An adaptive transit signal priority strategy is presented in this paper with the objective of passenger delay minimization at isolated intersections serving conflicting bus rapid transit (BRT) routes. The proposed passenger-based adaptive signal priority for BRT systems (PASPB) is designed to optimize both green times and phase sequences at the start of each cycle and for a prespecified decision horizon. Since a public transportation (PT) vehicle travel time model capable of estimating the dwell time at stops with multiple loading areas has not yet been developed, PT vehicle dwell time is modeled in this study by analyzing the cases of passenger service by single or double PT vehicles. The problem is formulated as a mixed-integer nonlinear program (MINLP) and at each execution, the optimization is conducted by genetic algorithm. The model is deployed to a real-field intersection with conflicting BRT routes under the SUMO microsimulation environment. The results show that PASPB outperforms the SYNCHRO optimal solution and phase insertion strategy regarding PT passenger delay. Besides, the sensitivity analysis proves that at high demand levels of the PT system or general traffic, PASPB presents the best performance in terms of general traffic, PT, and total passenger delay compared to other models.
{"title":"Passenger-based adaptive transit signal priority for BRT systems with multiple loading areas","authors":"Hamid Behbahani, Mohammad Poorjafari","doi":"10.1049/itr2.12488","DOIUrl":"10.1049/itr2.12488","url":null,"abstract":"<p>An adaptive transit signal priority strategy is presented in this paper with the objective of passenger delay minimization at isolated intersections serving conflicting bus rapid transit (BRT) routes. The proposed passenger-based adaptive signal priority for BRT systems (PASPB) is designed to optimize both green times and phase sequences at the start of each cycle and for a prespecified decision horizon. Since a public transportation (PT) vehicle travel time model capable of estimating the dwell time at stops with multiple loading areas has not yet been developed, PT vehicle dwell time is modeled in this study by analyzing the cases of passenger service by single or double PT vehicles. The problem is formulated as a mixed-integer nonlinear program (MINLP) and at each execution, the optimization is conducted by genetic algorithm. The model is deployed to a real-field intersection with conflicting BRT routes under the SUMO microsimulation environment. The results show that PASPB outperforms the SYNCHRO optimal solution and phase insertion strategy regarding PT passenger delay. Besides, the sensitivity analysis proves that at high demand levels of the PT system or general traffic, PASPB presents the best performance in terms of general traffic, PT, and total passenger delay compared to other models.</p>","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"18 6","pages":"1089-1108"},"PeriodicalIF":2.7,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/itr2.12488","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140115268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Electronic toll collection system (ETCS) devices on vehicles communicate wirelessly with road head devices at toll stations. ETCS is preferred in countries because it is more convenient and efficient than manual toll collection. However, the scattered and constant innovations in this sector require a bridge between worldwide ETCS usage and advancements and a single page to grasp this sector's developments to ensure further developments. Following a systematic review, this study examined ETCS worldwide and technology adaption considering the scopes, limitations, usages, and related technology of the ever-developing electronic toll collection system. Existing ETCS technologies have been investigated and synchronized with ingrowing tech disparity to overcome the research synchronization gap. The study also included a bibliometric assessment to identify the important areas of research, technologies most used, degree of knowledge generated, growth/trend of the researches, most well-known authors, keywords, countries, documents, source of publication, and so on considering time-to-time changes. The study provided bibliometric solutions to the gap of lack of synchronization of research worldwide and even ETCS implementation difference within a country, which complicated collaboration with the central system and linked organizations and made it difficult for users to adapt the system.
