Pub Date : 2024-11-26DOI: 10.1016/j.commtr.2024.100155
Elnaz Emami, Mohsen Ramezani
This study proposes a rebalancing method for a dockless e-micromobility sharing system, employing both trucks and users. Platform-owned trucks relocate and recharge e-micromobility vehicles using battery swapping technology. In addition, some users intending to rent an e-micromobility vehicle are offered incentives to end their trips in defined locations to assist with rebalancing. The integrated formulation of rebalancing and recharging accounts for each e-micromobility vehicle's characteristics, such as location and charge level. The problem is formulated as a mixed binary problem, which minimizes operational costs and total unmet demand while maximizing the system's profit. To solve the optimization problem, a Branch and Bound method is employed. Rebalancing decisions and routing plans of each truck are obtained by solving the optimization problem. We simulate an on-demand shared e-micromobility system with the proposed integrated rebalancing method and conduct numerical studies. The results indicate that the proposed method enhances system performance and user travel times.
{"title":"Integrated operator and user-based rebalancing and recharging in dockless shared e-micromobility systems","authors":"Elnaz Emami, Mohsen Ramezani","doi":"10.1016/j.commtr.2024.100155","DOIUrl":"10.1016/j.commtr.2024.100155","url":null,"abstract":"<div><div>This study proposes a rebalancing method for a dockless e-micromobility sharing system, employing both trucks and users. Platform-owned trucks relocate and recharge e-micromobility vehicles using battery swapping technology. In addition, some users intending to rent an e-micromobility vehicle are offered incentives to end their trips in defined locations to assist with rebalancing. The integrated formulation of rebalancing and recharging accounts for each e-micromobility vehicle's characteristics, such as location and charge level. The problem is formulated as a mixed binary problem, which minimizes operational costs and total unmet demand while maximizing the system's profit. To solve the optimization problem, a Branch and Bound method is employed. Rebalancing decisions and routing plans of each truck are obtained by solving the optimization problem. We simulate an on-demand shared e-micromobility system with the proposed integrated rebalancing method and conduct numerical studies. The results indicate that the proposed method enhances system performance and user travel times.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"4 ","pages":"Article 100155"},"PeriodicalIF":12.5,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142722281","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}
Pub Date : 2024-11-25DOI: 10.1016/j.commtr.2024.100148
Fangjie Liu , Muhammad Shafique , Xiaowei Luo
The transition toward battery electric vehicles (BEVs) is a critical element in the global shift toward sustainable transportation. This meta-analysis delves into the multifaceted factors influencing BEV performance, including environmental, technological, behavioral, and political-economic determinants. The purpose of this review is to systematically organize and assess how these factors impact BEV efficiency and sustainability across various operational scenarios, such as driving, charging, and decommissioning. By examining a wide range of literature, this study constructs a comprehensive framework that categorizes the primary components and performance metrics, revealing complex relationships and potential causal connections. The findings highlight that although technological advancements and regulatory frameworks are the predominant drivers of BEV performance, environmental conditions and user behaviors also play significant roles. The key emerging topics identified suggest further research avenues, particularly in optimizing battery technology and expanding policy support. Additionally, the analysis provides new and systematic insights compared with previous reviews, offering a clearer understanding of the determinants, their impacts, and the interactions between them. These insights are crucial for developing a transparent evaluation system for future research and policy formulation. This comprehensive synthesis not only aids in understanding the current landscape but also in directing future scholarly and practical endeavors in electric vehicle research.
