Pub Date : 2025-09-02DOI: 10.1080/23249935.2024.2318621
Di Zeng , Ling Zheng , Xiantong Yang , Yinong Li
The application of deep reinforcement learning in driving policy learning for automated vehicles is limited by the difficulty of designing reward functions. Most existing inverse reinforcement learning (IRL) methods make a structure assumption on the reward function and omit the uncertainty of neural networks. In view of this, this paper proposes a novel deep Bayesian IRL method that addresses both the reward function designing and the uncertainty-measuring issues by learning an approximate posterior distribution over the reward function. Furthermore, we propose to train uncertainty-aware human-like driving policies by maximising the predicted reward and penalising its uncertainty. Finally, the proposed methods were validated in simulated highway driving scenarios. The results show that AVRL models uncertainty and learns reward functions significantly outperforming the existing IRL method applied in automated driving. It was also found that penalising the uncertainty of the reward function during policy training improves the success rate and human likeness of the learned policy.
{"title":"Uncertainty-aware human-like driving policy learning with deep Bayesian inverse reinforcement learning","authors":"Di Zeng , Ling Zheng , Xiantong Yang , Yinong Li","doi":"10.1080/23249935.2024.2318621","DOIUrl":"10.1080/23249935.2024.2318621","url":null,"abstract":"<div><div>The application of deep reinforcement learning in driving policy learning for automated vehicles is limited by the difficulty of designing reward functions. Most existing inverse reinforcement learning (IRL) methods make a structure assumption on the reward function and omit the uncertainty of neural networks. In view of this, this paper proposes a novel deep Bayesian IRL method that addresses both the reward function designing and the uncertainty-measuring issues by learning an approximate posterior distribution over the reward function. Furthermore, we propose to train uncertainty-aware human-like driving policies by maximising the predicted reward and penalising its uncertainty. Finally, the proposed methods were validated in simulated highway driving scenarios. The results show that AVRL models uncertainty and learns reward functions significantly outperforming the existing IRL method applied in automated driving. It was also found that penalising the uncertainty of the reward function during policy training improves the success rate and human likeness of the learned policy.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 3","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139772275","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 : 2025-09-02DOI: 10.1080/23249935.2023.2294267
Qian Zhu , Yun Wang , Pan Shang , Xiaoning Zhu
Balancing energy efficiency with high-quality service on urban rail lines with highly asymmetric passenger demand is a crucial yet challenging issue. This paper proposes an efficient asymmetric rolling stock reposition strategy to simultaneously optimize the train timetable, speed profiles and rolling stock circulation, given the passenger demand in the undersaturated direction and timetable in the oversaturated direction. By constructing space-time networks for passengers and rolling stocks, respectively, an integer linear programming model is formulated by considering the tradeoff between the passenger travel time and train energy cost. A rolling horizon scheme incorporating the Lagrangian relaxation decomposition technique is designed, which can be decomposed into two subproblems by relaxing the capacity constraints. The effectiveness of our proposed methodology is validated through numerical experiments on a test network and the Beijing Batong Line, demonstrating that the optimized train circulation plan significantly reduces energy consumption while incurring a minimal increase in travel time.
