Multimodal Transportation最新文献_第7页

Multimodal adaptive traffic signal control: A decentralized multiagent reinforcement learning approach 多模式自适应交通信号控制：一种分散的多智能体强化学习方法

Multimodal Transportation

Pub Date : 2025-01-09 DOI: 10.1016/j.multra.2025.100190

Kareem Othman , Xiaoyu Wang , Amer Shalaby , Baher Abdulhai

Public transit is considered a compelling alternative to the car, renowned for its affordability and sustainability, given that a single transit vehicle can accommodate a substantially higher number of passengers compared to regular passenger vehicles. In urban areas, a significant portion of the travel time spent by street-running transit vehicles is consumed waiting at traffic signals. Thus, transit signal priority (TSP) strategies have evolved over the years to give preference to transit vehicles at signalized intersections. Traffic signals are usually optimized for the general vehicular traffic flow, with TSP logic subsequently inserted as an add-on to modify the underlying signal timing plans, thereby granting priority to transit vehicles. However, one major issue associated with the implementation of TSP is its negative impact on the surrounding traffic, creating a conflict between prioritizing passenger vehicles versus transit vehicles. This paper proposes a novel decentralized multimodal multiagent reinforcement learning signal controller that simultaneously optimizes the total person delays for both traffic and transit. The controller, named embedding communicated Multi-Agent Reinforcement Learning for Integrated Network-Multi Modal (eMARLIN-MM), consists of two components: the encoder that is responsible for transforming the observations into latent space and the executor that serves as the Q-network making timing decisions. eMARLIN-MM establishes communication between the control agents by sharing information between neighboring intersections. eMARLIN-MM was tested in a simulation model of five intersections in North York, Ontario, Canada. The results show that eMARLIN-MM can substantially reduce the total person delays by 54 % to 66 % compared to pre-timed signals at different levels of bus occupancy, outperforming the independent Deep Q-Networks (DQN) agents. eMARLIN-MM also outperforms eMARLIN which does not incorporate buses and bus passengers in the signal timing optimization process.

公共交通被认为是汽车的一个令人信服的替代品，以其可负担性和可持续性而闻名，因为与普通乘用车相比，一辆公共交通工具可以容纳更多的乘客。在城市地区，在街道上运行的交通车辆的很大一部分时间都花在了等待交通信号上。因此，多年来，交通信号优先（TSP）策略已经发展到优先考虑信号交叉口的交通车辆。交通信号通常针对一般车辆交通流进行优化，随后插入TSP逻辑作为附加组件来修改底层信号授时计划，从而赋予过境车辆优先权。然而，与TSP实施相关的一个主要问题是它对周围交通的负面影响，造成了优先考虑客运车辆与公交车辆之间的冲突。提出了一种新的分散多模态多智能体强化学习信号控制器，该控制器可以同时优化交通和公交的总延误。该控制器名为嵌入通信多智能体强化学习集成网络-多模态（eMARLIN-MM），由两个部分组成：负责将观测值转换为潜在空间的编码器和作为q网络进行时序决策的执行器。eMARLIN-MM通过在相邻的交叉口之间共享信息来建立控制代理之间的通信。eMARLIN-MM在加拿大安大略省北约克的五个十字路口的仿真模型中进行了测试。结果表明，eMARLIN-MM在不同的公交占用率水平下，与预定时信号相比，可以显著减少54%至66%的总人员延误，优于独立的深度q网络（DQN）代理。eMARLIN- mm在信号配时优化过程中也优于不考虑公交车和公交车乘客的eMARLIN。

{"title":"Multimodal adaptive traffic signal control: A decentralized multiagent reinforcement learning approach","authors":"Kareem Othman , Xiaoyu Wang , Amer Shalaby , Baher Abdulhai","doi":"10.1016/j.multra.2025.100190","DOIUrl":"10.1016/j.multra.2025.100190","url":null,"abstract":"<div><div>Public transit is considered a compelling alternative to the car, renowned for its affordability and sustainability, given that a single transit vehicle can accommodate a substantially higher number of passengers compared to regular passenger vehicles. In urban areas, a significant portion of the travel time spent by street-running transit vehicles is consumed waiting at traffic signals. Thus, transit signal priority (TSP) strategies have evolved over the years to give preference to transit vehicles at signalized intersections. Traffic signals are usually optimized for the general vehicular traffic flow, with TSP logic subsequently inserted as an add-on to modify the underlying signal timing plans, thereby granting priority to transit vehicles. However, one major issue associated with the implementation of TSP is its negative impact on the surrounding traffic, creating a conflict between prioritizing passenger vehicles versus transit vehicles. This paper proposes a novel decentralized multimodal multiagent reinforcement learning signal controller that simultaneously optimizes the total person delays for both traffic and transit. The controller, named embedding communicated Multi-Agent Reinforcement Learning for Integrated Network-Multi Modal (eMARLIN-MM), consists of two components: the encoder that is responsible for transforming the observations into latent space and the executor that serves as the Q-network making timing decisions. eMARLIN-MM establishes communication between the control agents by sharing information between neighboring intersections. eMARLIN-MM was tested in a simulation model of five intersections in North York, Ontario, Canada. The results show that eMARLIN-MM can substantially reduce the total person delays by 54 % to 66 % compared to pre-timed signals at different levels of bus occupancy, outperforming the independent Deep Q-Networks (DQN) agents. eMARLIN-MM also outperforms eMARLIN which does not incorporate buses and bus passengers in the signal timing optimization process.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100190"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133443","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

