Article
Transportation
Han Liu, Ye Tian, Jian Sun, Di Wang
Summary: Traditional traffic simulation systems have limitations in performance and calibration/validation processes due to their use of independent models without considering their coupling relationship. In this study, a Data-Driven Simulation System (DDSS) framework was introduced to address this issue by defining traffic system operation processes and coordinating submodules. Experimental results showed that DDSS outperforms the widely used VISSIM simulation system in terms of accuracy and overall performance.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Zizhen Xu, Chuwei Zhang, Shauhrat S. Chopra
Summary: This research evaluates node percolation in the transportation domain, specifically in the public bus transit system, and assesses the impact of post-disruption response measures on network robustness. The study finds that the dependent network model of public bus transit becomes increasingly vulnerable to infrastructure failures, but response measures are effective up to a certain level of disruption. Furthermore, the research provides prescriptive insights into the design of transportation contingency plans.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Wenhua Jiang, Nan Zheng, Inhi Kim
Summary: This paper presents a new perspective for in-station transfer flow estimation using data collected by a WiFi sensor system. The proposed method is critical for path choice modeling and pedestrian management. It utilizes a 'seed matrix' constructed based on the identification of inter-platform transfer activities to estimate the full in-station transfer flow. The main challenge is handling the missing elements in the 'seed matrix' caused by sensor failures. The proposed self-measuring multi-task Gaussian process (SM-MTGP) framework addresses this problem by capturing the heterogeneous correlations in temporal features.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Gen Li, Zhen Yang, Yiyong Pan, Jianxiao Ma
Summary: This paper investigates the characteristics of discretionary lane change duration on freeways and establishes four stochastic lane change duration models based on vehicle type and lane change direction. The results show that driver heterogeneity, vehicle type, and lane change direction significantly influence the duration of lane change. The findings of this study are helpful for understanding the mechanism of lane change process, the impact of lane change on traffic flow, and improving the safety of lane-changing behaviors of connected and autonomous vehicles.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Passant Reyad, Tarek Sayed
Summary: This paper proposes a multi-criteria reinforcement learning based ATSC algorithm, aiming to improve both traffic safety and mobility. The algorithm was trained and validated using real-time traffic simulation and extreme value theory models, showing significant improvements in safety and mobility.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Baorui Han, Ruitong Zhu, Ren Dong, Mengfan Zhang, Wanlu Song, Zhenjun Zhu
Summary: This study investigates the characteristics of traffic flow in narrow lanes by analyzing vehicle trajectory data. The results show that the behavior of drivers in narrow lanes is influenced by speed, lane width, and position, and a predictive model for driver's following strategy is constructed.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Lin Yu, Fangce Guo, Aruna Sivakumar, Sisi Jian
Summary: Short-term traffic prediction is a widely studied topic in Intelligent Transport Systems. Insufficient data across the entire road network poses a challenge for machine learning-based prediction techniques. To address this, a hybrid framework is developed, combining prior knowledge transferring algorithm and two popular models, Long-short Term Memory and Spatial-Temporal Graph Convolutional Neural Network. The proposed framework is trained and tested using traffic flow data from London, showing that transferring local network prior knowledge improves prediction accuracy under inadequate data conditions.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Servet Lapardhaja, Kemal Ulas Yagantekin, Mingyuan Yang, Tasnim Anika Majumder, Xingan (David) Kan, Mohamed Badhrudeen
Summary: Research has shown that using ACC with electric vehicles can increase road capacity at bottlenecks, and this has been validated in experiments.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Ruochen Hao, Meiqi Liu, Wanjing Ma, Bart van Arem, Meng Wang
Summary: Due to the complexity of manoeuvre, there is a lack of models in the literature that describe the platoon formation process on urban roads. Inspired by flocking behaviours in nature, this study proposes a two-dimensional model based on the potential theory to describe the dynamics of connected automated vehicle (CAV) groups, which can also be applied to human-driven vehicles in mixed traffic environments.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Surachet Pravinvongvuth, Imalka C. Matarage
Summary: This research proposes the Chet network as a new transportation network to enhance vehicular flow in a newly built area. The network consists of hexagonal blocks formed by uniquely arranged one- and two-way links, allowing vehicles to move without conflicts at intersections. With a low-cost infrastructure and no need for stop signs or traffic signals, the Chet network is expected to outperform traditional grid networks in terms of mobility. Microscopic traffic simulation validates the concept and yields impressive numerical results. This original and innovative design has the potential to revolutionize people's way of living and traveling.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Zebin Chen, Shukai Li, Huimin Zhang, Yanhui Wang, Lixing Yang
Summary: This paper proposes a novel distributed model predictive control scheme for real-time train regulation in urban metro transportation. By decomposing the original optimization problem into smaller and less complicated optimization control problems, the flexibility and modularity of the control structure are ensured.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Xia Jiang, Jian Zhang, Dan Li
Summary: This paper proposes an eco-driving framework for electric connected vehicles (CVs) based on reinforcement learning (RL) to improve vehicle energy efficiency at signalized intersections. The framework integrates car-following policy, lane-changing policy, and RL policy to ensure safe operation. A Markov Decision Process (MDP) is formulated to optimize the car-following and lane-changing behaviors of CVs. The proposed methods are evaluated in SUMO software and show significant reduction in energy consumption without interrupting other human-driven vehicles (HDVs).