{"title":"Efficient asymmetric reposition strategy of rolling stock for urban rail transit systems","authors":"Qian Zhu , Yun Wang , Pan Shang , Xiaoning Zhu","doi":"10.1080/23249935.2023.2294267","DOIUrl":"10.1080/23249935.2023.2294267","url":null,"abstract":"<div><div>Balancing energy efficiency with high-quality service on urban rail lines with highly asymmetric passenger demand is a crucial yet challenging issue. This paper proposes an efficient asymmetric rolling stock reposition strategy to simultaneously optimize the train timetable, speed profiles and rolling stock circulation, given the passenger demand in the undersaturated direction and timetable in the oversaturated direction. By constructing space-time networks for passengers and rolling stocks, respectively, an integer linear programming model is formulated by considering the tradeoff between the passenger travel time and train energy cost. A rolling horizon scheme incorporating the Lagrangian relaxation decomposition technique is designed, which can be decomposed into two subproblems by relaxing the capacity constraints. The effectiveness of our proposed methodology is validated through numerical experiments on a test network and the Beijing Batong Line, demonstrating that the optimized train circulation plan significantly reduces energy consumption while incurring a minimal increase in travel time.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 3","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138820289","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 : 2025-09-02DOI: 10.1080/23249935.2024.2318618
Miaoqing Hu , W. Y. Szeto , Yue Wang
Feeder services, which provide travellers effective access from local areas to trunk-line systems, are essential, especially when the long-haul trunk routes are designed with large spacing between stations. Apart from the short-haul bus, the development of bike-sharing systems has led to a powerful supplementary feeder service. Most research on feeder services focuses on the separate design of bike and bus systems, but their joint design deserves further study. This research proposes a bi-level mixed-integer programming model to simultaneously design the locations of feeder buses and shared bike stations as well as the bus routes. A modified genetic algorithm that encapsulates the fixed-point iteration and Frank-Wolfe algorithms is developed to solve the model for large network applications. Numerical examples are given to compare the joint design with the separate design. The key factors that affect the design outcomes are investigated. The effects of joint design on operators and travellers are also discussed.
支线服务为旅客提供从当地到干线系统的有效通道，这一点至关重要，尤其是当长途干线的设计间距较大时。
{"title":"Cooperative design of feeder bus and bike-sharing systems","authors":"Miaoqing Hu , W. Y. Szeto , Yue Wang","doi":"10.1080/23249935.2024.2318618","DOIUrl":"10.1080/23249935.2024.2318618","url":null,"abstract":"<div><div>Feeder services, which provide travellers effective access from local areas to trunk-line systems, are essential, especially when the long-haul trunk routes are designed with large spacing between stations. Apart from the short-haul bus, the development of bike-sharing systems has led to a powerful supplementary feeder service. Most research on feeder services focuses on the separate design of bike and bus systems, but their joint design deserves further study. This research proposes a bi-level mixed-integer programming model to simultaneously design the locations of feeder buses and shared bike stations as well as the bus routes. A modified genetic algorithm that encapsulates the fixed-point iteration and Frank-Wolfe algorithms is developed to solve the model for large network applications. Numerical examples are given to compare the joint design with the separate design. The key factors that affect the design outcomes are investigated. The effects of joint design on operators and travellers are also discussed.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 3","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140003448","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 : 2025-09-02DOI: 10.1080/23249935.2023.2270759
Seung-oh Son , Kyeongju Kwon , Juneyoung Park , Mohamed Abdel-Aty
This study proposed an improved calibration method in the safety evaluation framework and analysed the safety effect of installing the open road tolling (ORT) system. Although the ORT system in South Korea has recently installed in many tollgate sections, it is impossible to collect statistically significant crash data. Therefore, the safety benefits were estimated and compared by (1) applying the general calibration way suggested in the Highway Safety Manual, (2) the recent calibration research from Florida and (3) the improved calibration method suggested in this study. In the result, safety improvement effect of ORT installation was 43% to 51%. Additionally, the calibration function using the quadratic model showed the best performance. This study is meaningful in that the safety effectiveness was estimated using the calibration method when the sample size was insufficient, and it utilises new functions to predict nonlinear relationships that are difficult to calibrate with simple linear relationships.