Maritime vessel movement prediction: A temporal convolutional network model with optimal look-back window size determination 船舶运动预测：具有最佳回望窗大小确定的时间卷积网络模型

Multimodal Transportation

Pub Date : 2025-01-09 DOI: 10.1016/j.multra.2025.100191

Farshad Farahnakian, Paavo Nevalainen, Fahimeh Farahnakian, Tanja Vähämäki, Jukka Heikkonen

Ship movement prediction models are crucial for improving safety and situational awareness in complex maritime shipping networks. Current prediction models that utilize Automatic Identification System (AIS) data to forecast ship movements typically rely on a fixed look-back window size. This approach does not effectively consider the necessary amount of data required to train the models properly. This paper presents a framework that dynamically determines the optimal look-back window size for AIS data, tailored to user-defined prediction intervals. Initially, a DBSCAN clustering method, along with various pre-processing techniques, has been employed to efficiently eliminate non-essential data points and address noise in the raw AIS data. Following this, Temporal Convolutional Networks (TCNs) have been trained using the dynamic characteristics of ship movements based on one month of AIS data (April 2023) collected from the Baltic Sea, evaluating various look-back window sizes to identify the optimal size required for predictions. Subsequently, the framework has been tested using an additional AIS dataset in two scenarios: 1-hour and 5-hour predictions. The experimental results indicate that the proposed framework can effectively select the necessary AIS samples for forecasting a ship’s future movements. This framework has the potential to optimize prediction services by identifying the ideal look-back window size, thereby providing maritime agents with high-quality and accurate predictions to enhance their decision-making processes.

在复杂的海上航运网络中，船舶运动预测模型对于提高安全性和态势感知至关重要。目前利用自动识别系统（AIS）数据预测船舶运动的预测模型通常依赖于固定的后视窗口大小。这种方法没有有效地考虑正确训练模型所需的必要数据量。本文提出了一个框架，动态确定AIS数据的最佳回望窗口大小，根据用户自定义的预测间隔量身定制。最初，采用DBSCAN聚类方法以及各种预处理技术，有效地消除非必要数据点并处理原始AIS数据中的噪声。在此之后，基于从波罗的海收集的一个月的AIS数据（2023年4月），使用船舶运动的动态特征对时间卷积网络（tcn）进行了训练，评估了各种回看窗口的大小，以确定预测所需的最佳大小。随后，使用额外的AIS数据集在两种情况下对该框架进行了测试：1小时和5小时预测。实验结果表明，该框架可以有效地选择所需的AIS样本来预测船舶的未来运动。该框架有可能通过确定理想的回望窗口大小来优化预测服务，从而为海事代理提供高质量和准确的预测，以提高他们的决策过程。

{"title":"Maritime vessel movement prediction: A temporal convolutional network model with optimal look-back window size determination","authors":"Farshad Farahnakian, Paavo Nevalainen, Fahimeh Farahnakian, Tanja Vähämäki, Jukka Heikkonen","doi":"10.1016/j.multra.2025.100191","DOIUrl":"10.1016/j.multra.2025.100191","url":null,"abstract":"<div><div>Ship movement prediction models are crucial for improving safety and situational awareness in complex maritime shipping networks. Current prediction models that utilize Automatic Identification System (AIS) data to forecast ship movements typically rely on a fixed look-back window size. This approach does not effectively consider the necessary amount of data required to train the models properly. This paper presents a framework that dynamically determines the optimal look-back window size for AIS data, tailored to user-defined prediction intervals. Initially, a DBSCAN clustering method, along with various pre-processing techniques, has been employed to efficiently eliminate non-essential data points and address noise in the raw AIS data. Following this, Temporal Convolutional Networks (TCNs) have been trained using the dynamic characteristics of ship movements based on one month of AIS data (April 2023) collected from the Baltic Sea, evaluating various look-back window sizes to identify the optimal size required for predictions. Subsequently, the framework has been tested using an additional AIS dataset in two scenarios: 1-hour and 5-hour predictions. The experimental results indicate that the proposed framework can effectively select the necessary AIS samples for forecasting a ship’s future movements. This framework has the potential to optimize prediction services by identifying the ideal look-back window size, thereby providing maritime agents with high-quality and accurate predictions to enhance their decision-making processes.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100191"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133445","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

Autonomous vehicle safety: An advanced bagging classifier technique for crash injury prediction 自动驾驶汽车安全：一种用于碰撞损伤预测的先进袋装分类技术

