Pub Date : 2023-07-07DOI: 10.1080/21680566.2023.2231159
X. Jin, W. Ma, R. Zhong, G. Jiang
Fundamental diagrams (FDs) are the basis of traffic flow theory. Efficient model calibration from noisy traffic data is essential to identify the parameters of FDs to describe the traffic flow characteristics. Conventional least-squares based methods fit the aggregated traffic data to certain prescribed functions to obtain the FDs without considering the traffic dynamics or data scattering. To deal with this problem, this paper proposes a probabilistic sensitivity analysis guided variational Bayesian (PSA-VB) framework with high efficiency. Firstly, we formulate the calibration problem as a rare event optimization problem. Then, we develop a mean-field variational Bayesian algorithm to infer the unknown parameters by random sampling. To reduce the computational cost, a probabilistic sensitivity analysis (PSA) procedure is introduced for identifying important parameters, and an efficient two-stage PSA-VB calibration algorithm is proposed. We apply the proposed algorithms to calibrate the modified cell transmission model (MCTM) using the traffic data collected from the M25 highway in England. Compared with the cross entropy method (CEM), the least squares (LS) method and the weighted least squares (WLS) method, the proposed PSA-VB method possesses much lower computational cost and faster convergence speed. Moreover, by explicitly considering the traffic dynamics, the PSA-VB method can capture traffic flow characteristics such as the capacity drop.
{"title":"An efficient variational Bayesian algorithm for calibrating fundamental diagrams and its probabilistic sensitivity analysis","authors":"X. Jin, W. Ma, R. Zhong, G. Jiang","doi":"10.1080/21680566.2023.2231159","DOIUrl":"https://doi.org/10.1080/21680566.2023.2231159","url":null,"abstract":"Fundamental diagrams (FDs) are the basis of traffic flow theory. Efficient model calibration from noisy traffic data is essential to identify the parameters of FDs to describe the traffic flow characteristics. Conventional least-squares based methods fit the aggregated traffic data to certain prescribed functions to obtain the FDs without considering the traffic dynamics or data scattering. To deal with this problem, this paper proposes a probabilistic sensitivity analysis guided variational Bayesian (PSA-VB) framework with high efficiency. Firstly, we formulate the calibration problem as a rare event optimization problem. Then, we develop a mean-field variational Bayesian algorithm to infer the unknown parameters by random sampling. To reduce the computational cost, a probabilistic sensitivity analysis (PSA) procedure is introduced for identifying important parameters, and an efficient two-stage PSA-VB calibration algorithm is proposed. We apply the proposed algorithms to calibrate the modified cell transmission model (MCTM) using the traffic data collected from the M25 highway in England. Compared with the cross entropy method (CEM), the least squares (LS) method and the weighted least squares (WLS) method, the proposed PSA-VB method possesses much lower computational cost and faster convergence speed. Moreover, by explicitly considering the traffic dynamics, the PSA-VB method can capture traffic flow characteristics such as the capacity drop.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48397305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-06DOI: 10.1080/21680566.2023.2231158
Wanda Ma, Peng Li, Jing Zhao
ABSTRACT This study introduces an innovative bi-level model to address the challenges of managing traffic flow in construction work zones in urban transportation networks. The model integrates ramp closure, lane reorganization, and signal timing strategies within a network-level framework, thereby capturing the interdependencies between these strategies and enhancing the overall performance of the transportation network. The upper level optimizes the ramp closure locations, traffic control timing at signalized intersections and lane reorganization plans, whereas the lower level determines the optimal routing choice and traffic detour based on a Stochastic User Equilibrium (SUE) model. A Genetic Algorithm (GA)-based heuristic method is proposed to solve the optimization problem, and a case study demonstrates the effectiveness of the proposed approach. This study offers a comprehensive and innovative solution to mitigate the negative impacts of detour traffic on urban transportation networks, assist transportation agencies in effectively managing traffic flow and improve the overall system performance.