{"title":"Applying an improved calibration method in the safety evaluation framework for the open tolling system","authors":"Seung-oh Son , Kyeongju Kwon , Juneyoung Park , Mohamed Abdel-Aty","doi":"10.1080/23249935.2023.2270759","DOIUrl":"10.1080/23249935.2023.2270759","url":null,"abstract":"<div><div>This study proposed an improved calibration method in the safety evaluation framework and analysed the safety effect of installing the open road tolling (ORT) system. Although the ORT system in South Korea has recently installed in many tollgate sections, it is impossible to collect statistically significant crash data. Therefore, the safety benefits were estimated and compared by (1) applying the general calibration way suggested in the Highway Safety Manual, (2) the recent calibration research from Florida and (3) the improved calibration method suggested in this study. In the result, safety improvement effect of ORT installation was 43% to 51%. Additionally, the calibration function using the quadratic model showed the best performance. This study is meaningful in that the safety effectiveness was estimated using the calibration method when the sample size was insufficient, and it utilises new functions to predict nonlinear relationships that are difficult to calibrate with simple linear relationships.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 3","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135569995","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 : 2025-09-02DOI: 10.1080/23249935.2024.2302477
Xinmei Chen , Virginie Lurkin , Dian Wang , Qiyuan Peng , Siyu Tao
Motivated by a released official policy in China to promote the development of suburban rail within metropolitan areas, this paper investigates the suburban rail network design problem by integrating the physical network and the service network design, while considering a higher level of passenger satisfaction by assigning passengers to trains rather than to service routes widely adopted in previous works. The physical network design problem lies in determining the location of the suburban stations and suburban section tracks to be newly constructed, by considering the coordination of the existing urban rail network. The service network design problem aims to decide the newly operated service routes and the corresponding frequency and timetable of vehicles running on these service routes. We formulate the studied problem as a mixed integer linear programming (MILP) model, which minimises the weighted sum of the construction cost, operation costs, and generalised cost of passengers. Many practical requirements are considered to ensure the attractiveness of the computed solutions. A variable neighbourhood search-based (VNS-based) heuristic is designed to efficiently solve instances with different scales, including hypothetical instances and a practical-size real-world instance generated based on the Chongqing metropolitan in China.
{"title":"Integrated physical and service network design of suburban rail under the coordination of urban rail","authors":"Xinmei Chen , Virginie Lurkin , Dian Wang , Qiyuan Peng , Siyu Tao","doi":"10.1080/23249935.2024.2302477","DOIUrl":"10.1080/23249935.2024.2302477","url":null,"abstract":"<div><div>Motivated by a released official policy in China to promote the development of suburban rail within metropolitan areas, this paper investigates the suburban rail network design problem by integrating the physical network and the service network design, while considering a higher level of passenger satisfaction by assigning passengers to trains rather than to service routes widely adopted in previous works. The physical network design problem lies in determining the location of the suburban stations and suburban section tracks to be newly constructed, by considering the coordination of the existing urban rail network. The service network design problem aims to decide the newly operated service routes and the corresponding frequency and timetable of vehicles running on these service routes. We formulate the studied problem as a mixed integer linear programming (MILP) model, which minimises the weighted sum of the construction cost, operation costs, and generalised cost of passengers. Many practical requirements are considered to ensure the attractiveness of the computed solutions. A variable neighbourhood search-based (VNS-based) heuristic is designed to efficiently solve instances with different scales, including hypothetical instances and a practical-size real-world instance generated based on the Chongqing metropolitan in China.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 3","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139559667","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 : 2025-09-02DOI: 10.1080/23249935.2023.2267702
David Ellenberger , Michael Siebert
In Automatic Passenger Counting (APC), the demand for very low errors has been fueled by applications like revenue sharing, which amounts to massive annual sums. As a consequence, APC validation costs are increasing and this work presents a solution to increase the efficiency of initial or recurrent, e.g. yearly, validations. The new approach, the partitioned equivalence test, guarantees the same bounded, low user risk while reducing efforts in comparison to established (equivalence) test procedures. This involves a pre-classification step, which selects the more informative bits of data (e.g. footage). Different use cases are evaluated: from entirely manual to algorithmic, artificial intelligence assisted workflows. Already for manual counts, the new approach can be used as a drop-in replacement to reduce validation costs, while savings in algorithmic use cases demonstrated that cost halving is possible. Due to the user risk being controlled no additional technical requirements are introduced.