Multimodal Transportation

Pub Date : 2025-01-07 DOI: 10.1016/j.multra.2025.100189

Sai Sneha Channamallu, Deema Almaskati, Sharareh Kermanshachi, Apurva Pamidimukkala

The increasing utilization of autonomous vehicles (AVs) makes it critical to understand and mitigate their involvement in traffic accidents. This study, therefore, addresses a significant gap in the research on AV safety by focusing on predicting the possibility of injuries in AV-involved crashes. The California Department of Motor Vehicles’ comprehensive dataset of accidents that occurred from 2014 to May 2024 was utilized, and advanced machine learning techniques were applied to develop a model capable of predicting the outcomes of accidents involving AVs. The study found that the bagging classifier model outperforms other models in reliably predicting and identifying severe crashes and minimizing misclassification. Evaluations made through precision-recall, validation, and learning curves confirm the model's robustness, ability to generalize across data subsets, and effectiveness in increasing training data. Key predictors of crash severity include the extent of damage to the AV, vehicle type, manufacturer, and presence of a traffic signal. The study highlights the importance of tailored safety measures, robust safety mechanisms, and advanced traffic management systems to mitigate crash severity. The real-world application of this advanced model promises substantial benefits for vehicle manufacturers, urban planners, policymakers, and end-users, and will contribute to safer roadways.

自动驾驶汽车（AVs）的使用率越来越高，因此了解和减少它们与交通事故的关系至关重要。因此，本研究通过专注于预测自动驾驶事故中受伤的可能性，解决了自动驾驶安全研究中的一个重大空白。利用加州机动车辆管理局2014年至2024年5月发生的事故综合数据集，并应用先进的机器学习技术开发了一个能够预测涉及自动驾驶汽车事故结果的模型。研究发现，套袋分类器模型在可靠地预测和识别严重碰撞和最小化错误分类方面优于其他模型。通过精确召回率、验证和学习曲线进行的评估确认了模型的鲁棒性、跨数据子集的泛化能力以及增加训练数据的有效性。碰撞严重程度的关键预测因素包括自动驾驶汽车的损坏程度、车辆类型、制造商和交通信号的存在。该研究强调了量身定制的安全措施、健全的安全机制和先进的交通管理系统对于减轻碰撞严重程度的重要性。这一先进模型的实际应用为汽车制造商、城市规划者、政策制定者和最终用户带来了巨大的好处，并将有助于提高道路的安全性。

{"title":"Autonomous vehicle safety: An advanced bagging classifier technique for crash injury prediction","authors":"Sai Sneha Channamallu, Deema Almaskati, Sharareh Kermanshachi, Apurva Pamidimukkala","doi":"10.1016/j.multra.2025.100189","DOIUrl":"10.1016/j.multra.2025.100189","url":null,"abstract":"<div><div>The increasing utilization of autonomous vehicles (AVs) makes it critical to understand and mitigate their involvement in traffic accidents. This study, therefore, addresses a significant gap in the research on AV safety by focusing on predicting the possibility of injuries in AV-involved crashes. The California Department of Motor Vehicles’ comprehensive dataset of accidents that occurred from 2014 to May 2024 was utilized, and advanced machine learning techniques were applied to develop a model capable of predicting the outcomes of accidents involving AVs. The study found that the bagging classifier model outperforms other models in reliably predicting and identifying severe crashes and minimizing misclassification. Evaluations made through precision-recall, validation, and learning curves confirm the model's robustness, ability to generalize across data subsets, and effectiveness in increasing training data. Key predictors of crash severity include the extent of damage to the AV, vehicle type, manufacturer, and presence of a traffic signal. The study highlights the importance of tailored safety measures, robust safety mechanisms, and advanced traffic management systems to mitigate crash severity. The real-world application of this advanced model promises substantial benefits for vehicle manufacturers, urban planners, policymakers, and end-users, and will contribute to safer roadways.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100189"},"PeriodicalIF":0.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132800","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

Robust optimization of multi-regional truck scheduling for China-ASEAN cross-border container drayage 面向中国-东盟跨境集装箱运输的多区域卡车调度鲁棒优化

Multimodal Transportation

Pub Date : 2025-01-07 DOI: 10.1016/j.multra.2025.100187

Jie He, Zhiming Fang, Xintong Yan, Yuntao Ye, Hao Zhang, Changjian Zhang

Container drayage plays an important role in realizing cargo pickup and delivery between container yards and customers. To further describe and optimize the cross-border container drayage between China and the Association of Southeast Asian Nations (ASEAN), this paper studies a multi-regional container drayage problem under travel time uncertainty (MR-CDP-TTU), where multi-regional truck participation and travel time uncertainty are simultaneously considered. We first develop a multi-regional truck scheduling robust optimization model with travel time as the uncertain parameter and the objective of minimizing the total cost. Then, a variable neighborhood tabu search algorithm (VNTSA) is designed by introducing a greedy insertion method to generate the initial solution and structurally combining the tabu search algorithm with the variable neighborhood search algorithm. Finally, comparison and sensitivity analysis is conducted on the cross-border container drayage instances from a China's international logistics company. The results demonstrate that the designed algorithm outperforms in best value, average value, and standard deviation, which indicate that the algorithm can generate quality and stable solutions for the MR-CDP-TTU. Furthermore, the method proposed in this study enables China-ASEAN cross-border logistics to rationally schedule the multi-regional trucks according to their risk attitudes and the maximum deviations of travel time.