{"title":"Towards intelligent transportation system: A comprehensive review of electronic toll collection systems","authors":"Mahir Shahrier, Arif Hasnat, Jobaer Al-Mahmud, Armana Sabiha Huq, Sakib Ahmed, Md. Khorshadul Haque","doi":"10.1049/itr2.12500","DOIUrl":"10.1049/itr2.12500","url":null,"abstract":"<p>Electronic toll collection system (ETCS) devices on vehicles communicate wirelessly with road head devices at toll stations. ETCS is preferred in countries because it is more convenient and efficient than manual toll collection. However, the scattered and constant innovations in this sector require a bridge between worldwide ETCS usage and advancements and a single page to grasp this sector's developments to ensure further developments. Following a systematic review, this study examined ETCS worldwide and technology adaption considering the scopes, limitations, usages, and related technology of the ever-developing electronic toll collection system. Existing ETCS technologies have been investigated and synchronized with ingrowing tech disparity to overcome the research synchronization gap. The study also included a bibliometric assessment to identify the important areas of research, technologies most used, degree of knowledge generated, growth/trend of the researches, most well-known authors, keywords, countries, documents, source of publication, and so on considering time-to-time changes. The study provided bibliometric solutions to the gap of lack of synchronization of research worldwide and even ETCS implementation difference within a country, which complicated collaboration with the central system and linked organizations and made it difficult for users to adapt the system.</p>","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"18 6","pages":"965-983"},"PeriodicalIF":2.7,"publicationDate":"2024-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/itr2.12500","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140117471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to enhance the performance of safety and fuel economy of connected hybrid electric vehicles (CHEVs), a novel distributed hierarchical platoon control scheme of CHEVs is proposed. First, the non-linear dynamic model of CHEVs platooning is established to accurately depict the multi-process coupling characteristics of CHEVs. Then, a distributed hierarchical control framework for CHEVs platooning is proposed, which is consisted of a upper model predictive control (MPC) law and a lower energy management control law. The upper MPC control law is built to produce the desired accelerations of every vehicle in the platoon and the lower fuzzy-based energy management control law is constructed to ensure the engine maintain at the rang of optimum working point and the motor work with the high efficiency of CHEVs platooning. Finally, the results manifest that the effectiveness of proposed platoon control scheme for CHEVs.
{"title":"Fuel-efficient and safe distributed hierarchical control for connected hybrid electric vehicles platooning","authors":"Jinghua Guo, Jingyao Wang, Ban Wang","doi":"10.1049/itr2.12505","DOIUrl":"10.1049/itr2.12505","url":null,"abstract":"<p>In order to enhance the performance of safety and fuel economy of connected hybrid electric vehicles (CHEVs), a novel distributed hierarchical platoon control scheme of CHEVs is proposed. First, the non-linear dynamic model of CHEVs platooning is established to accurately depict the multi-process coupling characteristics of CHEVs. Then, a distributed hierarchical control framework for CHEVs platooning is proposed, which is consisted of a upper model predictive control (MPC) law and a lower energy management control law. The upper MPC control law is built to produce the desired accelerations of every vehicle in the platoon and the lower fuzzy-based energy management control law is constructed to ensure the engine maintain at the rang of optimum working point and the motor work with the high efficiency of CHEVs platooning. Finally, the results manifest that the effectiveness of proposed platoon control scheme for CHEVs.</p>","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"18 7","pages":"1227-1236"},"PeriodicalIF":2.3,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/itr2.12505","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140124499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohit Kumar Singh, Nicolette Formosa, Cheuk Ki Man, Craig Morton, Cansu Bahar Masera, Mohammed Quddus
Connected and automated vehicles (CAVs) are being developed and designed to operate on existing roads. Their safe and efficient operation during roadworks, where traffic management measures are often introduced, is crucial. Two alternative measures are commonly applied during roadworks on motorways: (i) closing one or multiple lanes (ii) narrowing one or all lanes. The former can cause delays and increased emissions, while the latter can pose safety risks. This study uses a VISSIM-based traffic microsimulation to compare the effectiveness of these two strategies on traffic efficiency and safety, considering various market penetration rates (MPR) of CAVs. The model was calibrated and validated with the data collected from M1 motorway in the United Kingdom. Results show that average delays per vehicle-kilometre-travelled decreased from 102.7 to 2.5 s (with lane closure) and 23.6 to 0.6 s (with narrow lanes) with 0% and 100% CAV MPR, respectively. Moreover, safety in narrow lanes improved by 4.8 times compared to 1.5 times improvement in lane closure with a 100% CAV MPR; indicating that narrow lanes would result in better safety performance. These findings could assist transport authorities in designing temporary traffic management measure that results in better CAV performance when navigating through roadworks.
