该包以毫秒为单位运行，并无缝集成到优化框架中。通过对MOVES进行逆向工程，通过超过2亿个批量查询生成一个全面的微观排放数据集（MOVES_RE, 9.89 GB）， NeuralMOVES使用机器学习将该数据集压缩4000倍以上，同时实现连续、可微和实时的排放估计。广泛的验证表明，在超过200万个测试场景中，平均绝对百分比误差为6.013%，每个测试场景都代表了在特定环境和车辆条件下评估的完整驾驶轨迹。我们在一个动态生态驾驶案例研究中展示了NeuralMOVES，表明它可以无缝集成到优化管道中，产生与替代模型不同的轨迹，并捕捉到替代模型忽略的参数敏感性。NeuralMOVES为全球新兴运输技术提供监管级微观排放模型，可在https://github.com/edgar-rs/neuralMOVES上获得。

{"title":"NeuralMOVES: A lightweight and microscopic vehicle emission estimation model based on reverse engineering and surrogate learning","authors":"Edgar Ramirez-Sanchez , Catherine Tang , Yaosheng Xu , Nrithya Renganathan , Vindula Jayawardana , Zhengbing He , Cathy Wu","doi":"10.1016/j.trc.2026.105530","DOIUrl":"10.1016/j.trc.2026.105530","url":null,"abstract":"<div><div>The transportation sector accounts for nearly one-quarter of global greenhouse gas (GHG) emissions. Emerging technologies-such as eco-driving, connected vehicle control, and others-offer significant potential for emission reduction; however, officially validated, yet optimization-ready emission models are essential for guiding their design, deployment, and evaluation. The U.S. EPA’ Motor Vehicle Emission Simulator (MOVES) is the validated regulatory and industry standard for vehicle emissions in the U.S. Yet, its complexity, macroscopic focus, and high computational demands make it unsuitable and incompatible with control and optimization applications, and burdensome even for traditional analyses. Furthermore, its reliance on location-specific inputs limits its applicability beyond the U.S. As a result, researchers often resort to alternative models, leading to emission estimates that are neither comparable nor officially validated. To address this gap, we introduce <strong>NeuralMOVES</strong>, an open-source, lightweight surrogate model for CO<sub>2</sub> emissions with near-MOVES fidelity. NeuralMOVES transforms MOVES from a multi-software system requiring specialized expertise and hours of computation into a 2.4 MB Python package that runs in milliseconds and integrates seamlessly into optimization frameworks. Developed by reverse-engineering MOVES through over 200 million batch queries to generate a comprehensive microscopic emission dataset (MOVES_RE, 9.89 GB), NeuralMOVES uses machine learning to compress this dataset by over 4,000× while enabling continuous, differentiable, and real-time emission estimation. An extensive validation shows a mean absolute percentage error of 6.013% across over two million test scenarios, each representing a complete driving trajectory evaluated under specific environmental and vehicle conditions. We demonstrate NeuralMOVES in a dynamic eco-driving case study, showing that it integrates seamlessly into optimization pipelines, leads to different trajectories than alternative models, and captures parameter sensitivities that alternative models overlook. NeuralMOVES enables regulatory-grade, microscopic emission modeling for emerging transportation technologies worldwide and is available at: <span><span>https://github.com/edgar-rs/neuralMOVES</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"184 ","pages":"Article 105530"},"PeriodicalIF":7.6,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078148","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

An integrated deep reinforcement learning-linear control strategy for longitudinal control of connected and automated vehicles 网联自动车辆纵向控制的综合深度强化学习-线性控制策略