集装箱拖运在实现集装箱堆场与客户之间的货物装卸中起着重要的作用。为了进一步描述和优化中国与东盟之间的跨境集装箱运输，本文研究了考虑旅行时间不确定性（MR-CDP-TTU）的多区域集装箱运输问题，其中同时考虑了多区域卡车参与和旅行时间不确定性。首先建立了以行程时间为不确定参数，以总成本最小为目标的多区域货车调度鲁棒优化模型。然后，引入贪婪插入法生成初始解，将禁忌搜索算法与可变邻域搜索算法在结构上结合，设计了一种可变邻域禁忌搜索算法（VNTSA）。最后，对中国某国际物流公司的跨境集装箱拖运实例进行对比和敏感性分析。结果表明，所设计的算法在最优值、平均值和标准差方面都优于其他算法，表明该算法能够生成高质量、稳定的MR-CDP-TTU解。此外，本文提出的方法使中国-东盟跨境物流能够根据其风险态度和旅行时间的最大偏差，对多区域卡车进行合理调度。

{"title":"Robust optimization of multi-regional truck scheduling for China-ASEAN cross-border container drayage","authors":"Jie He, Zhiming Fang, Xintong Yan, Yuntao Ye, Hao Zhang, Changjian Zhang","doi":"10.1016/j.multra.2025.100187","DOIUrl":"10.1016/j.multra.2025.100187","url":null,"abstract":"<div><div>Container drayage plays an important role in realizing cargo pickup and delivery between container yards and customers. To further describe and optimize the cross-border container drayage between China and the Association of Southeast Asian Nations (ASEAN), this paper studies a multi-regional container drayage problem under travel time uncertainty (MR-CDP-TTU), where multi-regional truck participation and travel time uncertainty are simultaneously considered. We first develop a multi-regional truck scheduling robust optimization model with travel time as the uncertain parameter and the objective of minimizing the total cost. Then, a variable neighborhood tabu search algorithm (VNTSA) is designed by introducing a greedy insertion method to generate the initial solution and structurally combining the tabu search algorithm with the variable neighborhood search algorithm. Finally, comparison and sensitivity analysis is conducted on the cross-border container drayage instances from a China's international logistics company. The results demonstrate that the designed algorithm outperforms in best value, average value, and standard deviation, which indicate that the algorithm can generate quality and stable solutions for the MR-CDP-TTU. Furthermore, the method proposed in this study enables China-ASEAN cross-border logistics to rationally schedule the multi-regional trucks according to their risk attitudes and the maximum deviations of travel time.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100187"},"PeriodicalIF":0.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133441","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

How realistic a bicycle simulator can be? - A validation study 自行车模拟器能有多逼真？-验证研究

Multimodal Transportation

Pub Date : 2025-01-04 DOI: 10.1016/j.multra.2025.100193

Amira Hammami, Attila Borsos, Ágoston Pál Sándor

The aim of this research is to objectively and subjectively validate the virtual reality Bicycle Simulator (BS) developed using off-the-shelf components at the University of Győr, Hungary.

To this end, this research compares the performance of 32 participants in two real-world environments (Site 1: separated bicycle-pedestrian path and Site 2: advisory bicycle lane) and in their replication in virtual reality (VR). The objective measures collected for the comparison include speed and Cumulative Lateral Position (CLP), whereas subjective measures include the Perceived Level of Realism (PLR) based on participants’ self-reported perceptions in a post-experiment questionnaire. PLR is a new indicator that we propose using subjects' perceptions of speed, BS control, and VR representation. The combination of these subjective and objective measures is proposed as the Degree of Realism (DR) to standardise the classification of the realism level of a bicycle simulator.

Subjectively, the results indicate that the BS provides a high level of safety and comfort for conducting such research. Subject characteristics have no significant influence on VR sickness scores or Perceived Level of Realism. Objectively, for both speed and CLP, we found no significant difference between on-site and the simulation measurements in the case of Site 1, but otherwise for Site 2. However, subjects were not able to accurately perceive either the actual or the relative differences.

In conclusion, our bicycle simulator is a safe and comfortable traffic safety research tool that needs further improvement. The proposed preliminary concept of the degree of realism requires further investigation.