{"title":"Joint optimization of ramp closure, lane reorganization, and signal control strategies for freeway mainline closure owing to construction zones","authors":"Wanda Ma, Peng Li, Jing Zhao","doi":"10.1080/21680566.2023.2231158","DOIUrl":"https://doi.org/10.1080/21680566.2023.2231158","url":null,"abstract":"ABSTRACT This study introduces an innovative bi-level model to address the challenges of managing traffic flow in construction work zones in urban transportation networks. The model integrates ramp closure, lane reorganization, and signal timing strategies within a network-level framework, thereby capturing the interdependencies between these strategies and enhancing the overall performance of the transportation network. The upper level optimizes the ramp closure locations, traffic control timing at signalized intersections and lane reorganization plans, whereas the lower level determines the optimal routing choice and traffic detour based on a Stochastic User Equilibrium (SUE) model. A Genetic Algorithm (GA)-based heuristic method is proposed to solve the optimization problem, and a case study demonstrates the effectiveness of the proposed approach. This study offers a comprehensive and innovative solution to mitigate the negative impacts of detour traffic on urban transportation networks, assist transportation agencies in effectively managing traffic flow and improve the overall system performance.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46000886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-30DOI: 10.1080/21680566.2023.2226348
Renyong Guo, Haijun Huang
In this paper, a dynamic entry pedestrian flow assignment problem is investigated. The problem concerns a scenario, i.e. a number of pedestrians enter a public place with multiple entrances and internal obstacles, and then get to their destinations in the public place. The problem aims at determining the access entrance, moving route, and destination position choice of pedestrians so as to minimize the total entry time of all pedestrians. A mesoscopic model is developed to formulate the dynamic entry process of pedestrians in the scenario and a heuristic algorithm is proposed to solve the dynamic entry pedestrian flow assignment problem. Moreover, a set of numerical investigations are provided to demonstrate the applications of the model and the effectiveness of the algorithm, especially to a case with a larger number of entry pedestrians.
{"title":"Modelling and solving dynamic entry pedestrian flow assignment problem","authors":"Renyong Guo, Haijun Huang","doi":"10.1080/21680566.2023.2226348","DOIUrl":"https://doi.org/10.1080/21680566.2023.2226348","url":null,"abstract":"In this paper, a dynamic entry pedestrian flow assignment problem is investigated. The problem concerns a scenario, i.e. a number of pedestrians enter a public place with multiple entrances and internal obstacles, and then get to their destinations in the public place. The problem aims at determining the access entrance, moving route, and destination position choice of pedestrians so as to minimize the total entry time of all pedestrians. A mesoscopic model is developed to formulate the dynamic entry process of pedestrians in the scenario and a heuristic algorithm is proposed to solve the dynamic entry pedestrian flow assignment problem. Moreover, a set of numerical investigations are provided to demonstrate the applications of the model and the effectiveness of the algorithm, especially to a case with a larger number of entry pedestrians.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47077815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-30DOI: 10.1080/21680566.2023.2226347
Nicolai A. Weinreich, D. B. van Diepen, Federico Chiariotti, C. Biscio
ABSTRACT The planning process for bike sharing systems is often complex, involving multiple stakeholders and several considerations: finding hotspots in the potential demand, and dimensioning the system, requires an intimate knowledge of urban mobility patterns and specific local features of the city. The significant costs associated with dynamic rebalancing of bike sharing systems, i.e. with moving bikes across the city to correct the demand imbalance and ensure that they are available where and when they are needed, make correct planning even more critical for the economic viability of the system. In this work, we consider urban environment data from multiple sources and different cities in Europe and the United States to design an automated planning pipeline to place stations in an area with no direct knowledge of the demand. The first step in the planning is to build models of activity patterns and correlate them with features of the urban environment such as land use and mass transit availability; these statistical models can then be used to expand an existing network or even create an entirely new one in a different city. A use case in New York City shows that our system can effectively plan a bike sharing system expansion, providing a valuable first step for the planning process and allowing system designers to identify gaps in existing systems and the locations of potential demand hotspots.
{"title":"Automatic bike sharing system planning from urban environment features","authors":"Nicolai A. Weinreich, D. B. van Diepen, Federico Chiariotti, C. Biscio","doi":"10.1080/21680566.2023.2226347","DOIUrl":"https://doi.org/10.1080/21680566.2023.2226347","url":null,"abstract":"ABSTRACT The planning process for bike sharing systems is often complex, involving multiple stakeholders and several considerations: finding hotspots in the potential demand, and dimensioning the system, requires an intimate knowledge of urban mobility patterns and specific local features of the city. The significant costs associated with dynamic rebalancing of bike sharing systems, i.e. with moving bikes across the city to correct the demand imbalance and ensure that they are available where and when they are needed, make correct planning even more critical for the economic viability of the system. In this work, we consider urban environment data from multiple sources and different cities in Europe and the United States to design an automated planning pipeline to place stations in an area with no direct knowledge of the demand. The first step in the planning is to build models of activity patterns and correlate them with features of the urban environment such as land use and mass transit availability; these statistical models can then be used to expand an existing network or even create an entirely new one in a different city. A use case in New York City shows that our system can effectively plan a bike sharing system expansion, providing a valuable first step for the planning process and allowing system designers to identify gaps in existing systems and the locations of potential demand hotspots.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44260960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-22DOI: 10.1080/21680566.2023.2226824
Enyi Chen, Q. Luo, Jingjing Chen, Yuxin He
The analysis of passenger travel choice behaviours under train delays has become a crucial topic in research on urban rail transit operation management. In this paper, we focus on analysing travel choices of affected regular passengers under train delays by utilizing the data collected through an automatic fare collection (AFC) system along with train delay log records. Along this line, we propose a data-driven four-stage framework for studying regular passengers’ responses under delays, consisting of data profiling, regular passenger screening and travel patterns extraction, affected regular passenger identification, and affected passenger behaviour prediction modelling. Using a real-world case of the Shenzhen Metro in China, we conduct extensive experiments for method validation and feature insights analysis. The proposed framework could provide a microscopic view of passenger travel behaviours under train delays for fine prediction and exhibit a possibility for multi-source heterogeneous data mining in passenger behaviour analysis and train delay-related tasks.
