Communications in Transportation Research最新文献_第7页

Sustainable operational strategies for mixed fleets: Integrating autonomous and human-driven taxis with heterogeneous energy types 混合车队的可持续运营策略：将自动驾驶和人工驾驶出租车与异质能源类型相结合

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-04-01 DOI: 10.1016/j.commtr.2025.100171

Qinru Hu , Beinuo Yang , Keyang Zhang , Jose Escribano Macias , Xiqun (Michael) Chen , Yanfeng Ouyang , Simon Hu

Taxi systems are transitioning into a complex integration of autonomous and human-driven vehicles powered by heterogeneous energy sources. Traditional operational strategies designed for homogeneous fleets fail to capture the unique dynamics and interactions present in mixed fleets. To address this gap, this study proposes a comprehensive modeling and simulation framework for the dynamic operation of mixed taxi fleets, including autonomous electric taxis (AETs), human-driven electric taxis, and human-driven gasoline taxis. The framework integrates centralized and decentralized control mechanisms to address the distinct characteristics of each taxi type. An integer linear programming model is developed to optimize taxi assignment and scheduling, with the objective of maximizing system profits by accounting for customer service revenues and energy and travel costs. An agent-based simulation platform is designed to model dynamic interactions among taxis, customers, and charging stations, offering continuous feedback on system performance. Real-world case studies reveal significant environmental, economic, and social benefits when incorporating operating costs into decision-making. Impact analyses demonstrate the competitiveness of AETs in passenger service due to lower operating costs and enhanced environmental efficiency, with reduced carbon emission intensity per kilometer and per request. This study provides valuable insights for taxi platforms and policymakers in formulating strategies that promote sustainable urban mobility during the ongoing transition period.

出租车系统正在转变为由不同能源驱动的自动驾驶和人类驾驶车辆的复杂集成。为同构车队设计的传统运营策略无法捕捉混合车队中存在的独特动态和相互作用。为了解决这一差距，本研究提出了一个综合的混合出租车车队动态运行建模和仿真框架，包括自动驾驶电动出租车（aet）、人工驾驶电动出租车和人工驾驶汽油出租车。该框架集成了集中和分散的控制机制，以解决每种出租车类型的独特特征。在考虑客户服务收入、能源和出行成本的情况下，以系统利润最大化为目标，建立了优化出租车分配和调度的整数线性规划模型。设计了一个基于agent的仿真平台，对出租车、顾客和充电站之间的动态交互进行建模，提供系统性能的持续反馈。现实世界的案例研究表明，将运营成本纳入决策时，显著的环境、经济和社会效益。影响分析表明，AETs在客运服务方面具有竞争力，因为它的运营成本更低，环境效率更高，每公里和每项要求的碳排放强度也更低。该研究为出租车平台和政策制定者在转型时期制定促进可持续城市交通的战略提供了有价值的见解。

{"title":"Sustainable operational strategies for mixed fleets: Integrating autonomous and human-driven taxis with heterogeneous energy types","authors":"Qinru Hu , Beinuo Yang , Keyang Zhang , Jose Escribano Macias , Xiqun (Michael) Chen , Yanfeng Ouyang , Simon Hu","doi":"10.1016/j.commtr.2025.100171","DOIUrl":"10.1016/j.commtr.2025.100171","url":null,"abstract":"<div><div>Taxi systems are transitioning into a complex integration of autonomous and human-driven vehicles powered by heterogeneous energy sources. Traditional operational strategies designed for homogeneous fleets fail to capture the unique dynamics and interactions present in mixed fleets. To address this gap, this study proposes a comprehensive modeling and simulation framework for the dynamic operation of mixed taxi fleets, including autonomous electric taxis (AETs), human-driven electric taxis, and human-driven gasoline taxis. The framework integrates centralized and decentralized control mechanisms to address the distinct characteristics of each taxi type. An integer linear programming model is developed to optimize taxi assignment and scheduling, with the objective of maximizing system profits by accounting for customer service revenues and energy and travel costs. An agent-based simulation platform is designed to model dynamic interactions among taxis, customers, and charging stations, offering continuous feedback on system performance. Real-world case studies reveal significant environmental, economic, and social benefits when incorporating operating costs into decision-making. Impact analyses demonstrate the competitiveness of AETs in passenger service due to lower operating costs and enhanced environmental efficiency, with reduced carbon emission intensity per kilometer and per request. This study provides valuable insights for taxi platforms and policymakers in formulating strategies that promote sustainable urban mobility during the ongoing transition period.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100171"},"PeriodicalIF":12.5,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modular AI agents for transportation surveys and interviews: Advancing engagement, transparency, and cost efficiency 用于交通调查和访谈的模块化人工智能代理：提高参与度、透明度和成本效率

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-03-24 DOI: 10.1016/j.commtr.2025.100172