本研究的目的是客观和主观地验证虚拟现实自行车模拟器（BS）使用匈牙利Győr大学的现成组件开发。为此，本研究比较了32名参与者在两个真实世界环境中的表现（站点1：分离的自行车-人行道和站点2：咨询自行车道）以及他们在虚拟现实（VR）中的复制。比较的客观测量包括速度和累积横向位置（CLP），而主观测量包括现实主义感知水平（PLR），基于参与者在实验后问卷中自我报告的感知。PLR是一个新的指标，我们建议使用受试者对速度，BS控制和VR表征的感知。将这些主观和客观的度量结合起来，提出了真实感度（DR）来规范自行车模拟器的真实感等级的分类。主观上，结果表明BS为进行此类研究提供了高水平的安全性和舒适性。受试者特征对虚拟现实疾病得分和现实主义感知水平无显著影响。客观地说，就速度和CLP而言，我们发现在Site 1的情况下，现场和模拟测量之间没有显著差异，但对于Site 2则不然。然而，受试者不能准确地感知实际差异或相对差异。总之，我们的自行车模拟器是一个安全舒适的交通安全研究工具，需要进一步完善。提出的现实程度的初步概念需要进一步调查。

{"title":"How realistic a bicycle simulator can be? - A validation study","authors":"Amira Hammami, Attila Borsos, Ágoston Pál Sándor","doi":"10.1016/j.multra.2025.100193","DOIUrl":"10.1016/j.multra.2025.100193","url":null,"abstract":"<div><div>The aim of this research is to objectively and subjectively validate the virtual reality Bicycle Simulator (BS) developed using off-the-shelf components at the University of Győr, Hungary.</div><div>To this end, this research compares the performance of 32 participants in two real-world environments (Site 1: separated bicycle-pedestrian path and Site 2: advisory bicycle lane) and in their replication in virtual reality (VR). The objective measures collected for the comparison include speed and Cumulative Lateral Position (CLP), whereas subjective measures include the Perceived Level of Realism (PLR) based on participants’ self-reported perceptions in a post-experiment questionnaire. PLR is a new indicator that we propose using subjects' perceptions of speed, BS control, and VR representation. The combination of these subjective and objective measures is proposed as the Degree of Realism (DR) to standardise the classification of the realism level of a bicycle simulator.</div><div>Subjectively, the results indicate that the BS provides a high level of safety and comfort for conducting such research. Subject characteristics have no significant influence on VR sickness scores or Perceived Level of Realism. Objectively, for both speed and CLP, we found no significant difference between on-site and the simulation measurements in the case of Site 1, but otherwise for Site 2. However, subjects were not able to accurately perceive either the actual or the relative differences.</div><div>In conclusion, our bicycle simulator is a safe and comfortable traffic safety research tool that needs further improvement. The proposed preliminary concept of the degree of realism requires further investigation.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100193"},"PeriodicalIF":0.0,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132797","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

Investigating the non-linear influence of the built environment on passengers’ travel distance within metro and bus networks using smart card data 利用智能卡数据研究了地铁和公交网络内建筑环境对乘客出行距离的非线性影响

Multimodal Transportation

Pub Date : 2025-01-04 DOI: 10.1016/j.multra.2025.100188

Yang Liu, Donglin He, Jiayou Lei, Mingwei He, Zhuangbin Shi

Understanding the travel behavior of transit passengers and its influencing factors is crucial for promoting transit use and alleviating urban traffic congestion. However, limited studies have examined the determinants of spatial expansion in multimodal public transportation and overlooked the nonlinear influence between variables. To address these gaps, this study employs the travel distance indicator to portray the spatial expansion of transit passengers. Using smart card data collected from Beijing, China, we propose a comprehensive trip chain extraction method within the metro and bus network, considering transfer behaviors. From the extracted trip chain data, we calculate travel distances and observe significant variations across different transit networks: an average travel distance of 8.09 km in the bus network, 14.93 km in the metro network, and 23.10 km in the integrated network. Further, we explore the non-linear relationship between transit travel distance and the built environment by employing a Gradient Boosting Regression Tree (GBRT) model. The finding reveals that the built environment exerts the most significant influence on travel distance (46.80 %), particularly regarding the distance to the nearest metro station and the central business district (CBD). Additionally, all variables exhibit non-linear effects on travel distance, with many exhibiting relevance only within specific ranges. For instance, there is a noticeable decline in travel distance when the bus stop density falls within the range of 15 units/km² and the bus coverage rate within a range of 0.8. Beyond these threshold values, the decline in travel distance becomes gradual. These findings emphasize the significance of considering non-linear relationships and threshold effects in transit and urban planning. Finally, this study provides practicable recommendations regarding non-linearities for the government that could be beneficial in promoting transit usage.