{"title":"Assessing temporary traffic management measures on a motorway: Lane closures vs narrow lanes for connected and autonomous vehicles in roadworks","authors":"Mohit Kumar Singh, Nicolette Formosa, Cheuk Ki Man, Craig Morton, Cansu Bahar Masera, Mohammed Quddus","doi":"10.1049/itr2.12503","DOIUrl":"10.1049/itr2.12503","url":null,"abstract":"<p>Connected and automated vehicles (CAVs) are being developed and designed to operate on existing roads. Their safe and efficient operation during roadworks, where traffic management measures are often introduced, is crucial. Two alternative measures are commonly applied during roadworks on motorways: (i) closing one or multiple lanes (ii) narrowing one or all lanes. The former can cause delays and increased emissions, while the latter can pose safety risks. This study uses a VISSIM-based traffic microsimulation to compare the effectiveness of these two strategies on traffic efficiency and safety, considering various market penetration rates (MPR) of CAVs. The model was calibrated and validated with the data collected from M1 motorway in the United Kingdom. Results show that average delays per vehicle-kilometre-travelled decreased from 102.7 to 2.5 s (with lane closure) and 23.6 to 0.6 s (with narrow lanes) with 0% and 100% CAV MPR, respectively. Moreover, safety in narrow lanes improved by 4.8 times compared to 1.5 times improvement in lane closure with a 100% CAV MPR; indicating that narrow lanes would result in better safety performance. These findings could assist transport authorities in designing temporary traffic management measure that results in better CAV performance when navigating through roadworks.</p>","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"18 7","pages":"1210-1226"},"PeriodicalIF":2.3,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/itr2.12503","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140072086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p>Electro-Mobility (e-Mobility) represents the concept of utilizing electric power-train techniques, in-vehicle information, communication techniques and related equipment to enable wise electric propulsion of vehicles and fleets. It has been recognized as not only a major innovative field of innovation in the coming decades but also a dominant technology for urban mobility in the future. Motivated by the need to improve fuel efficiency, meet emission requirements and satisfy market demands for lower operational costs, a large number of concrete plans for e-Mobility have been conducted and great efforts have been made in many countries.</p><p>However, the broad adoption of electric vehicles (including car and bus) by the public is still a challenging task today, due to high prices of the batteries and their long charging duration. More importantly, the seamless incorporation of e-Mobility into urban transport systems at this time still needs a series of advanced measures to ensure secure and safe operations of vehicles, rational developments of relevant standards, wise planning of urban infrastructure etc. Furthermore, it is also necessary to further analyze the potential effects of e-Mobility on individual daily mobility behavior, automotive supply chain and the long-term environmental protection of this technology accurately in quantification details. This covers a broad interdisciplinary area of research and development towards the success of the next generation of mobility solutions. The current Special Issue is focused on research ideas, articles and experimental studies related to “Electro-Mobility for Urban Traffic and Transportation” for Modeling, simulation, analyzing and forecasting for e-Mobility, and the various aspects of Electro-Mobility in related applications.</p><p>In this Special Issue, 13 papers were submitted with five papers accepted; overall the submissions were of high quality, which marks the success of this Special Issue.</p><p>The five papers that were finally accepted can be divided into four categories, namely, social investigation, battery power, on-board information and scheduling control. The first kind of paper conducts a social survey. Based on the analysis of the survey results, it understands the public's willingness to use electric vehicles and provides some constructive suggestions. This category includes Bosehans et al. The second type of paper provides a direct solution for the stability of energy power of electric vehicles by proposing a new model of battery detection and dispatching. This paper is by Zhang et al. The third kind of paper establishes a new model for the problem of vehicular information transmission and provides users with a scheme of active decision-making. This category includes a paper by Kyung et al. The fourth type of paper provides solutions for optimizing the allocation of EV related resources (parking lots, charging stations, roads etc.) by proposing a new scheduling control model. T