{"title":"Unveiling the determinants of battery electric vehicle performance: A systematic review and meta-analysis","authors":"Fangjie Liu , Muhammad Shafique , Xiaowei Luo","doi":"10.1016/j.commtr.2024.100148","DOIUrl":"10.1016/j.commtr.2024.100148","url":null,"abstract":"<div><div>The transition toward battery electric vehicles (BEVs) is a critical element in the global shift toward sustainable transportation. This meta-analysis delves into the multifaceted factors influencing BEV performance, including environmental, technological, behavioral, and political-economic determinants. The purpose of this review is to systematically organize and assess how these factors impact BEV efficiency and sustainability across various operational scenarios, such as driving, charging, and decommissioning. By examining a wide range of literature, this study constructs a comprehensive framework that categorizes the primary components and performance metrics, revealing complex relationships and potential causal connections. The findings highlight that although technological advancements and regulatory frameworks are the predominant drivers of BEV performance, environmental conditions and user behaviors also play significant roles. The key emerging topics identified suggest further research avenues, particularly in optimizing battery technology and expanding policy support. Additionally, the analysis provides new and systematic insights compared with previous reviews, offering a clearer understanding of the determinants, their impacts, and the interactions between them. These insights are crucial for developing a transparent evaluation system for future research and policy formulation. This comprehensive synthesis not only aids in understanding the current landscape but also in directing future scholarly and practical endeavors in electric vehicle research.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"4 ","pages":"Article 100148"},"PeriodicalIF":12.5,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707036","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}
Pub Date : 2024-11-14DOI: 10.1016/j.commtr.2024.100147
Fizza Hussain , Yuefeng Li , Md Mazharul Haque
Traffic conflict techniques rely heavily on the proper identification of conflict extremes, which directly affects the prediction performance of extreme value models. Two sampling techniques, namely, block maxima and peak over threshold, form the core of these models. Several studies have demonstrated the inefficacy of extreme value models based on these sampling approaches, as their crash estimates are too imprecise, hindering their widespread practical use. Recently, anomaly detection techniques for sampling conflict extremes have been used, but their application has been limited to estimating crash frequency without considering the crash severity aspect. To address this research gap, this study proposes a hybrid model of machine learning and extreme value theory within a bivariate framework of traffic conflict measures to estimate crash frequency by severity level. In particular, modified time-to-collision (MTTC) and expected post-collision change in velocity (Delta-V or ΔV) have been proposed in the hybrid modeling framework to estimate rear-end crash frequency by severity level. Rear-end conflicts were identified through artificial intelligence-based video analytics for three four-legged signalized intersections in Brisbane, Australia, using four days of data. Non-stationary bivariate hybrid generalized extreme value models with different anomaly detection/sampling techniques (isolation forest and minimum covariance determinant) were developed. The non-stationarity of traffic conflict extremes was handled by parameterizing model parameters, including location, scale, and both location and scale parameters simultaneously. The results indicate that the bivariate hybrid models can estimate severe and non-severe crashes when compared with historical crash records, thereby demonstrating the viability of the proposed approach. A comparative analysis of two anomaly techniques reveals that the isolation forest model marginally outperforms the minimum covariance determinant model. Overall, the modeling framework presented in this study advances conflict-based safety assessment, where the severity dimension can be captured via bivariate hybrid models.
{"title":"Integrating machine learning and extreme value theory for estimating crash frequency-by-severity via AI-based video analytics","authors":"Fizza Hussain , Yuefeng Li , Md Mazharul Haque","doi":"10.1016/j.commtr.2024.100147","DOIUrl":"10.1016/j.commtr.2024.100147","url":null,"abstract":"<div><div>Traffic conflict techniques rely heavily on the proper identification of conflict extremes, which directly affects the prediction performance of extreme value models. Two sampling techniques, namely, block maxima and peak over threshold, form the core of these models. Several studies have demonstrated the inefficacy of extreme value models based on these sampling approaches, as their crash estimates are too imprecise, hindering their widespread practical use. Recently, anomaly detection techniques for sampling conflict extremes have been used, but their application has been limited to estimating crash frequency without considering the crash severity aspect. To address this research gap, this study proposes a hybrid model of machine learning and extreme value theory within a bivariate framework of traffic conflict measures to estimate crash frequency by severity level. In particular, modified time-to-collision (MTTC) and expected post-collision change in velocity (Delta-<em>V</em> or Δ<em>V</em>) have been proposed in the hybrid modeling framework to estimate rear-end crash frequency by severity level. Rear-end conflicts were identified through artificial intelligence-based video analytics for three four-legged signalized intersections in Brisbane, Australia, using four days of data. Non-stationary bivariate hybrid generalized extreme value models with different anomaly detection/sampling techniques (isolation forest and minimum covariance determinant) were developed. The non-stationarity of traffic conflict extremes was handled by parameterizing model parameters, including location, scale, and both location and scale parameters simultaneously. The results indicate that the bivariate hybrid models can estimate severe and non-severe crashes when compared with historical crash records, thereby demonstrating the viability of the proposed approach. A comparative analysis of two anomaly techniques reveals that the isolation forest model marginally outperforms the minimum covariance determinant model. Overall, the modeling framework presented in this study advances conflict-based safety assessment, where the severity dimension can be captured via bivariate hybrid models.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"4 ","pages":"Article 100147"},"PeriodicalIF":12.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661685","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}
Pub Date : 2024-11-13DOI: 10.1016/j.commtr.2024.100149
Shahnaz N. Fuady , Paul C. Pfaffenbichler , Yusak O. Susilo
Rapid urbanization and shifting demographics worldwide necessitate innovative urban transportation solutions. Shared micromobility systems, such as bicycle- and scooter-sharing programs, have emerged as promising alternatives to traditional urban mobility challenges. This study delves into the complexity of shared micromobility fleet development, focusing on the interplay between fleet size, user demand, regulatory frameworks, economic viability, and public engagement. By employing a system dynamics modeling approach that incorporates causal loop diagrams (CLDs) and stock and flow models (SFMs), we explore various policy scenarios to optimize micromobility management systems. Our findings reveal that financial incentives, such as fee reductions and government subsidies, significantly increase user adoption and profitability, whereas increased operational fees necessitate a delicate balance between cost management and service attractiveness. Sensitivity and uncertainty analyses highlight critical parameters for effective fleet management. This research offers actionable insights for policymakers and operators, promoting sustainable urban transport systems.