Jiangbo Yu , Jinhua Zhao , Luis Miranda-Moreno , Matthew Korp

Surveys and interviews—structured, semi-structured, or unstructured—are widely used for collecting insights on emerging or hypothetical scenarios. Traditional human-led methods often face challenges related to cost, scalability, and consistency. For example, distributed questionnaires lack the ability to provide real-time guidance and request immediate clarifications. Recently, various domains have begun to explore the use of conversational agents (chatbots) powered by generative artificial intelligence (AI) technologies. However, considering decisions in transportation investments and policies often carry significant socioeconomic and environmental consequences, surveys and interviews face unique challenges in integrating AI agents. This issue underscors the need for a rigorous, explainable, and resource-efficient approach that enhances participant engagement and ensures privacy. This paper bridges this gap by introducing a modular approach accompanied by a parameterized process for designing and deploying AI agents for surveys and interviews, thereby supporting decision-makings in high-stakes contexts. We detail the system architecture, integrating engineered prompts, specialized knowledge bases, and customizable, goal-oriented conversational logic. We demonstrate the adaptability, generalizability, and efficacy of our modular approach through three empirical studies: (1) travel preference surveys, highlighting conditional logic and multimodal (voice, text, and image generation) capabilities; (2) public opinion elicitation on a newly constructed, novel infrastructure project, showcasing question customization and multilingual (English and French) capabilities; and (3) expert consultations about the impact of technologies on future transportation systems, highlighting real-time, clarification request capabilities for open-ended questions, resilience in handling erratic inputs, and efficient transcript postprocessing. The results suggest that the AI agent increases completion rates and response quality. Furthermore, the modular approach demonstrates controllability, flexibility, and robustness while addressing key ethical, privacy, security, and token consumption concerns. We believe this work lays the foundation for next-generation surveys and interviews in transportation research.

调查和访谈——结构化的、半结构化的或非结构化的——被广泛用于收集对新兴或假设场景的见解。传统的以人为主导的方法经常面临与成本、可伸缩性和一致性相关的挑战。例如，分发的问卷缺乏提供实时指导和要求立即澄清的能力。最近，各个领域已经开始探索由生成式人工智能（AI）技术驱动的会话代理（聊天机器人）的使用。然而，考虑到交通投资和政策决策往往会带来重大的社会经济和环境后果，调查和访谈在整合人工智能代理方面面临着独特的挑战。这个问题强调需要一种严格的、可解释的和资源高效的方法，以增强参与者的参与并确保隐私。本文通过引入模块化方法和参数化过程来设计和部署用于调查和访谈的人工智能代理，从而支持高风险环境中的决策制定，从而弥合了这一差距。我们详细介绍了系统架构，集成了工程提示、专门的知识库和可定制的、面向目标的会话逻辑。我们通过三个实证研究证明了模块化方法的适应性、普遍性和有效性：(1)旅行偏好调查，强调条件逻辑和多模式（语音、文本和图像生成）能力；(2)对新建的新型基础设施项目进行民意调查，展示问题定制和多语种（英语和法语）能力；(3)就技术对未来交通系统的影响进行专家咨询，强调对开放式问题的实时性、澄清请求能力、处理不稳定输入的弹性以及高效的记录后处理。结果表明，人工智能代理提高了完成率和响应质量。此外，模块化方法展示了可控性、灵活性和鲁棒性，同时解决了关键的道德、隐私、安全和代币消费问题。我们相信这项工作为下一代交通研究中的调查和访谈奠定了基础。

{"title":"Modular AI agents for transportation surveys and interviews: Advancing engagement, transparency, and cost efficiency","authors":"Jiangbo Yu , Jinhua Zhao , Luis Miranda-Moreno , Matthew Korp","doi":"10.1016/j.commtr.2025.100172","DOIUrl":"10.1016/j.commtr.2025.100172","url":null,"abstract":"<div><div>Surveys and interviews—structured, semi-structured, or unstructured—are widely used for collecting insights on emerging or hypothetical scenarios. Traditional human-led methods often face challenges related to cost, scalability, and consistency. For example, distributed questionnaires lack the ability to provide real-time guidance and request immediate clarifications. Recently, various domains have begun to explore the use of conversational agents (chatbots) powered by generative artificial intelligence (AI) technologies. However, considering decisions in transportation investments and policies often carry significant socioeconomic and environmental consequences, surveys and interviews face unique challenges in integrating AI agents. This issue underscors the need for a rigorous, explainable, and resource-efficient approach that enhances participant engagement and ensures privacy. This paper bridges this gap by introducing a modular approach accompanied by a parameterized process for designing and deploying AI agents for surveys and interviews, thereby supporting decision-makings in high-stakes contexts. We detail the system architecture, integrating engineered prompts, specialized knowledge bases, and customizable, goal-oriented conversational logic. We demonstrate the adaptability, generalizability, and efficacy of our modular approach through three empirical studies: (1) travel preference surveys, highlighting conditional logic and multimodal (voice, text, and image generation) capabilities; (2) public opinion elicitation on a newly constructed, novel infrastructure project, showcasing question customization and multilingual (English and French) capabilities; and (3) expert consultations about the impact of technologies on future transportation systems, highlighting real-time, clarification request capabilities for open-ended questions, resilience in handling erratic inputs, and efficient transcript postprocessing. The results suggest that the AI agent increases completion rates and response quality. Furthermore, the modular approach demonstrates controllability, flexibility, and robustness while addressing key ethical, privacy, security, and token consumption concerns. We believe this work lays the foundation for next-generation surveys and interviews in transportation research.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100172"},"PeriodicalIF":12.5,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143683927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fuel- and noise-minimal departure trajectory using deep reinforcement learning with aircraft dynamics and topography constraints 基于飞机动力学和地形约束的深度强化学习的燃油和噪声最小离场轨迹