{"title":"Guest Editorial: Electro-mobility for urban traffic and transportation","authors":"Dalin Zhang, Sabah Mohammed, Alessandro Calvi","doi":"10.1049/itr2.12499","DOIUrl":"10.1049/itr2.12499","url":null,"abstract":"<p>Electro-Mobility (e-Mobility) represents the concept of utilizing electric power-train techniques, in-vehicle information, communication techniques and related equipment to enable wise electric propulsion of vehicles and fleets. It has been recognized as not only a major innovative field of innovation in the coming decades but also a dominant technology for urban mobility in the future. Motivated by the need to improve fuel efficiency, meet emission requirements and satisfy market demands for lower operational costs, a large number of concrete plans for e-Mobility have been conducted and great efforts have been made in many countries.</p><p>However, the broad adoption of electric vehicles (including car and bus) by the public is still a challenging task today, due to high prices of the batteries and their long charging duration. More importantly, the seamless incorporation of e-Mobility into urban transport systems at this time still needs a series of advanced measures to ensure secure and safe operations of vehicles, rational developments of relevant standards, wise planning of urban infrastructure etc. Furthermore, it is also necessary to further analyze the potential effects of e-Mobility on individual daily mobility behavior, automotive supply chain and the long-term environmental protection of this technology accurately in quantification details. This covers a broad interdisciplinary area of research and development towards the success of the next generation of mobility solutions. The current Special Issue is focused on research ideas, articles and experimental studies related to “Electro-Mobility for Urban Traffic and Transportation” for Modeling, simulation, analyzing and forecasting for e-Mobility, and the various aspects of Electro-Mobility in related applications.</p><p>In this Special Issue, 13 papers were submitted with five papers accepted; overall the submissions were of high quality, which marks the success of this Special Issue.</p><p>The five papers that were finally accepted can be divided into four categories, namely, social investigation, battery power, on-board information and scheduling control. The first kind of paper conducts a social survey. Based on the analysis of the survey results, it understands the public's willingness to use electric vehicles and provides some constructive suggestions. This category includes Bosehans et al. The second type of paper provides a direct solution for the stability of energy power of electric vehicles by proposing a new model of battery detection and dispatching. This paper is by Zhang et al. The third kind of paper establishes a new model for the problem of vehicular information transmission and provides users with a scheme of active decision-making. This category includes a paper by Kyung et al. The fourth type of paper provides solutions for optimizing the allocation of EV related resources (parking lots, charging stations, roads etc.) by proposing a new scheduling control model. T","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"18 4","pages":"555-557"},"PeriodicalIF":2.7,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/itr2.12499","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140072255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sheraz Aslam, Michalis P. Michaelides, Herodotos Herodotou
Marine container terminals (MCTs) play a crucial role in intelligent maritime transportation (IMT) systems. Since the number of containers handled by MCTs has been increasing over the years, there is a need for developing effective and efficient approaches to enhance the productivity of IMT systems. The berth allocation problem (BAP) and the quay crane allocation problem (QCAP) are two well-known optimization problems in seaside operations of MCTs. The primary aim is to minimize the vessel service cost and maximize the performance of MCTs by optimally allocating berths and quay cranes to arriving vessels subject to practical constraints. This study presents an in-depth review of computational intelligence (CI) approaches developed to enhance the performance of MCTs. First, an introduction to MCTs and their key operations is presented, primarily focusing on seaside operations. A detailed overview of recent CI methods and solutions developed for the BAP is presented, considering various berthing layouts. Subsequently, a review of solutions related to the QCAP is presented. The datasets used in the current literature are also discussed, enabling future researchers to identify appropriate datasets to use in their work. Eventually, a detailed discussion is presented to highlight key opportunities along with foreseeable future challenges in the area.