了解公交乘客的出行行为及其影响因素，对于促进公交使用、缓解城市交通拥堵具有重要意义。然而，有限的研究考察了多式联运公共交通空间扩展的决定因素，忽视了变量之间的非线性影响。为了解决这些差距，本研究采用出行距离指标来描绘过境旅客的空间扩张。基于北京的智能卡数据，在考虑换乘行为的基础上，提出了一种综合的地铁和公交网络出行链提取方法。从提取的出行链数据中，我们计算了出行距离，并观察到不同交通网络之间的显著差异：公交网络的平均出行距离为8.09 km，地铁网络的平均出行距离为14.93 km，综合网络的平均出行距离为23.10 km。此外，我们采用梯度增强回归树（GBRT）模型探讨了交通出行距离与建成环境之间的非线性关系。研究结果表明，建筑环境对出行距离的影响最为显著（46.80%），尤其是到最近的地铁站和中央商务区（CBD）的距离。此外，所有变量对旅行距离都表现出非线性影响，其中许多变量仅在特定范围内表现出相关性。例如，当公交站点密度在15个单位/km²范围内，公交覆盖率在0.8范围内时，出行距离明显下降。超过这些阈值，行进距离的下降是逐渐的。这些发现强调了在交通和城市规划中考虑非线性关系和阈值效应的重要性。最后，本研究为政府提供了有关非线性的可行建议，有助于促进公共交通的使用。

{"title":"Investigating the non-linear influence of the built environment on passengers’ travel distance within metro and bus networks using smart card data","authors":"Yang Liu, Donglin He, Jiayou Lei, Mingwei He, Zhuangbin Shi","doi":"10.1016/j.multra.2025.100188","DOIUrl":"10.1016/j.multra.2025.100188","url":null,"abstract":"<div><div>Understanding the travel behavior of transit passengers and its influencing factors is crucial for promoting transit use and alleviating urban traffic congestion. However, limited studies have examined the determinants of spatial expansion in multimodal public transportation and overlooked the nonlinear influence between variables. To address these gaps, this study employs the travel distance indicator to portray the spatial expansion of transit passengers. Using smart card data collected from Beijing, China, we propose a comprehensive trip chain extraction method within the metro and bus network, considering transfer behaviors. From the extracted trip chain data, we calculate travel distances and observe significant variations across different transit networks: an average travel distance of 8.09 km in the bus network, 14.93 km in the metro network, and 23.10 km in the integrated network. Further, we explore the non-linear relationship between transit travel distance and the built environment by employing a Gradient Boosting Regression Tree (GBRT) model. The finding reveals that the built environment exerts the most significant influence on travel distance (46.80 %), particularly regarding the distance to the nearest metro station and the central business district (CBD). Additionally, all variables exhibit non-linear effects on travel distance, with many exhibiting relevance only within specific ranges. For instance, there is a noticeable decline in travel distance when the bus stop density falls within the range of 15 units/km² and the bus coverage rate within a range of 0.8. Beyond these threshold values, the decline in travel distance becomes gradual. These findings emphasize the significance of considering non-linear relationships and threshold effects in transit and urban planning. Finally, this study provides practicable recommendations regarding non-linearities for the government that could be beneficial in promoting transit usage.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100188"},"PeriodicalIF":0.0,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133444","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

Experimental determination of factors causing crashes involving automated vehicles 实验确定导致自动驾驶车辆碰撞的因素

Multimodal Transportation

Pub Date : 2024-12-30 DOI: 10.1016/j.multra.2024.100186

Teshome Kumsa Kurse , Girma Gebresenbet , Geleta Fikadu Daba , Negasa Tesfaye Tefera

Emergence of technologies to replace human action is occurring in many sectors, with autonomous vehicles being a leading example. Autonomous vehicles do not require human interaction and instead employ various devices to perform essential operations. This paper assesses factors which cause autonomous vehicles to suffer crashes, using field data collected by the Californian Department of Motor Vehicles. Data on these highly automated vehicles (AVs) were clustered based on degree and direction of impact, and analyzed by coding in Excel and RStudio programming. A novel feature of the work is that all clustering, analysis, application of association rules, and determination of degrees of severity of crashes were done by RStudio programming and that the direction of autonomous vehicles impacts was identified based on field data. Our analysis reveals that weather conditions, maneuvering, road conditions, and lighting are major factors in autonomous vehicles crashes. Rear-end crash and minor scratches to autonomous vehicles are the most frequent forms of damage, based on the available data. This study underscores the critical need for enhanced sensor technologies and improved algorithms to better handle adverse weather conditions, complex maneuvers, and varying road and lighting conditions. By identifying the most frequent types of damage, such as rear-end crashes and minor scratches, this research provides valuable insights for manufacturers and policymakers aiming to improve the safety and reliability of autonomous vehicles. The findings can inform future design improvements and regulatory measures, ultimately contributing to the reduction of crash rates and the advancement of autonomous vehicle technology.