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-03-12 DOI: 10.1016/j.commtr.2025.100165

Chris HC. Nguyen , James M. Shihua , Rhea P. Liem

Designing an optimal departure trajectory for an airport can minimize fuel emissions within the surrounding airspace and noise perceived by nearby populations, which brings positive sociological and economic implications in addition to environmental benefits. Yet, designing a trajectory that considers realistic operational constraints could be complex and, consequently, computationally expensive. Traditional trajectory optimization methods often simplify the problem to manage computational costs, which leads to compromised accuracy. To overcome this challenge, we propose a reinforcement learning (RL) approach that can satisfy multidisciplinary constraints by leveraging accurately modeled flight dynamics, high-fidelity population data, and topological data. This is achieved by establishing a comprehensive, physically-consistent simulated environment for the learning algorithm, while keeping the computational cost low. Instead of directly designing the trajectory itself, we train an RL agent to control the aircraft, whose trajectory is then considered as optimal. We model the RL problem as a continuous Markov decision process and employ the soft actor-critic architecture. By changing the relative importance of fuel consumption and noise in the optimization objective, we can obtain different optimum trajectories that are well-suited to the specific region of interest. Not surprisingly, a trade-off between fuel consumption and noise impact is observed in our results. This developed framework provides a more accurate and sophisticated approach for departure trajectory optimization, whose results are beneficial for future airspace design and can support sustainable aviation efforts.

为机场设计一个最佳的起飞轨迹可以最大限度地减少周围空域的燃油排放和附近人群感受到的噪音，这除了带来环境效益外，还带来了积极的社会和经济影响。然而，设计一个考虑实际操作约束的轨迹可能是复杂的，因此计算成本很高。传统的轨迹优化方法往往为了控制计算成本而简化问题，从而导致精度降低。为了克服这一挑战，我们提出了一种强化学习（RL）方法，该方法可以通过利用精确建模的飞行动力学、高保真种群数据和拓扑数据来满足多学科约束。这是通过为学习算法建立一个全面的、物理一致的模拟环境来实现的，同时保持较低的计算成本。我们不是直接设计轨迹本身，而是训练一个RL代理来控制飞机，然后将其轨迹视为最优。我们将RL问题建模为一个连续的马尔可夫决策过程，并采用了软参与者-评论家体系结构。通过改变燃油消耗和噪声在优化目标中的相对重要性，我们可以得到不同的最优轨迹，这些轨迹非常适合于特定的兴趣区域。毫不奇怪，在我们的结果中观察到燃料消耗和噪音影响之间的权衡。该开发框架为离场轨迹优化提供了更精确和复杂的方法，其结果有利于未来空域设计，并可支持可持续航空努力。

{"title":"Fuel- and noise-minimal departure trajectory using deep reinforcement learning with aircraft dynamics and topography constraints","authors":"Chris HC. Nguyen , James M. Shihua , Rhea P. Liem","doi":"10.1016/j.commtr.2025.100165","DOIUrl":"10.1016/j.commtr.2025.100165","url":null,"abstract":"<div><div>Designing an optimal departure trajectory for an airport can minimize fuel emissions within the surrounding airspace and noise perceived by nearby populations, which brings positive sociological and economic implications in addition to environmental benefits. Yet, designing a trajectory that considers realistic operational constraints could be complex and, consequently, computationally expensive. Traditional trajectory optimization methods often simplify the problem to manage computational costs, which leads to compromised accuracy. To overcome this challenge, we propose a reinforcement learning (RL) approach that can satisfy multidisciplinary constraints by leveraging accurately modeled flight dynamics, high-fidelity population data, and topological data. This is achieved by establishing a comprehensive, physically-consistent simulated environment for the learning algorithm, while keeping the computational cost low. Instead of directly designing the trajectory itself, we train an RL agent to control the aircraft, whose trajectory is then considered as optimal. We model the RL problem as a continuous Markov decision process and employ the soft actor-critic architecture. By changing the relative importance of fuel consumption and noise in the optimization objective, we can obtain different optimum trajectories that are well-suited to the specific region of interest. Not surprisingly, a trade-off between fuel consumption and noise impact is observed in our results. This developed framework provides a more accurate and sophisticated approach for departure trajectory optimization, whose results are beneficial for future airspace design and can support sustainable aviation efforts.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100165"},"PeriodicalIF":12.5,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143600833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reassessing desired time headway as a measure of car-following capability: Definition, quantification, and associated factors 重新评估期望车头时距作为车辆跟随能力的衡量标准：定义、量化和相关因素