{"title":"A survey on computational intelligence approaches for intelligent marine terminal operations","authors":"Sheraz Aslam, Michalis P. Michaelides, Herodotos Herodotou","doi":"10.1049/itr2.12469","DOIUrl":"10.1049/itr2.12469","url":null,"abstract":"<p>Marine container terminals (MCTs) play a crucial role in intelligent maritime transportation (IMT) systems. Since the number of containers handled by MCTs has been increasing over the years, there is a need for developing effective and efficient approaches to enhance the productivity of IMT systems. The berth allocation problem (BAP) and the quay crane allocation problem (QCAP) are two well-known optimization problems in seaside operations of MCTs. The primary aim is to minimize the vessel service cost and maximize the performance of MCTs by optimally allocating berths and quay cranes to arriving vessels subject to practical constraints. This study presents an in-depth review of computational intelligence (CI) approaches developed to enhance the performance of MCTs. First, an introduction to MCTs and their key operations is presented, primarily focusing on seaside operations. A detailed overview of recent CI methods and solutions developed for the BAP is presented, considering various berthing layouts. Subsequently, a review of solutions related to the QCAP is presented. The datasets used in the current literature are also discussed, enabling future researchers to identify appropriate datasets to use in their work. Eventually, a detailed discussion is presented to highlight key opportunities along with foreseeable future challenges in the area.</p>","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"18 5","pages":"755-793"},"PeriodicalIF":2.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/itr2.12469","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140072165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid development of vehicle-to-everything (V2X) communication technologies significantly promotes the revolution of intelligent transportation systems. V2X communication is expected to play a critical role in enhancing the safety and efficiency of connected and automated vehicles (CAVs), especially for mixed traffic scenarios. Additionally, the computational and storage capabilities of roadside units (RSUs) will be harnessed to effectively enhance the motion planning and control performance of CAVs within the constraints of limited on-board computational resources. Thus, a V2X assisted co-design of motion planning and control algorithm for CAVs to improve their situational awareness and computational efficiency is proposed. Under this architecture, a pre-planning algorithm is proposed first to utilize the computational and storage capabilities of RSUs and generate feasible trajectories for different driving tasks. By analysing the relationship between driving risk index and motion planning performance, an online-planning algorithm is derived to modify the pre-planned trajectories in real-time with static or dynamic obstacles. Furthermore, the lateral and longitudinal control of the vehicle using the Frenet coordinate system is decoupled. The lateral control employs an offline linear quadratic regulator (LQR) from RSUs to control the steering angle of the vehicle. The longitudinal control employs a dual-loop PID to control the throttle opening of the vehicle. The performance of the proposed framework is evaluated and demonstrated by a Carsim-Prescan simulation study in different mixed traffic scenarios. Compared with conventional methods, the proposed method improves the computational efficiency by 23% and reduces the collision rate by 13%.