{"title":"Understanding passenger travel choice behaviours under train delays in urban rail transits: a data-driven approach","authors":"Enyi Chen, Q. Luo, Jingjing Chen, Yuxin He","doi":"10.1080/21680566.2023.2226824","DOIUrl":"https://doi.org/10.1080/21680566.2023.2226824","url":null,"abstract":"The analysis of passenger travel choice behaviours under train delays has become a crucial topic in research on urban rail transit operation management. In this paper, we focus on analysing travel choices of affected regular passengers under train delays by utilizing the data collected through an automatic fare collection (AFC) system along with train delay log records. Along this line, we propose a data-driven four-stage framework for studying regular passengers’ responses under delays, consisting of data profiling, regular passenger screening and travel patterns extraction, affected regular passenger identification, and affected passenger behaviour prediction modelling. Using a real-world case of the Shenzhen Metro in China, we conduct extensive experiments for method validation and feature insights analysis. The proposed framework could provide a microscopic view of passenger travel behaviours under train delays for fine prediction and exhibit a possibility for multi-source heterogeneous data mining in passenger behaviour analysis and train delay-related tasks.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48676472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-13DOI: 10.1080/21680566.2023.2223769
Fushata A. Mohammed, Mahyar Amirgholy
Coordinating the movement of Connected Automated Vehicles (CAVs) can significantly improve traffic operations at signal-free intersections. However, we show there is a tradeoff between the operational capacity and the battery loss of CAVs at intersections. This research aims to enhance the battery life of CAVs with the minimum impact on operational capacity. To this end, we develop a stochastic model for the battery-capacity loss of CAV platoons at signal-free intersections. We account for the stochasticity in traffic operations at intersections by considering a probability distribution for the operational error in synchronizing the arrival and departure of consecutive platoons in crossing directions. We then balance the tradeoff between the battery-capacity loss rate and intersection capacity by optimizing the platoon size, traffic speed, and marginal gap length at a macroscopic scale. The numerical results of the research show that adjusting the macro-level control variables can improve CAVs' battery life by 27.6% at the cost of a 3.5% reduction from the maximum capacity.
{"title":"Traffic operation for longer battery life of connected automated vehicles in signal-free networks","authors":"Fushata A. Mohammed, Mahyar Amirgholy","doi":"10.1080/21680566.2023.2223769","DOIUrl":"https://doi.org/10.1080/21680566.2023.2223769","url":null,"abstract":"Coordinating the movement of Connected Automated Vehicles (CAVs) can significantly improve traffic operations at signal-free intersections. However, we show there is a tradeoff between the operational capacity and the battery loss of CAVs at intersections. This research aims to enhance the battery life of CAVs with the minimum impact on operational capacity. To this end, we develop a stochastic model for the battery-capacity loss of CAV platoons at signal-free intersections. We account for the stochasticity in traffic operations at intersections by considering a probability distribution for the operational error in synchronizing the arrival and departure of consecutive platoons in crossing directions. We then balance the tradeoff between the battery-capacity loss rate and intersection capacity by optimizing the platoon size, traffic speed, and marginal gap length at a macroscopic scale. The numerical results of the research show that adjusting the macro-level control variables can improve CAVs' battery life by 27.6% at the cost of a 3.5% reduction from the maximum capacity.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46206868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-31DOI: 10.1080/21680566.2023.2215955
Xinshao Zhang, Zhaocheng He, Yiting Zhu, Linlin You
Transit Signal Priority (TSP) strategy gives public transit vehicles privileges to pass through the intersection without stopping. Most previous studies have adopted the compulsory TSP strategy that considers to maximize the utility of public transportation, which is likely to reduce the efficiency of social vehicles. In this paper, we propose an Adaptive Transit Signal Priority (ATSP) model that considers the efficiency of both buses and social vehicles. This model has the Single Request Adaptive Transit Signal Priority (SR-ATSP) module and the Multi-Request Adaptive Transit Signal Priority (MR-ATSP) module. First, the intersection network is divided into grids based on the Discrete Traffic State Encoding (DTSE) idea to obtain the spatial information of vehicles. Then, in the SR-ATSP module, the Dueling Double Deep Q-learning Network (D3QN) algorithm is introduced to determine whether to implement the TSP strategy or not, considering the goal of minimizing the total passenger waiting time of buses and social vehicles. Based on the SR-ATSP, the MR-ATSP module introduces some rules to tackle the conflict from multiple priority requests of different buses. Simulation experiments based on an intersection in Nansha District, Guangzhou City are conducted on SUMO software. The results show that the proposed ATSP model can realize the priority treatment for of buses while reducing the waiting time of social vehicles by . It has superior performance for reducing the waiting time of buses and social vehicles than other widely-used TSP models.