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-03-12 DOI: 10.1016/j.commtr.2025.100169

Shubham Parashar , Zuduo Zheng , Andry Rakotonirainy , Md Mazharul Haque

The desired time headway is often used to incorporate human behavior in car-following (CF) models by treating it as a measure of driver capability in car-following interactions, which is latent and cannot be directly observed. However, the desired time headway is often assumed to be a constant value for a driver across all speed levels. This assumption can be unrealistic and unreliable. Studies indicate that the mean time headway during steady-state car-following interactions quantifies the desired time headway, but inconsistent conditions for steady-state interactions in the literature make such assessments challenging. This study aims to reassess the desired time headway as a metric of driver capability in car-following interactions. Specifically, it identifies steady-state car-following conditions for reliable desired time headway estimates via the NGSIM I80 dataset. The results show that using a sustenance window of 3.5 s with an acceleration threshold of ±0.75 m/s² and a relative speed of ±1.52 m/s reduces transient and sporadic time headway observations, which in turn improves the reliability of the desired time headway. The obtained conditions are applied to the car-following trajectories in a driving simulator experiment, designed to focus on the steady-state at two speed levels (85 and 40 km/h) in traditional environment (TE) and connected environment (CE). The results indicate that the desired time headway is significantly longer in high-speed car-following (85 km/h) than in low-speed car-following (40 km/h) in the TE and CE and that driving aids help maintain more consistent desired time headways. A comparison of the TE and CE in low-speed car-following shows that most drivers prioritize safety by increasing the desired time headway in the CE. However, in high-speed car-following, the mean desired time headway is not significantly different between the TE and the CE on an aggregate level. Furthermore, the study presents a generalized linear mixed model (GLMM) describing the desired time headway selection in different conditions, identifying age, gender, and crash involvement as significant variables other than the driving conditions.

期望车头时距通常用于车辆跟随（CF）模型中纳入人类行为，将其视为驾驶员在车辆跟随交互中的能力的度量，这是潜在的，不能直接观察到。然而，期望的车头时距通常被假定为驾驶员在所有速度水平上的恒定值。这种假设可能是不现实和不可靠的。研究表明，在稳态汽车跟随相互作用期间的平均车头时距量化了期望的车头时距，但文献中稳态相互作用的不一致条件使这种评估具有挑战性。本研究的目的是重新评估期望时距作为一种衡量驾驶员在汽车跟随互动中的能力。具体来说，它通过NGSIM I80数据集确定可靠的期望车头时距估计的稳态汽车跟随条件。结果表明，采用3.5 s的维持窗口，加速度阈值为±0.75 m/s2，相对速度为±1.52 m/s，可以减少瞬时和偶发车头时距观测，从而提高车头时距期望的可靠性。将得到的条件应用于驾驶模拟器的汽车跟车轨迹实验，重点研究了传统环境（TE）和互联环境（CE）下两种速度水平（85和40 km/h）下的稳态。结果表明，高速跟车（85 km/h）时的期望车头时距明显大于低速跟车（40 km/h）时距，驾驶辅助装置有助于保持更一致的期望车头时距。对低速跟车时的TE和CE的比较表明，在低速跟车时，大多数驾驶员通过增加期望车头时距来优先考虑安全。然而，在高速跟车中，平均期望车头时距在总水平上在TE和CE之间没有显著差异。此外，该研究提出了一个广义线性混合模型（GLMM），描述了在不同条件下期望的车头时距选择，将年龄、性别和碰撞卷入作为除驾驶条件外的重要变量。

{"title":"Reassessing desired time headway as a measure of car-following capability: Definition, quantification, and associated factors","authors":"Shubham Parashar , Zuduo Zheng , Andry Rakotonirainy , Md Mazharul Haque","doi":"10.1016/j.commtr.2025.100169","DOIUrl":"10.1016/j.commtr.2025.100169","url":null,"abstract":"<div><div>The desired time headway is often used to incorporate human behavior in car-following (CF) models by treating it as a measure of driver capability in car-following interactions, which is latent and cannot be directly observed. However, the desired time headway is often assumed to be a constant value for a driver across all speed levels. This assumption can be unrealistic and unreliable. Studies indicate that the mean time headway during steady-state car-following interactions quantifies the desired time headway, but inconsistent conditions for steady-state interactions in the literature make such assessments challenging. This study aims to reassess the desired time headway as a metric of driver capability in car-following interactions. Specifically, it identifies steady-state car-following conditions for reliable desired time headway estimates via the NGSIM I80 dataset. The results show that using a sustenance window of 3.5 s with an acceleration threshold of ±0.75 m/s<sup>2</sup> and a relative speed of ±1.52 m/s reduces transient and sporadic time headway observations, which in turn improves the reliability of the desired time headway. The obtained conditions are applied to the car-following trajectories in a driving simulator experiment, designed to focus on the steady-state at two speed levels (85 and 40 km/h) in traditional environment (TE) and connected environment (CE). The results indicate that the desired time headway is significantly longer in high-speed car-following (85 km/h) than in low-speed car-following (40 km/h) in the TE and CE and that driving aids help maintain more consistent desired time headways. A comparison of the TE and CE in low-speed car-following shows that most drivers prioritize safety by increasing the desired time headway in the CE. However, in high-speed car-following, the mean desired time headway is not significantly different between the TE and the CE on an aggregate level. Furthermore, the study presents a generalized linear mixed model (GLMM) describing the desired time headway selection in different conditions, identifying age, gender, and crash involvement as significant variables other than the driving conditions.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100169"},"PeriodicalIF":12.5,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143609140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Driving under the sun: Future of solar buses in Hong Kong, China 在阳光下驾驶：中国香港太阳能巴士的未来