许多领域都出现了取代人类行为的技术，自动驾驶汽车就是一个典型的例子。自动驾驶汽车不需要人工干预，而是使用各种设备来执行基本操作。本文利用加州机动车辆管理局收集的现场数据，评估了导致自动驾驶汽车发生碰撞的因素。这些高度自动化车辆（AVs）的数据根据影响程度和方向聚类，并通过Excel和RStudio编程进行编码分析。这项工作的一个新特点是，所有的聚类、分析、关联规则的应用和碰撞严重程度的确定都是由RStudio编程完成的，自动驾驶汽车的影响方向是根据现场数据确定的。我们的分析显示，天气条件、机动、道路状况和照明是自动驾驶汽车撞车的主要因素。根据现有数据，自动驾驶汽车最常见的损坏形式是追尾碰撞和轻微划痕。这项研究强调了增强传感器技术和改进算法的迫切需要，以更好地处理恶劣天气条件、复杂机动以及变化的道路和照明条件。通过识别最常见的损坏类型，如追尾碰撞和轻微划痕，该研究为旨在提高自动驾驶汽车安全性和可靠性的制造商和政策制定者提供了有价值的见解。研究结果可以为未来的设计改进和监管措施提供参考，最终有助于降低碰撞率和推进自动驾驶汽车技术。

{"title":"Experimental determination of factors causing crashes involving automated vehicles","authors":"Teshome Kumsa Kurse , Girma Gebresenbet , Geleta Fikadu Daba , Negasa Tesfaye Tefera","doi":"10.1016/j.multra.2024.100186","DOIUrl":"10.1016/j.multra.2024.100186","url":null,"abstract":"<div><div>Emergence of technologies to replace human action is occurring in many sectors, with autonomous vehicles being a leading example. Autonomous vehicles do not require human interaction and instead employ various devices to perform essential operations. This paper assesses factors which cause autonomous vehicles to suffer crashes, using field data collected by the Californian Department of Motor Vehicles. Data on these highly automated vehicles (AVs) were clustered based on degree and direction of impact, and analyzed by coding in Excel and RStudio programming. A novel feature of the work is that all clustering, analysis, application of association rules, and determination of degrees of severity of crashes were done by RStudio programming and that the direction of autonomous vehicles impacts was identified based on field data. Our analysis reveals that weather conditions, maneuvering, road conditions, and lighting are major factors in autonomous vehicles crashes. Rear-end crash and minor scratches to autonomous vehicles are the most frequent forms of damage, based on the available data. This study underscores the critical need for enhanced sensor technologies and improved algorithms to better handle adverse weather conditions, complex maneuvers, and varying road and lighting conditions. By identifying the most frequent types of damage, such as rear-end crashes and minor scratches, this research provides valuable insights for manufacturers and policymakers aiming to improve the safety and reliability of autonomous vehicles. The findings can inform future design improvements and regulatory measures, ultimately contributing to the reduction of crash rates and the advancement of autonomous vehicle technology.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100186"},"PeriodicalIF":0.0,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132798","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

Analysis of the driver's stress level while driving in Truck Platooning 卡车队列行驶中驾驶员压力水平分析

Multimodal Transportation

Pub Date : 2024-12-27 DOI: 10.1016/j.multra.2024.100185

Paolo Gandini, Luca Studer, Marta Zecchini, Marco Ponti

The logistic is interested by changes and truck manufacturers are investing in solutions such as truck platooning. This system leads to benefits (fuel consumption, safety, traffic efficiency). The paper presents the analysis of the psychophysical state of drivers during real tests in truck platooning. The peaks in the LF/HF (Low Frequency/High Frequency) parameter are considered, as they are linked to feelings of discomfort. Their occurrence may indicate whether the psychophysical state of the drivers is influenced by the different phases of driving in platoon. A method is defined to monitor and process the HRV (Heart Rate Variability) physiological parameter and the LF/HF ratio, based on the use of commercial smartwatches. An experimental activity, part of the European project C-Roads, allowed the collection of the physiological parameters of drivers and of the data featuring the vehicles in platoon. In general, the correlation between the two data sets revealed that drivers were not negatively affected by driving in platoon. The monitoring of the Follower driver, compared to the Leader, showed a higher level of stress. Peaks in the LF/HF parameter (i.e. high levels of stress) were associated in the 85 % of the cases to punctual situations that were expected to be stressful. Further possible applications of the method are presented, such as the investigation of the C-ITS impacts on the drivers.

物流对变化感兴趣，卡车制造商正在投资卡车队列等解决方案。这个系统带来了好处（燃油消耗、安全性、交通效率）。本文分析了卡车队列行驶中驾驶员的心理生理状态。考虑LF/HF（低频/高频）参数的峰值，因为它们与不适的感觉有关。这些现象的出现可能表明驾驶员的心理生理状态是否受到队列中不同驾驶阶段的影响。基于商用智能手表的使用，定义了一种监测和处理HRV（心率变异性）生理参数和LF/HF比值的方法。作为欧洲项目C-Roads的一部分，一项实验活动允许收集驾驶员的生理参数和车辆排的数据。总体而言，两个数据集之间的相关性表明，驾驶员不受排驾驶的负面影响。与领头司机相比，跟随司机的监测显示出更高的压力水平。在85%的病例中，LF/HF参数的峰值（即高水平的压力）与预期会有压力的准时情况有关。提出了该方法的进一步应用，如研究C-ITS对驾驶员的影响。