{"title":"Bridging the gap: Toward a holistic understanding of shared micromobility fleet development dynamics","authors":"Shahnaz N. Fuady , Paul C. Pfaffenbichler , Yusak O. Susilo","doi":"10.1016/j.commtr.2024.100149","DOIUrl":"10.1016/j.commtr.2024.100149","url":null,"abstract":"<div><div>Rapid urbanization and shifting demographics worldwide necessitate innovative urban transportation solutions. Shared micromobility systems, such as bicycle- and scooter-sharing programs, have emerged as promising alternatives to traditional urban mobility challenges. This study delves into the complexity of shared micromobility fleet development, focusing on the interplay between fleet size, user demand, regulatory frameworks, economic viability, and public engagement. By employing a system dynamics modeling approach that incorporates causal loop diagrams (CLDs) and stock and flow models (SFMs), we explore various policy scenarios to optimize micromobility management systems. Our findings reveal that financial incentives, such as fee reductions and government subsidies, significantly increase user adoption and profitability, whereas increased operational fees necessitate a delicate balance between cost management and service attractiveness. Sensitivity and uncertainty analyses highlight critical parameters for effective fleet management. This research offers actionable insights for policymakers and operators, promoting sustainable urban transport systems.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"4 ","pages":"Article 100149"},"PeriodicalIF":12.5,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661682","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}
Pub Date : 2024-11-06DOI: 10.1016/j.commtr.2024.100146
Senyun Kuang, Yang Liu, Xin Wang, Xinhua Wu, Yintao Wei
{"title":"Harnessing multimodal large language models for traffic knowledge graph generation and decision-making","authors":"Senyun Kuang, Yang Liu, Xin Wang, Xinhua Wu, Yintao Wei","doi":"10.1016/j.commtr.2024.100146","DOIUrl":"10.1016/j.commtr.2024.100146","url":null,"abstract":"","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"4 ","pages":"Article 100146"},"PeriodicalIF":12.5,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593075","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}
Pub Date : 2024-11-04DOI: 10.1016/j.commtr.2024.100143
Yujie Yang , Letian Tao , Likun Wang, Shengbo Eben Li
Controllability is a fundamental property of control systems, serving as the prerequisite for controller design. While controllability test is well established in modelic (i.e., model-driven) control systems, extending it to datatic (i.e., data-driven) control systems is still a challenging task due to the absence of system models. In this study, we propose a general controllability test method for nonlinear systems with datatic description, where the system behaviors are merely described by data. In this situation, the state transition information of a dynamic system is available only at a limited number of data points, leaving the behaviors beyond these points unknown. Different from traditional exact controllability, we introduce a new concept called ϵ-controllability, which extends the definition from point-to-point form to point-to-region form. Accordingly, our focus shifts to checking whether the system state can be steered to a closed state ball centered on the target state, rather than exactly at that target state. Given a known state transition sample, the Lipschitz continuity assumption restricts the one-step transition of all the points in a state ball to a small neighborhood of the subsequent state. This property is referred to as one-step controllability backpropagation, i.e., if the states within this neighborhood are ϵ-controllable, those within the state ball are also ϵ-controllable. On its basis, we propose a tree search algorithm called maximum expansion of controllable subset (MECS) to identify controllable states in the dataset. Starting with a specific target state, our algorithm can iteratively propagate controllability from a known state ball to a new one. This iterative process gradually enlarges the ϵ-controllable subset by incorporating new controllable balls until all ϵ-controllable states are searched. Besides, a simplified version of MECS is proposed by solving a special shortest path problem, called Floyd expansion with radius fixed (FERF). FERF maintains a fixed radius of all controllable balls based on a mutual controllability assumption of neighboring states. The effectiveness of our method is validated in three datatic control systems whose dynamic behaviors are described by sampled data.