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-03-12 DOI: 10.1016/j.commtr.2025.100168

Zhuowei Wang , Yiyang Peng , Hongxing Yang , Anthony Chen

引用次数: 0

Public acceptance of driverless buses: An extended UTAUT2 model with anthropomorphic perception and empathy 公众对无人驾驶公交车的接受度：具有拟人化感知和同理心的扩展UTAUT2模型

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-03-11 DOI: 10.1016/j.commtr.2025.100167

Zijing He , Ying Yang , Yan Mu , Xiaobo Qu

The sustainable transportation strategy emphasizes the enormous potential of driverless buses and enables their gradual integration into society over the coming decade. Therefore, it is crucial to cultivate public acceptance of driverless buses. This study is based on the extended unified theory of acceptance and use of technology (UTAUT2) and empathy theory. The structural equation modeling (SEM) method was used to analyze valid survey responses from 852 participants residing in China. Both the UTAUT2 factors and the anthropomorphic perception components independently predicted the public acceptance of driverless buses. This study indicates that future campaigns promoting driverless buses should highlight not only their functional value but also their perceived socioemotional value. Considering users’ psychological characteristics (such as empathy and communal traits) can help improve the travel experience, accelerate the transition to emerging innovative technologies, and achieve the potential benefits of intelligent and sustainable transportation.

可持续交通战略强调了无人驾驶公共汽车的巨大潜力，并使其在未来十年逐步融入社会。因此，培养公众对无人驾驶公交车的接受度至关重要。本研究基于技术接受与使用扩展统一理论（UTAUT2）和共情理论。采用结构方程建模（SEM）方法对852名居住在中国的调查参与者的有效回复进行分析。UTAUT2因子和拟人化感知因子都独立预测了公众对无人驾驶公交车的接受程度。这项研究表明，未来推广无人驾驶公交车的活动不仅要突出其功能价值，还要突出其感知的社会情感价值。考虑用户的心理特征（如移情和公共特征）可以帮助改善出行体验，加速向新兴创新技术的过渡，并实现智能和可持续交通的潜在效益。

引用次数: 0

A systematic review of machine learning-based microscopic traffic flow models and simulations 基于机器学习的微观交通流模型和模拟的系统综述

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-02-27 DOI: 10.1016/j.commtr.2025.100164

Davies Rowan , Haitao He , Fang Hui , Ali Yasir , Quddus Mohammed

Microscopic traffic flow models and simulations are crucial for capturing vehicle interactions and analyzing traffic. They can provide critical insights for transport planning, management, and operation through scenario testing and optimization. With the growing availability of high-resolution data and rapid advancements in machine learning (ML) techniques, ML-based microscopic traffic flow models are emerging as promising alternatives to traditional physical models, offering improved accuracy and greater flexibility. Although many models have been developed, comprehensive studies that critically assess the strengths and weaknesses of these models and the overall ML-based approach are lacking. To fill this gap, this study presents a systematic review of ML-based microscopic traffic flow models and simulations, covering both car-following and lane-changing behaviors. This review identifies key areas for future research, including the development of methods to improve model transferability across different operational design domains, the need to capture both driver-specific and location-specific heterogeneity via benchmark datasets, and the incorporation of advanced ML techniques such as meta-learning, federated learning, and causal learning. Additionally, enhancing model interpretability, accounting for mesoscopic and macroscopic traffic impacts, incorporating physical constraints in model training, and developing ML models designed for autonomous vehicles are crucial for the practical adoption of ML-based microscopic models in traffic simulations.

微观交通流模型和仿真对于捕获车辆相互作用和分析交通至关重要。它们可以通过场景测试和优化为运输规划、管理和运营提供关键的见解。随着高分辨率数据的日益可用性和机器学习（ML）技术的快速发展，基于ML的微观交通流模型正在成为传统物理模型的有希望的替代品，提供更高的准确性和更大的灵活性。尽管已经开发了许多模型，但缺乏批判性地评估这些模型的优缺点和整体基于ml的方法的全面研究。为了填补这一空白，本研究系统地回顾了基于机器学习的微观交通流模型和模拟，涵盖了车辆跟随和变道行为。这篇综述确定了未来研究的关键领域，包括开发方法来提高模型在不同操作设计领域的可移植性，通过基准数据集捕获特定驾驶员和特定位置的异质性，以及结合元学习、联邦学习和因果学习等高级机器学习技术。此外，增强模型可解释性，考虑中观和宏观交通影响，在模型训练中纳入物理约束，以及开发为自动驾驶汽车设计的ML模型，对于在交通模拟中实际采用基于ML的微观模型至关重要。

