Communications in Transportation Research最新文献

One of the core problems in the strategic planning of railway operations revolves around developing an optimal line plan. The line plan optimisation problem aims to build a workable line system that achieves specific objectives. Many models presented in existing literature typically focus on either maximising direct traveller numbers or minimising costs. In contrast, this paper introduces a model with diverse objectives for addressing line plan optimisation problems, allowing for variations in stopping patterns across different lines. Our model examines how setting different objectives can result in different line plan designs. This will be valuable for railway operators, offering diverse perspectives when selecting the most suitable design, particularly in the context of new railway service development, such as the introduction of a high-speed train. A case study of future semi high-speed rail in Indonesia is presented to test the model.

Vehicle trajectory data have become essential for many research fields, such as traffic flow, traffic safety, and automated driving. To make trajectory data useable for researchers, an overview of the included road section and traffic situation as well as a description of the data processing methodology is necessary. In this paper, we present a trajectory dataset from a German highway with two lanes per direction, an off-ramp and congested traffic in one direction, and an on-ramp in the other direction. The dataset contains 8,648 trajectories and covers 87 ​min and an ∼1,200 ​m long section of the road. The trajectories were extracted from drone videos using a posttrained YOLOv5 object detection model and projected onto the road surface via three-dimensional (3D) camera calibration. The postprocessing methodology can compensate for most false detections and yield accurate speeds and accelerations. The trajectory data are also compared with induction loop data and vehicle-based smartphone sensor data to evaluate the plausibility and quality of the trajectory data. The deviations of the speeds and accelerations are estimated at 0.45 ​m/s and 0.3 ​m/s², respectively. We also present some applications of the data, including traffic flow analysis and accident risk analysis.

Nowadays, electric vehicles (EVs) are increasingly equipped with advanced onboard devices capable of collecting and recording real-time charging data. The analysis of such data from a large-scale EV fleet plays a crucial role in supporting decision-making processes, particularly in the deployment of charging infrastructure and the formulation of EV-focused policies. Nevertheless, the challenges of collecting these data are significant, primarily due to privacy concerns and the high costs associated with data access. In response, this study introduces an innovative methodology for generating large-scale and diverse EV charging data, mirroring real-world patterns for cost-efficient and privacy-compliant use. Specifically, this approach combines Gibbs sampling and conditional density networks and was trained and validated using a real-world dataset consisting of approximately 1.65 million charging events from 3,777 battery EVs (BEVs) in Shanghai over a year. Results illustrate that the proposed model can effectively capture the underlying distribution of the original charging data, enabling the generation of synthetic samples that closely resemble real-world charging events. The approach is readily employed for data imputation and augmentation, and it can also help simulate future charging distributions by conditional generation based on anticipated development premises.

As urbanization and high-rise living increase, frequent delivery of goods in the building to higher floors from the ground level is becoming a pressing issue. We introduce a drone-based vertical delivery system aimed at enhancing the efficiency of high-rise building logistics. The potential of the proposed system in reducing delivery time and energy consumption compared to conventional elevator-based delivery is analyzed. By assessing the requisite number of drones, their operating frequencies, and identifying scenarios in which drones can surpass conventional methods, the advantages using drone delivery systems are highlighted. The results indicate that drone delivery is not only viable but also advantageous to meet certain demand levels, offering a promising alternative to elevator-based deliveries.

Academic papers are the cornerstone of knowledge dissemination and crucial for researchers’ career development. This is particularly true for rapidly evolving research domains such as transportation, as evidenced by the surge of journals and papers in the past decade. While abundant literature offers guidance on successful publication strategies, insights into the reasons for rejection are rare. This study fills in this gap by examining why papers are rejected in the area of transportation. We present concrete evidence based on data from over 5,000 rejected transport papers. Quantitative analyses are conducted to reveal the impacts of similarity rate, duplication submission rate, and topic on desk rejections. Additionally, we shed light on the distinct focus reviewers have when serving different journals. We hope the results could equip transport researchers with a deeper comprehension of publication criteria and a better awareness of common but avoidable mistakes.

This paper presents a spatially formulated cooperative dynamic mandatory connected automated vehicle (CAV) lane-changing and car-following approach on curved highways with the assistance of vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communication. This work proposes mandatory lane-changing control in a spatial domain to accomplish car-following and lane-changing efficiency in a systematic manner. This control technique initially creates a virtual CAV car-following lane by assigning CAVs sequential numbers based on their spatial position. On this basis, a multi-objective model predictive control (MPC) strategy in the spatial domain is designed to optimize the trajectories in a rolling horizon fashion in order to maintain the inter-vehicle spacing and speed difference while simultaneously satisfying collision avoidances, traffic regulations, and vehicle kinematics constraints. Multi-scenario numerical simulations are conducted to validate the control efficacy of our technique.

Despite significant progress in autonomous vehicles (AVs), the development of driving policies that ensure both the safety of AVs and traffic flow efficiency has not yet been fully explored. In this paper, we propose an enhanced human-in-the-loop reinforcement learning method, termed the Human as AI mentor-based deep reinforcement learning (HAIM-DRL) framework, which facilitates safe and efficient autonomous driving in mixed traffic platoon. Drawing inspiration from the human learning process, we first introduce an innovative learning paradigm that effectively injects human intelligence into AI, termed Human as AI mentor (HAIM). In this paradigm, the human expert serves as a mentor to the AI agent. While allowing the agent to sufficiently explore uncertain environments, the human expert can take control in dangerous situations and demonstrate correct actions to avoid potential accidents. On the other hand, the agent could be guided to minimize traffic flow disturbance, thereby optimizing traffic flow efficiency. In detail, HAIM-DRL leverages data collected from free exploration and partial human demonstrations as its two training sources. Remarkably, we circumvent the intricate process of manually designing reward functions; instead, we directly derive proxy state-action values from partial human demonstrations to guide the agents’ policy learning. Additionally, we employ a minimal intervention technique to reduce the human mentor’s cognitive load. Comparative results show that HAIM-DRL outperforms traditional methods in driving safety, sampling efficiency, mitigation of traffic flow disturbance, and generalizability to unseen traffic scenarios.