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Hongyu Rao, Duo Zhang, Guoyang Qin, Lishengsa Yue, Jian Sun
Summary: This study used a large-scale naturalistic driving data set to investigate the occurrence of driver's intra-driver heterogeneity in car-following. The researchers identified unusual behavior by comparing observed behavior with a baseline model and found that intra-driver heterogeneity was statistically related to vehicle kinematic features, traffic flow, and surrounding environment, but not driver sociodemographics. Being cut in was the most prominent trigger for intra-driver heterogeneity. These findings provide valuable insights for improving car-following modeling and other engineering practices.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Review
Transportation
Can Li, Lei Bai, Lina Yao, S. Travis Waller, Wei Liu
Summary: Transportation is crucial for the economy and urban development, but it faces challenges in terms of efficiency, sustainability, resilience, and intelligence. Reinforcement Learning (RL) has emerged as a useful approach for smart transportation applications, allowing autonomous decision-makers to learn from experiences and make optimal actions in complex environments. This paper conducts a bibliometric analysis to understand the development of RL-based methods in transportation applications and provides a comprehensive literature review on the specific topics. Future research directions for RL applications and developments are also discussed.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Wenbo Du, Shaochuan Zhu, Lu (Carol) Tong, Kaiquan Cai, Zhe Liang
Summary: The Robust Gate Assignment Problem (RGAP) focuses on generating a reliable schedule that minimizes potential gate conflicts caused by stochastic flight delays. This study explores the relationship between schedule robustness and aircraft delay heterogeneity, which has not been well investigated. Two new measurements are proposed to quantify potential conflicts from an expected perspective, and a set-covering model is developed to optimize both expected conflict cost and operating cost. A column generation-based heuristic (CDBH) is developed to efficiently solve the model and provide high-quality solutions. Computational studies based on Shenzhen Baoan International Airport demonstrate that the proposed measurements significantly improve the robustness of gate schedules considering delay heterogeneity.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Guohong Wu, Rui Jiang
Summary: In this paper, a mixed integer linear programming (MILP) model is proposed to optimize autonomous intersection management and trajectory smoothing design (TSD) simultaneously. The model takes into account driving safety, constraints, and the vehicle trajectory within the intersection. A rolling horizon framework is used to solve the model. The joint optimization model is compared with a two-stage strategy in terms of traffic efficiency, fuel economy, monetary cost, and driving comfort.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Adje Jeremie Alagbe, Sheng Jin, Qianhan Bao, Wentong Guo
Summary: This study investigates the flow distribution patterns at intersection approaches with variable approach lanes (VALs) and proposes a new lane utilization adjustment factor specifically for VALs. Unmanned aerial vehicles (UAVs) were used to collect naturalistic data, including traffic flow, approach geometry, and signal control-specific information, at selected intersections in Hangzhou, China. Machine learning techniques were employed to develop accurate regression models for estimating lane utilization, separately for the two VAL statuses.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Xinhua Mao, Shi Dong, Jianwei Wang, Jibiao Zhou, Changwei Yuan, Tao Zheng
Summary: This study proposes a bi-objective mixed integer programming model that considers the capital constraints in road network maintenance scheduling. A link-based day-to-day dynamics model is developed to simulate the transient fluctuation in traffic flows, and a nondominated sorting genetic algorithm-II (NSGA-II) is used to solve the bi-objective model and generate optimal Pareto solutions. The TOPSIS method is then adopted to determine the best compromise solution.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Muaid Abdulkareem Alnazir Ahmed, Hooi Ling Khoo, Oon-Ee Ng
Summary: This study introduces a control strategy based on intersection capacity, utilizing available space at discharge routes for optimization. The downstream policy guides a deep Q-learning agent (DQLA) using density and speed (k-v) measurements and a constrained local communication protocol to manage a signalized junction. Testing in a simulated micro-model of a real urban traffic network proves the effectiveness of the discharge-based controller in mitigating overall operation. The DQLA k-v controller achieves significant cost savings in waiting and travel time, and attains the highest mean travel speed, resulting in close to optimum network operation with a 0.80 clearance ratio.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Transportation
Jiyeon Lee, Ilkyeong Moon
Summary: The purpose of this study is to adjust flight schedules in response to changes in airport capacity in order to maximize airline profits. A mixed-integer linear programming (MILP) model was formulated to reschedule flights, considering uncertainty in future conditions. The optimal model provides solutions for different scenarios of capacity changes, while the stochastic model minimizes the expected cost across all scenarios. The study also considers delay propagation between airports and incorporates costs associated with airline resources.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)