{"title":"A systematic review of machine learning-based microscopic traffic flow models and simulations","authors":"Davies Rowan , Haitao He , Fang Hui , Ali Yasir , Quddus Mohammed","doi":"10.1016/j.commtr.2025.100164","DOIUrl":"10.1016/j.commtr.2025.100164","url":null,"abstract":"<div><div>Microscopic traffic flow models and simulations are crucial for capturing vehicle interactions and analyzing traffic. They can provide critical insights for transport planning, management, and operation through scenario testing and optimization. With the growing availability of high-resolution data and rapid advancements in machine learning (ML) techniques, ML-based microscopic traffic flow models are emerging as promising alternatives to traditional physical models, offering improved accuracy and greater flexibility. Although many models have been developed, comprehensive studies that critically assess the strengths and weaknesses of these models and the overall ML-based approach are lacking. To fill this gap, this study presents a systematic review of ML-based microscopic traffic flow models and simulations, covering both car-following and lane-changing behaviors. This review identifies key areas for future research, including the development of methods to improve model transferability across different operational design domains, the need to capture both driver-specific and location-specific heterogeneity via benchmark datasets, and the incorporation of advanced ML techniques such as meta-learning, federated learning, and causal learning. Additionally, enhancing model interpretability, accounting for mesoscopic and macroscopic traffic impacts, incorporating physical constraints in model training, and developing ML models designed for autonomous vehicles are crucial for the practical adoption of ML-based microscopic models in traffic simulations.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100164"},"PeriodicalIF":12.5,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On the stochastic fundamental diagram: A general micro-macroscopic traffic flow modeling framework 论随机基本图：一种通用的微观宏观交通流建模框架

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-02-13 DOI: 10.1016/j.commtr.2025.100163

Xiaohui Zhang, Jie Sun, Jian Sun

The stochastic fundamental diagram (SFD), which describes the stochasticity of the macroscopic relations of traffic flow, plays a crucial role in understanding the uncertainty of traffic flow evolution and developing robust traffic control strategies. Although many efforts have been made to reproduce the SFD via various methods, few studies have focused on the analytical modeling of the SFD, particularly linking the macroscopic relations with microscopic behaviors. This study fills this gap by proposing a general micro-macroscopic modeling approach, which uses probabilistic leader–follower behavior to derive the macroscopic relations of a platoon and is referred to as the leader–follower conditional distribution-based stochastic traffic modeling (LFCD-STM) framework. Specifically, we first define a conditional probability distribution of speed for the leader‒follower pair according to Brownian dynamics, which is proven to be a general representation of the longitudinal interaction and compatible with classical car-following models. As a result, we can describe the joint distribution of vehicle speeds of the platoon through Markov chain modeling and further derive the macroscopic relations (e.g., the mean flow‒density relation and its variance) under equilibrium conditions. On the basis of this general micro-macroscopic framework, we utilize the maximum entropy approach to theoretically derive the SFD model, in which we provide a specific conditional distribution for longitudinal interaction and thus solve the analytical functions of the mean and variance of FD. The performance of the maximum entropy-based SFD model is thoroughly validated with the NGSIM I-80, US-101 and HighD datasets. The high consistency between the theoretical results and empirical results demonstrates the soundness of the LFCD-STM framework and the maximum entropy-based SFD model. Finally, the proposed SFD model has practical implications for promoting smoother driving behaviors to suppress stochasticity and improve traffic flow.

随机基本图（SFD）描述了交通流宏观关系的随机性，对于理解交通流演化的不确定性和制定稳健的交通控制策略具有重要意义。尽管人们已经通过各种方法对SFD进行了再现，但很少有研究关注SFD的分析建模，特别是将宏观关系与微观行为联系起来。本研究提出了一种通用的微观宏观建模方法来填补这一空白，该方法利用概率leader-follower行为来推导队列的宏观关系，被称为基于leader-follower条件分布的随机交通建模（LFCD-STM）框架。具体地说，我们首先根据布朗动力学定义了领队-随从对速度的条件概率分布，并证明了这是纵向相互作用的一般表示，与经典的汽车跟随模型兼容。因此，我们可以通过马尔可夫链建模来描述车队车速的联合分布，并进一步推导出平衡条件下的宏观关系（如平均流量密度关系及其方差）。在这一宏观微观框架的基础上，利用最大熵方法从理论上推导出SFD模型，该模型为纵向相互作用提供了特定的条件分布，从而求解出FD的均值和方差的解析函数。利用NGSIM I-80、US-101和HighD数据集对基于最大熵的SFD模型的性能进行了验证。理论结果与实证结果的高度一致性证明了LFCD-STM框架和基于最大熵的SFD模型的合理性。最后，本文提出的SFD模型对于促进驾驶行为的平稳性以抑制随机性和改善交通流具有实际意义。