{"title":"Artificial intelligence in automatic passenger counting: cost-efficient validation using the partitioned equivalence test","authors":"David Ellenberger , Michael Siebert","doi":"10.1080/23249935.2023.2267702","DOIUrl":"10.1080/23249935.2023.2267702","url":null,"abstract":"<div><div>In Automatic Passenger Counting (APC), the demand for very low errors has been fueled by applications like revenue sharing, which amounts to massive annual sums. As a consequence, APC validation costs are increasing and this work presents a solution to increase the efficiency of initial or recurrent, e.g. yearly, validations. The new approach, the partitioned equivalence test, guarantees the same bounded, low user risk while reducing efforts in comparison to established (equivalence) test procedures. This involves a pre-classification step, which selects the more informative bits of data (e.g. footage). Different use cases are evaluated: from entirely manual to algorithmic, artificial intelligence assisted workflows. Already for manual counts, the new approach can be used as a drop-in replacement to reduce validation costs, while savings in algorithmic use cases demonstrated that cost halving is possible. Due to the user risk being controlled no additional technical requirements are introduced.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 3","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135883160","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 : 2025-09-02DOI: 10.1080/23249935.2023.2288636
Xiao (Luke) Wen , Chunxi Huang , Sisi Jian , Dengbo He
This study aims to quantify the impact of discretionary lane-changing (DLC) on following vehicles (FVs) in the target lane using real-world dataset. The Waymo Open Dataset is used to identify the differences between autonomous vehicles (AVs) DLC and human-driven vehicles (HDVs) DLC maneuvers and compare their impacts on the driving volatility. Then, a block maxima (BM) model is applied to estimate crash risks. Finally, multivariate adaptive regression splines (MARS) is adopted to model gap acceptance behaviors of AV and HDV. Compared to HDV DLC, AV DLC leads to lower speed and yaw rate volatility and smaller acceleration rates of FVs. Further, the BM model reveals that the crash risk in AV DLC events is half of that in HDV DLC events. Additionally, MARS show that AV and HDV accept different lead gap. These findings highlight the benefits of mixing AVs in traffic and guide the improvement of AV controllers.
{"title":"Analysis of discretionary lane-changing behaviours of autonomous vehicles based on real-world data","authors":"Xiao (Luke) Wen , Chunxi Huang , Sisi Jian , Dengbo He","doi":"10.1080/23249935.2023.2288636","DOIUrl":"10.1080/23249935.2023.2288636","url":null,"abstract":"<div><div>This study aims to quantify the impact of discretionary lane-changing (DLC) on following vehicles (FVs) in the target lane using real-world dataset. The Waymo Open Dataset is used to identify the differences between autonomous vehicles (AVs) DLC and human-driven vehicles (HDVs) DLC maneuvers and compare their impacts on the driving volatility. Then, a block maxima (BM) model is applied to estimate crash risks. Finally, multivariate adaptive regression splines (MARS) is adopted to model gap acceptance behaviors of AV and HDV. Compared to HDV DLC, AV DLC leads to lower speed and yaw rate volatility and smaller acceleration rates of FVs. Further, the BM model reveals that the crash risk in AV DLC events is half of that in HDV DLC events. Additionally, MARS show that AV and HDV accept different lead gap. These findings highlight the benefits of mixing AVs in traffic and guide the improvement of AV controllers.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 3","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138532522","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 : 2025-05-04DOI: 10.1080/23249935.2023.2253477
Jiabin Wu , Yifeng Lin , Weiwei Qi
Emergency vehicles encounter traffic accidents at intersections of the network frequently, which seriously threatens the lives of rescue teams and patients. To improve the driving safety and travel efficiency of emergency vehicles, this study proposes a new method of timing co-evolutionary path optimisation for emergency vehicles based on the safety evaluation of intersections in an uncertain environment. First, the associated benefit calculation of emergency priority for vehicles passing through the nodes and road sections is provided then. Second, a mathematical description of the emergency vehicle path optimisation model is proposed, and its primary optimisation objective is to minimise travel time. A secondary optimisation objective based on a flexible time window is proposed to optimise the risk coefficient of the rescue path. Finally, an improved ripple-spreading algorithm is designed to find the optimal path. The findings can help to provide auxiliary decision support for the path selection of emergency rescue actions.