{"title":"V2X assisted co-design of motion planning and control for connected automated vehicle","authors":"Jiahang Li, Cailian Chen, Bo Yang","doi":"10.1049/itr2.12501","DOIUrl":"https://doi.org/10.1049/itr2.12501","url":null,"abstract":"The rapid development of vehicle-to-everything (V2X) communication technologies significantly promotes the revolution of intelligent transportation systems. V2X communication is expected to play a critical role in enhancing the safety and efficiency of connected and automated vehicles (CAVs), especially for mixed traffic scenarios. Additionally, the computational and storage capabilities of roadside units (RSUs) will be harnessed to effectively enhance the motion planning and control performance of CAVs within the constraints of limited on-board computational resources. Thus, a V2X assisted co-design of motion planning and control algorithm for CAVs to improve their situational awareness and computational efficiency is proposed. Under this architecture, a pre-planning algorithm is proposed first to utilize the computational and storage capabilities of RSUs and generate feasible trajectories for different driving tasks. By analysing the relationship between driving risk index and motion planning performance, an online-planning algorithm is derived to modify the pre-planned trajectories in real-time with static or dynamic obstacles. Furthermore, the lateral and longitudinal control of the vehicle using the Frenet coordinate system is decoupled. The lateral control employs an offline linear quadratic regulator (LQR) from RSUs to control the steering angle of the vehicle. The longitudinal control employs a dual-loop PID to control the throttle opening of the vehicle. The performance of the proposed framework is evaluated and demonstrated by a Carsim-Prescan simulation study in different mixed traffic scenarios. Compared with conventional methods, the proposed method improves the computational efficiency by 23% and reduces the collision rate by 13%.","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"67 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140071892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The ability to predict the trajectory of an autonomous vehicle accurately is crucial for safe and efficient navigation. However, predicting diverse and multimodal futures can be challenging. Recent approaches such as attention and graph neural networks have achieved state-of-the-art performance by considering agent interactions and map contexts. This study focused on multi-agent prediction using an agent-centric approach with transformers. This enables parallel computation and a comprehensive understanding of the environment. Two main features are introduced: an adaptive receptive field (ARF) that captures the relevant surroundings for each agent, and perception encoding, which serves as spatial context embeddings. The ARF adapts to the agent's velocity and rotation, focusing attention ahead at high speeds or to the sides when it is slower. Perception encoding divides agents or lanes into levels and encodes the information of each level. This approach enables the efficient encoding of complex spatial relationships. The proposed method combines these advances with transformer modelling for multi-agent trajectory prediction while ensuring real-time prediction capabilities. The approach is evaluated on the Argoverse benchmark and better performance than the state-of-the-art baseline is achieved. By addressing challenges such as multimodal outputs and robustness, the study enhances the safety and efficiency of autonomous driving systems by more accurately predicting trajectories.
{"title":"Multi-agent trajectory prediction with adaptive perception-guided transformers","authors":"Ngan Linh Nguyen, Myungsik Yoo","doi":"10.1049/itr2.12502","DOIUrl":"10.1049/itr2.12502","url":null,"abstract":"<p>The ability to predict the trajectory of an autonomous vehicle accurately is crucial for safe and efficient navigation. However, predicting diverse and multimodal futures can be challenging. Recent approaches such as attention and graph neural networks have achieved state-of-the-art performance by considering agent interactions and map contexts. This study focused on multi-agent prediction using an agent-centric approach with transformers. This enables parallel computation and a comprehensive understanding of the environment. Two main features are introduced: an adaptive receptive field (ARF) that captures the relevant surroundings for each agent, and perception encoding, which serves as spatial context embeddings. The ARF adapts to the agent's velocity and rotation, focusing attention ahead at high speeds or to the sides when it is slower. Perception encoding divides agents or lanes into levels and encodes the information of each level. This approach enables the efficient encoding of complex spatial relationships. The proposed method combines these advances with transformer modelling for multi-agent trajectory prediction while ensuring real-time prediction capabilities. The approach is evaluated on the Argoverse benchmark and better performance than the state-of-the-art baseline is achieved. By addressing challenges such as multimodal outputs and robustness, the study enhances the safety and efficiency of autonomous driving systems by more accurately predicting trajectories.