{"title":"On the stochastic fundamental diagram: A general micro-macroscopic traffic flow modeling framework","authors":"Xiaohui Zhang, Jie Sun, Jian Sun","doi":"10.1016/j.commtr.2025.100163","DOIUrl":"10.1016/j.commtr.2025.100163","url":null,"abstract":"<div><div>The stochastic fundamental diagram (SFD), which describes the stochasticity of the macroscopic relations of traffic flow, plays a crucial role in understanding the uncertainty of traffic flow evolution and developing robust traffic control strategies. Although many efforts have been made to reproduce the SFD via various methods, few studies have focused on the analytical modeling of the SFD, particularly linking the macroscopic relations with microscopic behaviors. This study fills this gap by proposing a general micro-macroscopic modeling approach, which uses probabilistic leader–follower behavior to derive the macroscopic relations of a platoon and is referred to as the leader–follower conditional distribution-based stochastic traffic modeling (LFCD-STM) framework. Specifically, we first define a conditional probability distribution of speed for the leader‒follower pair according to Brownian dynamics, which is proven to be a general representation of the longitudinal interaction and compatible with classical car-following models. As a result, we can describe the joint distribution of vehicle speeds of the platoon through Markov chain modeling and further derive the macroscopic relations (e.g., the mean flow‒density relation and its variance) under equilibrium conditions. On the basis of this general micro-macroscopic framework, we utilize the maximum entropy approach to theoretically derive the SFD model, in which we provide a specific conditional distribution for longitudinal interaction and thus solve the analytical functions of the mean and variance of FD. The performance of the maximum entropy-based SFD model is thoroughly validated with the NGSIM I-80, US-101 and HighD datasets. The high consistency between the theoretical results and empirical results demonstrates the soundness of the LFCD-STM framework and the maximum entropy-based SFD model. Finally, the proposed SFD model has practical implications for promoting smoother driving behaviors to suppress stochasticity and improve traffic flow.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100163"},"PeriodicalIF":12.5,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Drone to recharge electric vehicles: Operations, benefits, and challenges 无人机为电动汽车充电：操作、好处和挑战

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-02-13 DOI: 10.1016/j.commtr.2025.100162

Dongdong He , Ying Yang , Andrea Morichetta , Jianjun Wu

Electric vehicles (EVs) are a promising solution to reduce greenhouse gas emissions and foster sustainable urban transportation. However, the widespread adoption of EVs is hindered by range anxiety and the fear of running outnqt of battery before reaching a charging station. To address this challenge, we propose a novel drone-to-vehicle (D2V) charging system, which leverages drones as mobile charging units to provide on-the-go recharging services for EVs. This study explores the operational and technical aspects of the D2V system, including drone charging docks, order-dispatching strategies, and dynamic drone reallocation mechanisms. A key contribution is to introduce a concept of the adaptive route meetup location selection (ARMLS), which optimizes drone dispatch and pricing models based on real-time parameters such as distance, battery levels, and traffic conditions. Our analysis highlights the potential of D2V systems to alleviate range anxiety, enhance road network efficiency through dynamic traffic redistribution, and reduce carbon emissions by integrating renewable energy sources. The study suggests that implementing D2V services can significantly improve the reliability of EVs in critical situations while fostering broader EV adoption. Future work will focus on reinforcement learning-based optimization algorithms to further improve drone operations and address scalability challenges. The proposed D2V system represents a crucial step toward a sustainable and efficient urban mobility future.

电动汽车（ev）是减少温室气体排放和促进可持续城市交通的一种有前途的解决方案。然而，电动汽车的广泛采用受到里程焦虑和担心在到达充电站之前耗尽电池的阻碍。为了解决这一挑战，我们提出了一种新型的无人机-车辆（D2V）充电系统，该系统利用无人机作为移动充电单元，为电动汽车提供随时充电服务。本研究探讨了D2V系统的操作和技术方面，包括无人机充电桩、订单调度策略和无人机动态再分配机制。其中一个关键贡献是引入了自适应路线集合位置选择（ARMLS）的概念，该概念可以根据距离、电池电量和交通状况等实时参数优化无人机调度和定价模型。我们的分析强调了D2V系统在缓解里程焦虑、通过动态交通再分配提高道路网络效率以及通过整合可再生能源减少碳排放方面的潜力。该研究表明，实施D2V服务可以显著提高电动汽车在关键情况下的可靠性，同时促进电动汽车的广泛采用。未来的工作将集中在基于强化学习的优化算法上，以进一步改善无人机的操作并解决可扩展性的挑战。拟议的D2V系统是迈向可持续和高效城市交通未来的关键一步。