{"title":"DRL-based adaptive signal control for bus priority service under connected vehicle environment","authors":"Xinshao Zhang, Zhaocheng He, Yiting Zhu, Linlin You","doi":"10.1080/21680566.2023.2215955","DOIUrl":"https://doi.org/10.1080/21680566.2023.2215955","url":null,"abstract":"Transit Signal Priority (TSP) strategy gives public transit vehicles privileges to pass through the intersection without stopping. Most previous studies have adopted the compulsory TSP strategy that considers to maximize the utility of public transportation, which is likely to reduce the efficiency of social vehicles. In this paper, we propose an Adaptive Transit Signal Priority (ATSP) model that considers the efficiency of both buses and social vehicles. This model has the Single Request Adaptive Transit Signal Priority (SR-ATSP) module and the Multi-Request Adaptive Transit Signal Priority (MR-ATSP) module. First, the intersection network is divided into grids based on the Discrete Traffic State Encoding (DTSE) idea to obtain the spatial information of vehicles. Then, in the SR-ATSP module, the Dueling Double Deep Q-learning Network (D3QN) algorithm is introduced to determine whether to implement the TSP strategy or not, considering the goal of minimizing the total passenger waiting time of buses and social vehicles. Based on the SR-ATSP, the MR-ATSP module introduces some rules to tackle the conflict from multiple priority requests of different buses. Simulation experiments based on an intersection in Nansha District, Guangzhou City are conducted on SUMO software. The results show that the proposed ATSP model can realize the priority treatment for of buses while reducing the waiting time of social vehicles by . It has superior performance for reducing the waiting time of buses and social vehicles than other widely-used TSP models.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43321129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-27DOI: 10.1080/21680566.2023.2217704
Wenzhang Yang, Changyin Dong, Hao Wang
ABSTRACT This study proposed an on-ramp cooperative control strategy for connected and automated vehicles (CAVs) based on the virtual platoon method. First, the formation rules of the virtual platoon and merging conditions of the vehicles were introduced. Different control strategies were then arranged for different types of vehicle combinations in the virtual platoon. Merging speed control was proposed for vehicle combinations in different lanes. The simulation results showed that merging speed control effectively increases vehicle speed and reduces fuel consumption and average pollutant emissions. In the typical macroscopic simulation, the average speed of vehicles with merging speed control increased by 25%, while fuel consumption and average pollutant emissions decreased by 31.4% and 52%. A longer communication area, shorter desired gap headway, and smaller flow rate can lead to higher vehicle speed, lower fuel consumption and pollutant emissions. Fuel consumption and pollutant emissions are inversely proportional to the steady speed.