{"title":"Controllability test for nonlinear datatic systems","authors":"Yujie Yang , Letian Tao , Likun Wang, Shengbo Eben Li","doi":"10.1016/j.commtr.2024.100143","DOIUrl":"10.1016/j.commtr.2024.100143","url":null,"abstract":"<div><div>Controllability is a fundamental property of control systems, serving as the prerequisite for controller design. While controllability test is well established in modelic (i.e., model-driven) control systems, extending it to datatic (i.e., data-driven) control systems is still a challenging task due to the absence of system models. In this study, we propose a general controllability test method for nonlinear systems with datatic description, where the system behaviors are merely described by data. In this situation, the state transition information of a dynamic system is available only at a limited number of data points, leaving the behaviors beyond these points unknown. Different from traditional exact controllability, we introduce a new concept called <em>ϵ</em>-controllability, which extends the definition from point-to-point form to point-to-region form. Accordingly, our focus shifts to checking whether the system state can be steered to a closed state ball centered on the target state, rather than exactly at that target state. Given a known state transition sample, the Lipschitz continuity assumption restricts the one-step transition of all the points in a state ball to a small neighborhood of the subsequent state. This property is referred to as one-step controllability backpropagation, i.e., if the states within this neighborhood are <em>ϵ</em>-controllable, those within the state ball are also <em>ϵ</em>-controllable. On its basis, we propose a tree search algorithm called maximum expansion of controllable subset (MECS) to identify controllable states in the dataset. Starting with a specific target state, our algorithm can iteratively propagate controllability from a known state ball to a new one. This iterative process gradually enlarges the <em>ϵ</em>-controllable subset by incorporating new controllable balls until all <em>ϵ</em>-controllable states are searched. Besides, a simplified version of MECS is proposed by solving a special shortest path problem, called Floyd expansion with radius fixed (FERF). FERF maintains a fixed radius of all controllable balls based on a mutual controllability assumption of neighboring states. The effectiveness of our method is validated in three datatic control systems whose dynamic behaviors are described by sampled data.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"4 ","pages":"Article 100143"},"PeriodicalIF":12.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578752","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}
Pub Date : 2024-10-21DOI: 10.1016/j.commtr.2024.100141
Siyuan Feng , Taijie Chen , Yuhao Zhang , Jintao Ke , Zhengfei Zheng , Hai Yang
On-demand ride services or ride-sourcing services have been experiencing fast development and steadily reshaping the way people travel in the past decade. Various optimization algorithms, including reinforcement learning approaches, have been developed to help ride-sourcing platforms design better operational strategies to achieve higher efficiency. However, due to cost and reliability issues, it is commonly infeasible to validate these models and train/test these optimization algorithms within real-world ride-sourcing platforms. Acting as a proper test bed, a simulation platform for ride-sourcing systems will thus be essential for both researchers and industrial practitioners. While previous studies have established simulators for their tasks, they lack a fair and public platform for comparing the models/algorithms proposed by different researchers. In addition, the existing simulators still face many challenges, ranging from their closeness to real environments of ride-sourcing systems to the completeness of tasks they can implement. To address the challenges, we propose a novel simulation platform for ride-sourcing systems on real transportation networks. It provides a few accessible portals to train and test various optimization algorithms, especially reinforcement learning algorithms, for a variety of tasks, including on-demand matching, idle vehicle repositioning, and dynamic pricing. Evaluated on real-world data-based experiments, the simulator is demonstrated to be an efficient and effective test bed for various tasks related to on-demand ride service operations.