{"title":"Drone to recharge electric vehicles: Operations, benefits, and challenges","authors":"Dongdong He , Ying Yang , Andrea Morichetta , Jianjun Wu","doi":"10.1016/j.commtr.2025.100162","DOIUrl":"10.1016/j.commtr.2025.100162","url":null,"abstract":"<div><div>Electric vehicles (EVs) are a promising solution to reduce greenhouse gas emissions and foster sustainable urban transportation. However, the widespread adoption of EVs is hindered by range anxiety and the fear of running outnqt of battery before reaching a charging station. To address this challenge, we propose a novel drone-to-vehicle (D2V) charging system, which leverages drones as mobile charging units to provide on-the-go recharging services for EVs. This study explores the operational and technical aspects of the D2V system, including drone charging docks, order-dispatching strategies, and dynamic drone reallocation mechanisms. A key contribution is to introduce a concept of the adaptive route meetup location selection (ARMLS), which optimizes drone dispatch and pricing models based on real-time parameters such as distance, battery levels, and traffic conditions. Our analysis highlights the potential of D2V systems to alleviate range anxiety, enhance road network efficiency through dynamic traffic redistribution, and reduce carbon emissions by integrating renewable energy sources. The study suggests that implementing D2V services can significantly improve the reliability of EVs in critical situations while fostering broader EV adoption. Future work will focus on reinforcement learning-based optimization algorithms to further improve drone operations and address scalability challenges. The proposed D2V system represents a crucial step toward a sustainable and efficient urban mobility future.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100162"},"PeriodicalIF":12.5,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating spatial-temporal risk maps with candidate trajectory trees for explainable autonomous driving planning 将时空风险图与候选轨迹树相结合，实现可解释的自动驾驶规划

IF 12.5 Q1 TRANSPORTATION

Communications in Transportation Research

Pub Date : 2025-01-28 DOI: 10.1016/j.commtr.2025.100161

Qiyuan Liu , Jiawei Zhang , Jingwei Ge , Cheng Chang , Zhiheng Li , Shen Li , Li Li

With increasing public concern about autonomous vehicles, there is a growing demand for developing explainable autonomous driving planning technology. Traditional risk field methods use handcrafted potential field models to explain driving risks in a scenario. When explaining highly interactive scenarios, such prior knowledge-based methods still lack flexibility, leading to insufficient interpretability. In this study, we first propose the concept of a risk map that can be seen as a discrete, ego vehicle's view form of the risk field. We then design an explainable trajectory planning framework that integrates risk maps with the candidate trajectory tree generated by trajectory prediction models. We further filter safe candidate trajectories from the tree on the basis of their cumulative risks in the risk maps and then select the optimal trajectory to execute by balancing other driving objectives. The validation results in various real-world scenarios demonstrate that our method can generate understandable risk maps and explain the risk differences between trajectories. Open-loop experiments show our model's advantages in terms of safety and efficiency for the trajectory planning task. An analysis of runtime demonstrated its potential for real-world applications.

随着公众对自动驾驶汽车的关注日益增加，开发可解释的自动驾驶规划技术的需求日益增长。传统的风险场方法使用手工制作的势场模型来解释场景中的驱动风险。在解释高度交互的场景时，这种基于知识的先验方法仍然缺乏灵活性，导致可解释性不足。在这项研究中，我们首先提出了风险图的概念，它可以被看作是风险场的离散的、自我载体的视图形式。然后，我们设计了一个可解释的轨迹规划框架，该框架将风险图与由轨迹预测模型生成的候选轨迹树相结合。我们进一步根据风险图中的累积风险从树中筛选安全候选轨迹，然后通过平衡其他驱动目标来选择执行的最佳轨迹。在各种现实场景中的验证结果表明，我们的方法可以生成可理解的风险图，并解释轨迹之间的风险差异。开环实验表明，该模型在求解轨迹规划任务的安全性和效率方面具有优势。对运行时的分析展示了它在实际应用程序中的潜力。

{"title":"Integrating spatial-temporal risk maps with candidate trajectory trees for explainable autonomous driving planning","authors":"Qiyuan Liu , Jiawei Zhang , Jingwei Ge , Cheng Chang , Zhiheng Li , Shen Li , Li Li","doi":"10.1016/j.commtr.2025.100161","DOIUrl":"10.1016/j.commtr.2025.100161","url":null,"abstract":"<div><div>With increasing public concern about autonomous vehicles, there is a growing demand for developing explainable autonomous driving planning technology. Traditional risk field methods use handcrafted potential field models to explain driving risks in a scenario. When explaining highly interactive scenarios, such prior knowledge-based methods still lack flexibility, leading to insufficient interpretability. In this study, we first propose the concept of a risk map that can be seen as a discrete, ego vehicle's view form of the risk field. We then design an explainable trajectory planning framework that integrates risk maps with the candidate trajectory tree generated by trajectory prediction models. We further filter safe candidate trajectories from the tree on the basis of their cumulative risks in the risk maps and then select the optimal trajectory to execute by balancing other driving objectives. The validation results in various real-world scenarios demonstrate that our method can generate understandable risk maps and explain the risk differences between trajectories. Open-loop experiments show our model's advantages in terms of safety and efficiency for the trajectory planning task. An analysis of runtime demonstrated its potential for real-world applications.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100161"},"PeriodicalIF":12.5,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143161572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0