Communications in Transportation Research最新文献

Amid escalating energy crises and environmental pressures, electric vehicles (EVs) have emerged as an effective measure to reduce reliance on fossil fuels, combat climate change, uphold sustainable energy and environmental development, and strive towards carbon peaking and neutrality goals. This study introduces a nonlinear integer programming model for the deployment of dynamic wireless charging lanes (DWCLs) and EV charging strategy joint optimization in highway networks. Taking into account established charging resources in highway service areas (HSAs), the nonlinear charging characteristics of EV batteries, and the traffic capacity constraints of DWCLs. The model identifies the deployment of charging facilities and the EV charging strategy as the decision-making variables and aims to minimize both the DWCL construction and user charging costs. By ensuring that EVs maintain an acceptable state of charge (SoC), the model combines highway EV charging demand and highway EV charging strategy to optimize the DWCL deployment, thus reducing the construction cost of wireless charging facilities and user charging expenses. The efficacy and universality of the model are demonstrated using the classical Nguyen–Dupius network as a numerical example and a real-world highway network in Guangdong Province, China. Finally, a sensitivity analysis is conducted to corroborate the stability of the model. The results show that the operating speed of EVs on DWCLs has the largest impact on total cost, while battery capacity has the smallest. This comprehensive study offers vital insights into the strategic deployment of DWCLs, promoting the sustainable and efficient use of EVs in highway networks.

In recent years, the advancement of artificial intelligence techniques has led to significant interest in reinforcement learning (RL) within the traffic and transportation community. Dynamic traffic control has emerged as a prominent application field for RL in traffic systems. This paper presents a comprehensive survey of RL studies in dynamic traffic control, addressing the challenges associated with implementing RL-based traffic control strategies in practice, and identifying promising directions for future research. The first part of this paper provides a comprehensive overview of existing studies on RL-based traffic control strategies, encompassing their model designs, training algorithms, and evaluation methods. It is found that only a few studies have isolated the training and testing environments while evaluating their RL controllers. Subsequently, we examine the challenges involved in implementing existing RL-based traffic control strategies. We investigate the learning costs associated with online RL methods and the transferability of offline RL methods through simulation experiments. The simulation results reveal that online training methods with random exploration suffer from high exploration and learning costs. Additionally, the performance of offline RL methods is highly reliant on the accuracy of the training simulator. These limitations hinder the practical implementation of existing RL-based traffic control strategies. The final part of this paper summarizes and discusses a few existing efforts which attempt to overcome these challenges. This review highlights a rising volume of studies dedicated to mitigating the limitations of RL strategies, with the specific aim of enhancing their practical implementation in recent years.

The estimation and analysis of road traffic represent the preliminary steps towards satisfying the current needs for smooth, safe, and green transportation. Therefore, effective traffic monitoring is an essential topic alongside the planning of sustainable transportation systems and the development of new traffic management concepts. In contrast to classical traffic detection solutions, this study investigates the correlation between travelers' social activities and road traffic. The s's primary goal is to investigate the presence of the relationship between social activity and road traffic, which might allow an infrastructure-independent traffic monitoring technique as well. People's general activities at Point of Interest (POI) locations (measured as occupancy parameter) are correlated with traffic data so that, finally, proper proxys can be defined for link-level average traffic speed estimation. The method is tested and evaluated using real-world traffic and POI occupancy data from Budapest (District XI.). The results of the correlation investigation justify an indirect relationship between activity at POIs and road traffic, which holds promise for future practical applicability.

This study presents a comprehensive analysis of the relationship between congestion and lane changing, using vehicle trajectory data from the M1 motorway in Sydney. We establish a connection between the distribution of travel time and lane changing frequency and employ a Poisson process to describe the intensity of lane changing occurrences in different travel time ranges. From an individual perspective, lane changing does not bring significant speed benefits in most cases, except when the speed range is between 45 and 50 ​km/h. From a system perspective, the relationship between lane change rate and speed depends on the purpose of the lane changes. In merging, diverging, and lane restriction areas, for instance, mandatory lane changes dominate. In most sections of the motorway, discretionary lane changes are motivated by the expectation of improving speed and/or safety. Additionally, we demonstrate a mutual causality relationship between lane changing and congestion through the Granger causality test. This relationship is more pronounced in general areas during peak periods and contributes to the deterioration of the driving environment.