{"title":"A multi-functional simulation platform for on-demand ride service operations","authors":"Siyuan Feng , Taijie Chen , Yuhao Zhang , Jintao Ke , Zhengfei Zheng , Hai Yang","doi":"10.1016/j.commtr.2024.100141","DOIUrl":"10.1016/j.commtr.2024.100141","url":null,"abstract":"<div><div>On-demand ride services or ride-sourcing services have been experiencing fast development and steadily reshaping the way people travel in the past decade. Various optimization algorithms, including reinforcement learning approaches, have been developed to help ride-sourcing platforms design better operational strategies to achieve higher efficiency. However, due to cost and reliability issues, it is commonly infeasible to validate these models and train/test these optimization algorithms within real-world ride-sourcing platforms. Acting as a proper test bed, a simulation platform for ride-sourcing systems will thus be essential for both researchers and industrial practitioners. While previous studies have established simulators for their tasks, they lack a fair and public platform for comparing the models/algorithms proposed by different researchers. In addition, the existing simulators still face many challenges, ranging from their closeness to real environments of ride-sourcing systems to the completeness of tasks they can implement. To address the challenges, we propose a novel simulation platform for ride-sourcing systems on real transportation networks. It provides a few accessible portals to train and test various optimization algorithms, especially reinforcement learning algorithms, for a variety of tasks, including on-demand matching, idle vehicle repositioning, and dynamic pricing. Evaluated on real-world data-based experiments, the simulator is demonstrated to be an efficient and effective test bed for various tasks related to on-demand ride service operations.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"4 ","pages":"Article 100141"},"PeriodicalIF":12.5,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142531464","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}
Pub Date : 2024-10-18DOI: 10.1016/j.commtr.2024.100142
Zihao Sheng, Zilin Huang, Sikai Chen
Model-based reinforcement learning (RL) is anticipated to exhibit higher sample efficiency than model-free RL by utilizing a virtual environment model. However, obtaining sufficiently accurate representations of environmental dynamics is challenging because of uncertainties in complex systems and environments. An inaccurate environment model may degrade the sample efficiency and performance of model-based RL. Furthermore, while model-based RL can improve sample efficiency, it often still requires substantial training time to learn from scratch, potentially limiting its advantages over model-free approaches. To address these challenges, this paper introduces a knowledge-informed model-based residual reinforcement learning framework aimed at enhancing learning efficiency by infusing established expert knowledge into the learning process and avoiding the issue of beginning from zero. Our approach integrates traffic expert knowledge into a virtual environment model, employing the intelligent driver model (IDM) for basic dynamics and neural networks for residual dynamics, thus ensuring adaptability to complex scenarios. We propose a novel strategy that combines traditional control methods with residual RL, facilitating efficient learning and policy optimization without the need to learn from scratch. The proposed approach is applied to connected automated vehicle (CAV) trajectory control tasks for the dissipation of stop-and-go waves in mixed traffic flows. The experimental results demonstrate that our proposed approach enables the CAV agent to achieve superior performance in trajectory control compared with the baseline agents in terms of sample efficiency, traffic flow smoothness and traffic mobility.
{"title":"Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control","authors":"Zihao Sheng, Zilin Huang, Sikai Chen","doi":"10.1016/j.commtr.2024.100142","DOIUrl":"10.1016/j.commtr.2024.100142","url":null,"abstract":"<div><div>Model-based reinforcement learning (RL) is anticipated to exhibit higher sample efficiency than model-free RL by utilizing a virtual environment model. However, obtaining sufficiently accurate representations of environmental dynamics is challenging because of uncertainties in complex systems and environments. An inaccurate environment model may degrade the sample efficiency and performance of model-based RL. Furthermore, while model-based RL can improve sample efficiency, it often still requires substantial training time to learn from scratch, potentially limiting its advantages over model-free approaches. To address these challenges, this paper introduces a knowledge-informed model-based residual reinforcement learning framework aimed at enhancing learning efficiency by infusing established expert knowledge into the learning process and avoiding the issue of beginning from zero. Our approach integrates traffic expert knowledge into a virtual environment model, employing the intelligent driver model (IDM) for basic dynamics and neural networks for residual dynamics, thus ensuring adaptability to complex scenarios. We propose a novel strategy that combines traditional control methods with residual RL, facilitating efficient learning and policy optimization without the need to learn from scratch. The proposed approach is applied to connected automated vehicle (CAV) trajectory control tasks for the dissipation of stop-and-go waves in mixed traffic flows. The experimental results demonstrate that our proposed approach enables the CAV agent to achieve superior performance in trajectory control compared with the baseline agents in terms of sample efficiency, traffic flow smoothness and traffic mobility.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"4 ","pages":"Article 100142"},"PeriodicalIF":12.5,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142531463","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号