</p>","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"18 7","pages":"1196-1209"},"PeriodicalIF":2.3,"publicationDate":"2024-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/itr2.12502","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140037701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p>Connected and automated vehicle (CAV) technology has undergone significant development in the last decades. The traffic mixed with vehicles of various automation and communication levels will become the main body of the future transportation system, which makes the traditional theories of transportation research face great challenges. Such ongoing and forthcoming challenges make traffic mixed with CAVs a priority for research with interests across the spectrum of governmental agencies and industries.</p><p>Although a number of studies have been dedicated to the driving behaviours of vehicles with different intelligence and networking technologies, the following questions regarding mixed traffic are still open: (1) How do various types of vehicles operate in the heterogeneous traffic flow? (2) How do they interact with each other? (3) What is the evolution mechanism of the mixed traffic? (4) How to improve the efficiency of mixed traffic by optimizing vehicle trajectory and providing reasonable coordinated traffic control methods? The current special issue is focused on research ideas, articles and experimental studies related to modelling, operation and management of traffic mixed with CAVs, regular vehicles (RVs), automated vehicles (AVs) and connected vehicles (CVs).</p><p>In this special issue, we have received eight papers, all of which underwent peer review. Mixed traffic is investigated from three perspectives, namely, driving behaviours modelling, driving behaviours optimization, and traffic flow modelling. The papers laying in the first category exhibit novelties in driving behaviours analysis and simulation. The papers in this category are by Jami et al. and Yao et al. The second category of papers offers solutions to driving behaviour optimization by means of coordinate induction and traffic control. These papers are by Wang et al. and Huang et al. The last category proposes new methods concerning traffic state identification and traffic flow prediction. These papers are by Qi et al., Yang et al., Qi et al. and Guo et al. A brief presentation of each of the papers in this special issue follows.</p><p>Jami et al. present a simulation platform for a hybrid transportation system that includes both human-driven and automated vehicles. They decompose the human driving task and offer a modular approach to simulate a large-scale traffic scenario, allowing for a thorough investigation of automated and active safety systems. A large driving dataset is analysed to extract expressive parameters that would best describe different driving characteristics. Then a similarly dense traffic scenario within the simulator is recreated, and a thorough analysis of various human-specific and system-specific factors is conducted by examining their effects on traffic network performance and safety.</p><p>Yao et al. propose a fully sampled trajectory reconstruction method for traffic mixed with RVs, CVs and CAVs. Considering the minimum safety distance constr
{"title":"Guest Editorial: Modelling, operation and management of traffic mixed with connected and automated vehicles","authors":"Fang Zong, Renxin Zhong, Wei Ma, Dujuan Yang, Ziyuan Pu, Ngoduy Dong, Zhengbing He","doi":"10.1049/itr2.12496","DOIUrl":"10.1049/itr2.12496","url":null,"abstract":"<p>Connected and automated vehicle (CAV) technology has undergone significant development in the last decades. The traffic mixed with vehicles of various automation and communication levels will become the main body of the future transportation system, which makes the traditional theories of transportation research face great challenges. Such ongoing and forthcoming challenges make traffic mixed with CAVs a priority for research with interests across the spectrum of governmental agencies and industries.</p><p>Although a number of studies have been dedicated to the driving behaviours of vehicles with different intelligence and networking technologies, the following questions regarding mixed traffic are still open: (1) How do various types of vehicles operate in the heterogeneous traffic flow? (2) How do they interact with each other? (3) What is the evolution mechanism of the mixed traffic? (4) How to improve the efficiency of mixed traffic by optimizing vehicle trajectory and providing reasonable coordinated traffic control methods? The current special issue is focused on research ideas, articles and experimental studies related to modelling, operation and management of traffic mixed with CAVs, regular vehicles (RVs), automated vehicles (AVs) and connected vehicles (CVs).