{"title":"A cooperative merging speed control strategy of CAVs based on virtual platoon in on-ramp merging system","authors":"Wenzhang Yang, Changyin Dong, Hao Wang","doi":"10.1080/21680566.2023.2217704","DOIUrl":"https://doi.org/10.1080/21680566.2023.2217704","url":null,"abstract":"ABSTRACT This study proposed an on-ramp cooperative control strategy for connected and automated vehicles (CAVs) based on the virtual platoon method. First, the formation rules of the virtual platoon and merging conditions of the vehicles were introduced. Different control strategies were then arranged for different types of vehicle combinations in the virtual platoon. Merging speed control was proposed for vehicle combinations in different lanes. The simulation results showed that merging speed control effectively increases vehicle speed and reduces fuel consumption and average pollutant emissions. In the typical macroscopic simulation, the average speed of vehicles with merging speed control increased by 25%, while fuel consumption and average pollutant emissions decreased by 31.4% and 52%. A longer communication area, shorter desired gap headway, and smaller flow rate can lead to higher vehicle speed, lower fuel consumption and pollutant emissions. Fuel consumption and pollutant emissions are inversely proportional to the steady speed.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43561471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-22DOI: 10.1080/21680566.2023.2215957
Xia Jiang, Jian Zhang, Dan Li
This paper proposes an eco-driving framework for electric connected vehicles (CVs) based on reinforcement learning (RL) to improve vehicle energy efficiency at signalized intersections. The vehicle agent is specified by integrating the model-based car-following policy, lane-changing policy, and RL policy, to ensure the safe operation of a CV. Subsequently, a Markov Decision Process (MDP) is formulated, which enables the vehicle to perform longitudinal control and lateral decisions, jointly optimizing the car-following and lane-changing behaviours of the CVs in the vicinity of intersections. Then, the hybrid action space is parameterized as a hierarchical structure and thereby trains the agents with two-dimensional motion patterns in a dynamic traffic environment. Finally, our proposed methods are evaluated in SUMO software from both a single-vehicle-based perspective and a flow-based perspective. The results show that our strategy can significantly reduce energy consumption by learning proper action schemes without any interruption of other human-driven vehicles (HDVs).
{"title":"Eco-driving at signalized intersections: a parameterized reinforcement learning approach","authors":"Xia Jiang, Jian Zhang, Dan Li","doi":"10.1080/21680566.2023.2215957","DOIUrl":"https://doi.org/10.1080/21680566.2023.2215957","url":null,"abstract":"This paper proposes an eco-driving framework for electric connected vehicles (CVs) based on reinforcement learning (RL) to improve vehicle energy efficiency at signalized intersections. The vehicle agent is specified by integrating the model-based car-following policy, lane-changing policy, and RL policy, to ensure the safe operation of a CV. Subsequently, a Markov Decision Process (MDP) is formulated, which enables the vehicle to perform longitudinal control and lateral decisions, jointly optimizing the car-following and lane-changing behaviours of the CVs in the vicinity of intersections. Then, the hybrid action space is parameterized as a hierarchical structure and thereby trains the agents with two-dimensional motion patterns in a dynamic traffic environment. Finally, our proposed methods are evaluated in SUMO software from both a single-vehicle-based perspective and a flow-based perspective. The results show that our strategy can significantly reduce energy consumption by learning proper action schemes without any interruption of other human-driven vehicles (HDVs).","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47969600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-17DOI: 10.1080/21680566.2023.2212324
Thomas Maxner, A. Ranjbari, Chase P. Dowling, Şeyma Güneş
Curbspace is a limited resource in urban areas. Delivery, ridehailing and passenger vehicles must compete for spaces at the curb. Cities are increasingly adjusting curb rules and allocating curb spaces for uses other than short-term paid parking, yet they lack the tools or data needed to make informed decisions. In this research, we analyse and quantify the impacts of different curb use allocations on curb performance through simulation. Three metrics are developed to evaluate the performance of the curb, covering productivity and accessibility of passengers and goods, and CO2 emissions. The metrics are calculated for each scenario across a range of input parameters (traffic volume, parking rate, vehicle dwell time, and street design speed) and compared to a baseline scenario. This work can inform policy decisions by providing municipalities tools to analyse various curb management strategies and choose the ones that produce results more in line with their policy goals.
{"title":"Simulation-based analysis of different curb space type allocations on curb performance","authors":"Thomas Maxner, A. Ranjbari, Chase P. Dowling, Şeyma Güneş","doi":"10.1080/21680566.2023.2212324","DOIUrl":"https://doi.org/10.1080/21680566.2023.2212324","url":null,"abstract":"Curbspace is a limited resource in urban areas. Delivery, ridehailing and passenger vehicles must compete for spaces at the curb. Cities are increasingly adjusting curb rules and allocating curb spaces for uses other than short-term paid parking, yet they lack the tools or data needed to make informed decisions. In this research, we analyse and quantify the impacts of different curb use allocations on curb performance through simulation. Three metrics are developed to evaluate the performance of the curb, covering productivity and accessibility of passengers and goods, and CO2 emissions. The metrics are calculated for each scenario across a range of input parameters (traffic volume, parking rate, vehicle dwell time, and street design speed) and compared to a baseline scenario. This work can inform policy decisions by providing municipalities tools to analyse various curb management strategies and choose the ones that produce results more in line with their policy goals.","PeriodicalId":48872,"journal":{"name":"Transportmetrica B-Transport Dynamics","volume":" ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44774229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：