{"title":"Timing co-evolutionary path optimisation method for emergency vehicles considering the safe passage","authors":"Jiabin Wu , Yifeng Lin , Weiwei Qi","doi":"10.1080/23249935.2023.2253477","DOIUrl":"10.1080/23249935.2023.2253477","url":null,"abstract":"<div><div>Emergency vehicles encounter traffic accidents at intersections of the network frequently, which seriously threatens the lives of rescue teams and patients. To improve the driving safety and travel efficiency of emergency vehicles, this study proposes a new method of timing co-evolutionary path optimisation for emergency vehicles based on the safety evaluation of intersections in an uncertain environment. First, the associated benefit calculation of emergency priority for vehicles passing through the nodes and road sections is provided then. Second, a mathematical description of the emergency vehicle path optimisation model is proposed, and its primary optimisation objective is to minimise travel time. A secondary optimisation objective based on a flexible time window is proposed to optimise the risk coefficient of the rescue path. Finally, an improved ripple-spreading algorithm is designed to find the optimal path. The findings can help to provide auxiliary decision support for the path selection of emergency rescue actions.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 2","pages":"Pages 1-33"},"PeriodicalIF":3.6,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46888455","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 : 2025-05-04DOI: 10.1080/23249935.2023.2266041
Yilang Hao , Zhibin Chen , Jiangang Jin , Xiaotong Sun
Semi-autonomous truck platooning, a futuristic and promising traveling mode of trucks on highways, has received extensive attention as autonomous driving gains more maturity. Under the semi-autonomous platooning mode, rather than requiring a human driver for each truck in the platoon, only one human driver is needed for the leading truck, and all following trucks can be controlled by autonomous driving and wireless communication technology. Therefore, in addition to saving energy, such a technology can help reduce labor costs by using fewer drivers to fulfill the same demand. Compared to traditional truck platooning, the schedules of drivers under semi-autonomous truck platooning may not be exactly the same as trucks, which are usually neglected in recent studies. Therefore, in this paper, we make the first attempt to develop a mathematical modeling framework to optimise the operation plan of drivers and trucks interdependently. To be mentioned, the truck fleet is equipped with the semi-autonomous platooning function and time windows. Specifically, the operation plan will dictate the number of drivers to be dispatched, and traveling routes and time schedules of drivers and trucks interdependently with the objective to minimise the total operation cost, including drivers' fixed dispatch cost, on-road labor cost, and energy consumption cost while fulfilling all delivery demands. To tackle the large-scale problem in a timely manner, a tailored Lagrangian Relaxation approach is proposed to solve the model. Numerical experiments are conducted to demonstrate the performance of the proposed modeling framework and validate the feasibility and efficiency of the proposed solution algorithm.