The data-driven Intelligent Transportation System (ITS) provides great support to travel decisions and system management but inevitably encounters the issue of data missing in monitoring systems. Hence, network-wide traffic state prediction and imputation is critical to recognizing the system level state of a transportation network. Abundant research works have adopted various approaches for traffic prediction and imputation. However, previous methods ignore the reliability analysis of the predicted/imputed traffic information. Thus, this study originally proposes an attentive graph neural process (AGNP) method for network-level short-term traffic speed prediction and imputation, simultaneously considering reliability. Firstly, the Gaussian process (GP) is used to model the observed traffic speed state. Such a stochastic process is further learned by the proposed AGNP method, which is utilized for inferring the congestion state on the remaining unobserved road segments. Data from a transportation network in Anhui Province, China, is used to conduct three experiments with increasing missing data ratio for model testing. Based on comparisons against other machine learning models, the results show that the proposed AGNP model can impute traffic networks and predict traffic speed with high-level performance. With the probabilistic confidence provided by the AGNP, reliability analysis is conducted both numerically and visually to show that the predicted distributions are beneficial to guide traffic control strategies and travel plans.

This paper considers the problem of supply-demand imbalances in Mobility-on-Demand (MoD) services. These imbalances occur due to uneven stochastic travel demand and can be mitigated by proactively rebalancing empty vehicles to areas where the demand is high. To achieve this, we propose a method that takes into account uncertainties of predicted travel demand while minimizing pick-up time and rebalance mileage for autonomous MoD ride-hailing. More precisely, first travel demand is predicted using Gaussian Process Regression (GPR) which provides uncertainty bounds on the prediction. We then formulate a stochastic model predictive control (MPC) for the autonomous ride-hailing service and integrate the demand predictions with uncertainty bounds. In order to guarantee constraint satisfaction in the optimization under estimated stochastic demand prediction, we employ a probabilistic constraining method with user-defined confidence interval, using Chance Constrained MPC (CCMPC). The benefits of the proposed method are twofold. First, travel demand uncertainty prediction from data can naturally be embedded into the MoD optimization framework, allowing us to keep the imbalance at each station below a certain threshold with a user-defined probability. Second, CCMPC can be relaxed into a Mixed-Integer-Linear-Program (MILP) and the MILP can be solved as a corresponding Linear-Program, which always admits an integral solution. Our transportation simulations show that by tuning the confidence bound on the chance constraint, close to optimal oracle performance can be achieved, with a median customer wait time reduction of 4% compared to using only the mean prediction of the GPR.

Understanding the interdependent nature of multimodal public transit networks (PTNs) is vital for ensuring the resilience and robustness of transportation systems. However, previous studies have predominantly focused on assessing the vulnerability and characteristics of single-mode PTNs, neglecting the impacts of heterogeneous disturbances and shifts in travel behavior within multimodal PTNs. Therefore, this study introduces a novel resilience assessment framework that comprehensively analyzes the coupling mechanism, structural and functional characteristics of bus–rail transit networks (BRTNs). In this framework, a network performance metric is proposed by considering the passengers’ travel behaviors under various disturbances. Additionally, stations and subnetworks are classified using the k-means algorithm and resilience metric by simulating various disturbances occurring at each station or subnetwork. The proposed framework is validated via a case study of a BRTN in Beijing, China. Results indicate that the rail transit network (RTN) plays a crucial role in maintaining network function and resisting external disturbances in the interdependent BRTN. Furthermore, the coupling interactions between the RTN and bus transit network (BTN) exhibit distinct characteristics under infrastructure component disruption and functional disruption. These findings provide valuable insights into emergency management for PTNs and understanding the coupling relationship between BTN and RTN.

Vehicle electrification has emerged as a global strategy to address climate change and emissions externalities from the transportation sector. Deployment of charging infrastructure is needed to accelerate technology adoption; however, managers and policymakers have had limited evidence on the use of public charging stations due to poor data sharing and decentralized ownership across regions. In this article, we use machine learning based classifiers to reveal insights about consumer charging behavior in 72 detected languages including Chinese. We investigate 10 years of consumer reviews in East and Southeast Asia from 2011 to 2021 to enable infrastructure evaluation at a larger geographic scale than previously available. We find evidence that charging stations at government locations result in higher failure rates with consumers compared to charging stations at private points of interest. This evidence contrasts with predictions in the U.S. and European markets, where the performance is closer to parity. We also find that networked stations with communication protocols provide a relatively higher quality of charging services, which favors policy support for connectivity, particularly for underserved or remote areas.