{"title":"Analysis of the driver's stress level while driving in Truck Platooning","authors":"Paolo Gandini, Luca Studer, Marta Zecchini, Marco Ponti","doi":"10.1016/j.multra.2024.100185","DOIUrl":"10.1016/j.multra.2024.100185","url":null,"abstract":"<div><div>The logistic is interested by changes and truck manufacturers are investing in solutions such as truck platooning. This system leads to benefits (fuel consumption, safety, traffic efficiency). The paper presents the analysis of the psychophysical state of drivers during real tests in truck platooning. The peaks in the LF/HF (Low Frequency/High Frequency) parameter are considered, as they are linked to feelings of discomfort. Their occurrence may indicate whether the psychophysical state of the drivers is influenced by the different phases of driving in platoon. A method is defined to monitor and process the HRV (Heart Rate Variability) physiological parameter and the LF/HF ratio, based on the use of commercial smartwatches. An experimental activity, part of the European project C-Roads, allowed the collection of the physiological parameters of drivers and of the data featuring the vehicles in platoon. In general, the correlation between the two data sets revealed that drivers were not negatively affected by driving in platoon. The monitoring of the Follower driver, compared to the Leader, showed a higher level of stress. Peaks in the LF/HF parameter (i.e. high levels of stress) were associated in the 85 % of the cases to punctual situations that were expected to be stressful. Further possible applications of the method are presented, such as the investigation of the C-ITS impacts on the drivers.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100185"},"PeriodicalIF":0.0,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132799","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

The roadmap and strategy for prioritizing the development of public transport in China 中国公共交通优先发展的路线图和战略

Multimodal Transportation

Pub Date : 2024-12-20 DOI: 10.1016/j.multra.2024.100184

Jing Wang , Changjian Liu , Zhouhao Wu , Rufeng Liao , Gengze Li , Huapu Lu

With the acceleration of urbanization and continuous population growth in China, transportation issues in central cities, especially large and mega-cities, have become increasingly prominent. A series of problems such as economic efficiency decline and reduced residents' well-being caused by traffic congestion have become significant factors constraining the sustainable development of cities. As a core component of the urban transportation system, the prioritized development of urban public transportation is crucial for alleviating traffic congestion, improving environmental quality, and enhancing residents' quality of life. However, from the beginning of 2023, the share of public transportation in residents' travel has gradually decreased, with the total passenger volume still lower than the same period in 2019. In response to the challenges faced by the public transportation system under the new circumstances, this paper reviews the necessity of prioritized development of urban public transportation, analyzes the reasons for the decline in the share of public transportation in residents' overall travel modes, and proposes targeted suggestions. On this basis, the paper explores the intrinsic connection between the strategy of prioritizing public transportation development and sustainable urban development.

随着中国城市化进程的加快和人口的持续增长，中心城市特别是特大城市的交通问题日益突出。交通拥堵导致的经济效率下降、居民幸福感下降等一系列问题已成为制约城市可持续发展的重要因素。城市公共交通作为城市交通系统的核心组成部分，优先发展城市公共交通对于缓解交通拥堵、改善环境质量、提高居民生活质量至关重要。然而，从2023年开始，公共交通在居民出行中的占比逐渐下降，总客运量仍低于2019年同期。针对新形势下公共交通系统面临的挑战，本文回顾了城市公共交通优先发展的必要性，分析了公共交通在居民整体出行方式中所占比例下降的原因，并提出了针对性的建议。在此基础上，探讨了公共交通优先发展战略与城市可持续发展的内在联系。

{"title":"The roadmap and strategy for prioritizing the development of public transport in China","authors":"Jing Wang , Changjian Liu , Zhouhao Wu , Rufeng Liao , Gengze Li , Huapu Lu","doi":"10.1016/j.multra.2024.100184","DOIUrl":"10.1016/j.multra.2024.100184","url":null,"abstract":"<div><div>With the acceleration of urbanization and continuous population growth in China, transportation issues in central cities, especially large and mega-cities, have become increasingly prominent. A series of problems such as economic efficiency decline and reduced residents' well-being caused by traffic congestion have become significant factors constraining the sustainable development of cities. As a core component of the urban transportation system, the prioritized development of urban public transportation is crucial for alleviating traffic congestion, improving environmental quality, and enhancing residents' quality of life. However, from the beginning of 2023, the share of public transportation in residents' travel has gradually decreased, with the total passenger volume still lower than the same period in 2019. In response to the challenges faced by the public transportation system under the new circumstances, this paper reviews the necessity of prioritized development of urban public transportation, analyzes the reasons for the decline in the share of public transportation in residents' overall travel modes, and proposes targeted suggestions. On this basis, the paper explores the intrinsic connection between the strategy of prioritizing public transportation development and sustainable urban development.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100184"},"PeriodicalIF":0.0,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133450","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

Challenges in transport modelling and planning 交通建模和规划方面的挑战

Multimodal Transportation

Pub Date : 2024-12-13 DOI: 10.1016/j.multra.2024.100183

Juan de Dios Ortúzar

引用次数: 0