</p><p>In this special issue, we have received eight papers, all of which underwent peer review. Mixed traffic is investigated from three perspectives, namely, driving behaviours modelling, driving behaviours optimization, and traffic flow modelling. The papers laying in the first category exhibit novelties in driving behaviours analysis and simulation. The papers in this category are by Jami et al. and Yao et al. The second category of papers offers solutions to driving behaviour optimization by means of coordinate induction and traffic control. These papers are by Wang et al. and Huang et al. The last category proposes new methods concerning traffic state identification and traffic flow prediction. These papers are by Qi et al., Yang et al., Qi et al. and Guo et al. A brief presentation of each of the papers in this special issue follows.</p><p>Jami et al. present a simulation platform for a hybrid transportation system that includes both human-driven and automated vehicles. They decompose the human driving task and offer a modular approach to simulate a large-scale traffic scenario, allowing for a thorough investigation of automated and active safety systems. A large driving dataset is analysed to extract expressive parameters that would best describe different driving characteristics. Then a similarly dense traffic scenario within the simulator is recreated, and a thorough analysis of various human-specific and system-specific factors is conducted by examining their effects on traffic network performance and safety.</p><p>Yao et al. propose a fully sampled trajectory reconstruction method for traffic mixed with RVs, CVs and CAVs. Considering the minimum safety distance constr","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"18 3","pages":"433-435"},"PeriodicalIF":2.7,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/itr2.12496","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140005680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Haitao Li, Tao Peng, Ningguo Qiao, Zhiwei Guan, Xinyun Feng, Peng Guo, Tingting Duan, Jinfeng Gong
With the rapid advancement of highway construction, the maintenance of highway infrastructure has become particularly vital. During highway maintenance, the effective detection of tiny road surface cracks helps to extend the lifespan of roads and enhance traffic efficiency and safety. To elevate the performance of existing road detection models, the CrackTinyNet (CrTNet) algorithm is specifically proposed for detecting tiny road surface cracks. This algorithm utilizes the novel BiFormer general visual transformer, designed expressly for tiny objects, and optimizes the loss function to a normalized Wasserstein distance loss function. It replaces traditional downsampling with Space-to-Depth Conv to prevent the excessive loss of tiny object information in the network structure. To highlight the model's advantage in detecting tiny road cracks, ablation experiments and comparison trials were conducted with mainstream deep learning models for crack detection. The results of the ablation experiments show that, compared to the baseline, CrTNet improved the Mean Average Precision (MAP) by 0.22. When compared to other network models suitable for road detection, these results exhibited an improvement of over 8.9%. In conclusion, the CrTNet proposed in this study enables a more accurate detection of tiny road cracks, playing a significant role in the advancement of intelligent traffic management.
{"title":"CrackTinyNet: A novel deep learning model specifically designed for superior performance in tiny road surface crack detection","authors":"Haitao Li, Tao Peng, Ningguo Qiao, Zhiwei Guan, Xinyun Feng, Peng Guo, Tingting Duan, Jinfeng Gong","doi":"10.1049/itr2.12497","DOIUrl":"https://doi.org/10.1049/itr2.12497","url":null,"abstract":"With the rapid advancement of highway construction, the maintenance of highway infrastructure has become particularly vital. During highway maintenance, the effective detection of tiny road surface cracks helps to extend the lifespan of roads and enhance traffic efficiency and safety. To elevate the performance of existing road detection models, the CrackTinyNet (CrTNet) algorithm is specifically proposed for detecting tiny road surface cracks. This algorithm utilizes the novel BiFormer general visual transformer, designed expressly for tiny objects, and optimizes the loss function to a normalized Wasserstein distance loss function. It replaces traditional downsampling with Space-to-Depth Conv to prevent the excessive loss of tiny object information in the network structure. To highlight the model's advantage in detecting tiny road cracks, ablation experiments and comparison trials were conducted with mainstream deep learning models for crack detection. The results of the ablation experiments show that, compared to the baseline, CrTNet improved the Mean Average Precision (MAP) by 0.22. When compared to other network models suitable for road detection, these results exhibited an improvement of over 8.9%. In conclusion, the CrTNet proposed in this study enables a more accurate detection of tiny road cracks, playing a significant role in the advancement of intelligent traffic management.","PeriodicalId":50381,"journal":{"name":"IET Intelligent Transport Systems","volume":"34 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140005547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}