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

Transportation Research Part C-Emerging Technologies

Pub Date : 2026-01-31 DOI: 10.1016/j.trc.2026.105541

Ziwei Yi , Min Xu , Shuaian Wang

String stability is important to maintain the longitudinal control of connected and automated vehicles (CAVs). It prevents the amplification of the perturbations as they propagate through the platoon. A variety of methods based on the deep reinforcement learning (DRL) approach have been proposed for longitudinal control of CAVs, which show excellent performance. However, none of those methods consider string stability on theoretical grounds due to the lack of explicit mathematical models in the DRL approach. To address this problem, we integrate a novel linear controller in a DRL framework for longitudinal control of CAVs, referred to integrated DRL-linear control (IDL) strategy. It can guarantee string stability while striking a good balance among various benefits, including vehicle safety, comfort, and efficiency. We employ the twin delay depth deterministic policy gradient (TD3) algorithm, a promosing DRL, in the proposed framework for decision. Numerical simulation results demonstrate that the proposed approach ensures theoretical string stability while significantly enhancing vehicle safety, comfort, and efficiency compared to human-driven vehicles (HDVs) and a model-based cooperative adaptive cruise control (CACC) strategy. It also outperforms the deep deterministic policy gradient (DDPG) and pure TD3 strategies in terms of safety, comfort, and string stability. These results indicate that the proposed IDL strategy not only benefits from the advantages of the linear controller in analyzing theoretical string stability conditions but also retains the advantage of the DRL approach in terms of optimizing the trade-off between multiple benefits.

管柱的稳定性对于联网自动驾驶车辆（cav）的纵向控制至关重要。它可以防止扰动在队列中传播时放大。在深度强化学习（DRL）方法的基础上，提出了多种自动驾驶汽车纵向控制方法，并取得了良好的效果。然而，由于在DRL方法中缺乏明确的数学模型，这些方法都没有从理论上考虑弦的稳定性。为了解决这个问题，我们在DRL框架中集成了一种新的线性控制器，用于cav的纵向控制，称为集成DRL-线性控制（IDL）策略。它可以保证管柱的稳定性，同时在车辆安全性、舒适性和效率等各种效益之间取得良好的平衡。在提出的决策框架中，我们采用了双延迟深度确定性策略梯度（TD3）算法，这是一种促进DRL的算法。数值模拟结果表明，与人类驾驶车辆（HDVs）和基于模型的协同自适应巡航控制（CACC）策略相比，该方法在保证理论管柱稳定性的同时，显著提高了车辆的安全性、舒适性和效率。在安全性、舒适性和管柱稳定性方面，它也优于深度确定性策略梯度（DDPG）和纯TD3策略。这些结果表明，所提出的IDL策略不仅在分析理论弦稳定性条件方面受益于线性控制器的优势，而且在优化多个优势之间的权衡方面保留了DRL方法的优势。

{"title":"An integrated deep reinforcement learning-linear control strategy for longitudinal control of connected and automated vehicles","authors":"Ziwei Yi , Min Xu , Shuaian Wang","doi":"10.1016/j.trc.2026.105541","DOIUrl":"10.1016/j.trc.2026.105541","url":null,"abstract":"<div><div>String stability is important to maintain the longitudinal control of connected and automated vehicles (CAVs). It prevents the amplification of the perturbations as they propagate through the platoon. A variety of methods based on the deep reinforcement learning (DRL) approach have been proposed for longitudinal control of CAVs, which show excellent performance. However, none of those methods consider string stability on theoretical grounds due to the lack of explicit mathematical models in the DRL approach. To address this problem, we integrate a novel linear controller in a DRL framework for longitudinal control of CAVs, referred to integrated DRL-linear control (IDL) strategy. It can guarantee string stability while striking a good balance among various benefits, including vehicle safety, comfort, and efficiency. We employ the twin delay depth deterministic policy gradient (TD3) algorithm, a promosing DRL, in the proposed framework for decision. Numerical simulation results demonstrate that the proposed approach ensures theoretical string stability while significantly enhancing vehicle safety, comfort, and efficiency compared to human-driven vehicles (HDVs) and a model-based cooperative adaptive cruise control (CACC) strategy. It also outperforms the deep deterministic policy gradient (DDPG) and pure TD3 strategies in terms of safety, comfort, and string stability. These results indicate that the proposed IDL strategy not only benefits from the advantages of the linear controller in analyzing theoretical string stability conditions but also retains the advantage of the DRL approach in terms of optimizing the trade-off between multiple benefits.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"184 ","pages":"Article 105541"},"PeriodicalIF":7.6,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078212","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

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Transportation Research Part C-Emerging Technologies

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