IET Intelligent Transport Systems最新文献

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.

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.

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.

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

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.

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.

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.

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).

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.

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.

Yao et al. propose a fully sampled trajectory reconstruction method for traffic mixed with RVs, CVs and CAVs. Considering the minimum safety distance constr

With the development of automated vehicles, researches related to automated vehicle platoon (AVP) have received more and more attention. AVP is considered one of the effective means to alleviate traffic congestion and reduce vehicle energy consumption. This paper studies a three-layer method of avoiding obstacle vehicles in traffic by switching the formation for the automated heavy vehicle platoon. In the decision-making layer, a decision-making system based on the finite-state machine is established for formation switching. In the second layer, the lane-changing trajectory is optimized based on the quantic polynomial curve fitting for vehicles that need to change lanes. In terms of vehicle control layer, each vehicle has a longitudinal controller based on sliding mode control and a lateral controller based on model predictive control to track the planned trajectory to complete the target formation. Finally, the proposed method is simulated in MATLAB/TruckSim. The simulation results show that the proposed method could effectively avoid the obstacle vehicles by switching the formation and has a small average value of errors in speed tracking and trajectory tracking.

Adaptive cruise control (ACC) is the core building block of future full autonomous driving. Numerous recent research demonstrated that Autonomous Vehicles (AVs) adopting shorter headways generally increase road capacity and may relieve congestion at bottlenecks for moderate demand scenarios. However, with high demand scenarios, bottlenecks can still be activated causing capacity breakdown. Therefore, extra control measures as dynamic traffic control near bottlenecks is necessary. The challenge is harder on urban freeways with consecutive bottlenecks which affect each other. This paper aims to improve the performance of ACC systems in a high demand scenario. A multi-bottleneck dynamic headway control strategy based on deep reinforcement learning (DRL) that adapts headways to optimize traffic flow and minimize delay is proposed. The controller dynamically assigns an optimal headway for each controlled section, based on state measurement representing the current traffic conditions. The case study is a freeway stretch with three consecutive bottlenecks which is then extended to include eight bottlenecks. Three different RL agent configurations are presented and compared. It is quantitatively demonstrated that the proposed control strategy improves traffic and enhances the system delay by up to 22.30%, and 18.87% compared to shortest headway setting for the three-bottleneck and the eight-bottleneck networks, respectively.

Road traffic accidents are the leading causes of injuries and fatalities. Understanding the traffic accident occurrence pattern and its contributing factors are prerequisites for effective traffic safety management. The paper proposes a deep learning approach for traffic accident recognition and information extraction from online Chinese news to extract and organize traffic accidents automatically. The approach consists of three modules, including automated news collection, news classification, and traffic accident information extraction. The automated news collection module crawls news from online sources, cleans and organizes it into a general news database with different categories of news. The news classification module robustly recognizes the traffic accident news from all types of news by fusing the sentence-wise and context-wise semantic news information. The accident information extraction module extracts the key attributes of traffic accidents (e.g. causes, times, locations) from news text using the SoftLexicon-BiLSTM-CRF method. The proposed approach is validated by comparing it with state-of-the-art text mining methods using Chinese news data crawled online. The results show that the approach can achieve a high information extraction performance in terms of precision, recall, and F1-score. It improves the performance of the best benchmark model (BiLSTM-CRF) by 18.8% in precision and 12.08% in F1-score. In addition, the potential value of the automatically extracted accident data is illustrated from online news in complementing traditional authority accident data to drive more effective traffic safety management in practice.