{"title":"Joint operation planning of drivers and trucks for semi-autonomous truck platooning","authors":"Yilang Hao , Zhibin Chen , Jiangang Jin , Xiaotong Sun","doi":"10.1080/23249935.2023.2266041","DOIUrl":"10.1080/23249935.2023.2266041","url":null,"abstract":"<div><div>Semi-autonomous truck platooning, a futuristic and promising traveling mode of trucks on highways, has received extensive attention as autonomous driving gains more maturity. Under the semi-autonomous platooning mode, rather than requiring a human driver for each truck in the platoon, only one human driver is needed for the leading truck, and all following trucks can be controlled by autonomous driving and wireless communication technology. Therefore, in addition to saving energy, such a technology can help reduce labor costs by using fewer drivers to fulfill the same demand. Compared to traditional truck platooning, the schedules of drivers under semi-autonomous truck platooning may not be exactly the same as trucks, which are usually neglected in recent studies. Therefore, in this paper, we make the first attempt to develop a mathematical modeling framework to optimise the operation plan of drivers and trucks interdependently. To be mentioned, the truck fleet is equipped with the semi-autonomous platooning function and time windows. Specifically, the operation plan will dictate the number of drivers to be dispatched, and traveling routes and time schedules of drivers and trucks interdependently with the objective to minimise the total operation cost, including drivers' fixed dispatch cost, on-road labor cost, and energy consumption cost while fulfilling all delivery demands. To tackle the large-scale problem in a timely manner, a tailored Lagrangian Relaxation approach is proposed to solve the model. Numerical experiments are conducted to demonstrate the performance of the proposed modeling framework and validate the feasibility and efficiency of the proposed solution algorithm.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 2","pages":"Pages 1-37"},"PeriodicalIF":3.6,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135141513","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}
Manoeuvring in the presence of emergency vehicles is still a major issue for vehicle autonomy systems. Most studies that address this topic are based on rule-based methods, which cannot cover all possible scenarios that can take place in autonomous traffic. Multi-Agent Proximal Policy Optimisation (MAPPO) has recently emerged as a powerful method for autonomous systems because it allows for training in thousands of different situations. In this study, we present an approach based on MAPPO to guarantee the safe and efficient manoeuvring of autonomous vehicles in the presence of an emergency vehicle. We introduce a risk metric that summarises the potential risk of collision in a single index. The proposed method generates cooperative policies allowing the emergency vehicle to go at $ 15 % $ higher average speed while maintaining high safety distances. Moreover, we conduct a comprehensive evaluation of our method in a wide range of scenarios, including assessing the trade-offs between traffic efficiency and safety, measuring the scalability of the approach with respect to the number of autonomous vehicles, analysing different distributions of mixed human and autonomous traffic, and examining the various levels of cooperation and competition among agents.
{"title":"Safe and efficient manoeuvring for emergency vehicles in autonomous traffic using multi-agent proximal policy optimisation","authors":"Leandro Parada , Eduardo Candela , Luis Marques , Panagiotis Angeloudis","doi":"10.1080/23249935.2023.2246586","DOIUrl":"10.1080/23249935.2023.2246586","url":null,"abstract":"<div><div>Manoeuvring in the presence of emergency vehicles is still a major issue for vehicle autonomy systems. Most studies that address this topic are based on rule-based methods, which cannot cover all possible scenarios that can take place in autonomous traffic. Multi-Agent Proximal Policy Optimisation (MAPPO) has recently emerged as a powerful method for autonomous systems because it allows for training in thousands of different situations. In this study, we present an approach based on MAPPO to guarantee the safe and efficient manoeuvring of autonomous vehicles in the presence of an emergency vehicle. We introduce a risk metric that summarises the potential risk of collision in a single index. The proposed method generates cooperative policies allowing the emergency vehicle to go at $ 15 % $ <span><math><mn>15</mn><mi>%</mi></math></span> higher average speed while maintaining high safety distances. Moreover, we conduct a comprehensive evaluation of our method in a wide range of scenarios, including assessing the trade-offs between traffic efficiency and safety, measuring the scalability of the approach with respect to the number of autonomous vehicles, analysing different distributions of mixed human and autonomous traffic, and examining the various levels of cooperation and competition among agents.</div></div>","PeriodicalId":48871,"journal":{"name":"Transportmetrica A-Transport Science","volume":"21 2","pages":"Pages 1-29"},"PeriodicalIF":3.6,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136392616","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}
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