Transportation Research Part C-Emerging Technologies最新文献

Accurate monitoring and sensing network-wide traffic conditions under uncertainty is vital for addressing urban transportation obstacles and promoting the evolution of intelligent transportation systems (ITS). Owing to fluctuations in traffic demand, traffic conditions exhibit stochastic variations by the time of day and day of the year. The joint estimation of stochastic speed and flow is pivotal in ITS, drawing on the symbiotic relationship between these two variables to furnish comprehensive insights into traffic conditions. Nevertheless, constraints such as budgetary limitations and physical boundaries render the coverage of traffic detectors both sparse and inadequate, thereby complicating the precise assessment of network-wide traffic speeds and flows in uncertain scenarios. To address this challenging problem, this paper proposes a novel network-wide traffic speed-flow estimator (SFE) grounded in the Kullback-Leibler divergence optimization method. This SFE harnesses data derived from sparse multi-type detectors, such as point detectors and automatic vehicle identification sensors. Significantly, it leverages the statistical correlation relationships (i.e., covariance matrix) of the speed and flow between observed and unobserved links to estimate stochastic speed and flow on unobserved links (i.e., the links without traffic detectors). In addition, fundamental diagrams, modeling the interdependence between link speeds and flows, are incorporated as constraints in the proposed SFE. This inclusion markedly diminishes discrepancies and elevates estimation precision relative to individual assessments of speeds and flows. Numerical illustrations, encompassing both simulated and real-world road networks, validate the enhanced performance and applicability of the proposed SFE, suggesting its potential role in augmenting data robustness within ITS.

Introducing electric vehicles that tow aircraft during taxiing is an emerging technology aimed at supporting climate neutrality for aviation. Planning electric towing operations is, however, impeded by the high uncertainty in aircraft arrival and departure times. We address the question of how to plan the operation of a fleet of Electric Towing Vehicles (ETVs) to maximize environmental benefits, given the uncertainty in aircraft arrival/departure times. For this, we propose a stochastic and dynamic planning framework for ETVs, where stochastic aircraft arrival and departure times are updated during the day. With this, the assignment of the ETVs-to-aircraft to replace conventional taxiing, and ETV battery charging times are planned such that the fuel savings are maximized. At the same time, we ensure that aircraft delays induced by the use of ETVs are minimized. We illustrate our framework for a large European airport. The results show that our framework achieves 79.5% of the highest possible cost reduction (fuel and ETV-induced delay), which is obtained when full knowledge of the arrival/departure times is available in advance. Furthermore, we show that considering the uncertainty in the arrival/departure times, rather than using point estimates of these times, leads to a 17.7% additional cost reduction. Overall, our framework supports the implementation of electric aircraft towing with maximum environmental benefits while considering the dynamic, uncertain arrival and departure times of aircraft.

Intercity truck transport emerged as a crucial lifeline for maintaining city operations during COVID-19 pandemic. Understanding pandemic-imposed impacts on intercity truck transport can inform policymakers in crafting more effective strategies for future crises and disruptions. However, to our best knowledge, previous research predominantly focused on freight movements under normal circumstances. Due to the data limitation, the pandemic-related studies commonly relied on freight survey and focused on specific industries, which cannot capture the full spectrum of factors influencing freight trip generation (FTG) during the pandemic. Here, a novel dataset capturing large-scale individual truck movements during the COVID-19 pandemic is provided. By leveraging the mobility dataset, pandemic-induced changes in truck transport demand structure are quantified using spatial statistical methods. Furthermore, an interpretable machine learning framework for intercity freight demand estimation is developed, revealing the complex interplay of factors that influence and shape the behavior shifts of intercity truck transport systems due to the pandemic outbreak. The findings suggest significant changes in various factors influencing intercity truck movements across local and broader regions, emphasizing city-specific challenges amidst pandemic. The developed FTG model could serve as a tool to predict freight demand between cities for future crises and to support policymaking in the practice of freight management.

In the context of the global maritime industry, which plays a vital role in international trade, navigating vessels safely and efficiently remains a complex challenge, especially due to the absence of structured road-like networks on the open seas. This paper proposes MATNEC, a framework for constructing a data-driven Maritime Traffic Network (MTN), represented as a graph that facilitates realistic route generation. Our approach, leveraging Automatic Identification System (AIS) data along with portcall and global coastline datasets, aims to address key challenges in MTN construction from AIS data observed in the literature, particularly the imprecise placement of network nodes and sub-optimal definition of network edges. At the core of MATNEC is a novel incremental clustering algorithm that is capable of intelligently determining the placement and distribution of the graph nodes in a diverse set of environments, based on several environmental factors. To ensure that the resulting MTN generates maritime routes as realistic as possible, we design a novel edge mapping algorithm that defines the edges of the network by treating the mapping of AIS trajectories to network nodes as an optimisation problem. Finally, due to the absence of a unified approach in the literature for measuring the efficacy of an MTN’s ability to generate realistic routes, we propose a novel methodology to address this gap. Utilising our proposed evaluation methodology, we compare MATNEC with existing methods from literature. The outcome of these experiments affirm the enhanced performance of MATNEC compared to previous approaches.

This paper systematically analyzes the security risks associated with artificial intelligence (AI) components in autonomous vehicles (AVs). Given the increasing reliance on AI for various AV functions, from perception to control, the potential for security breaches presents a significant challenge. We focus on AI security, including attacks like adversarial examples, backdoors, privacy breaches and unauthorized model replication, reviewing over 170 papers. To evaluate the practical implications of such vulnerabilities we introduce qualitative measures for assessing the exposure and severity of potential attacks. Our findings highlight a critical need for more realistic security evaluations and a balanced focus on various sensors, learning paradigms, threat models, and studied attacks. We also pinpoint areas requiring more research, such as the study of training time attacks, transferability, system-based studies and development of effective defenses. By also outlining implications for the automotive industry and policymakers, we not only advance the understanding of AI security risks in AVs, but contribute to the development of safer and more reliable autonomous driving technologies.

The dial-a-ride (DAR) service is a precursor to emerging shared mobility. Service providers expect efficient management of fleet resources to improve service quality without degrading economic viability. Most existing studies overlook possible future demands that could yield better matching opportunities and scheduling benefits, and therefore have short-sighted limitations. Moreover, the effects of correlated demand and potential prediction errors were ignored. To address these gaps, this paper investigates prediction-failure-risk-aware online DAR scheduling with spatial demand correlation. Request selection and cancellation are explicitly considered. We formulate the problem as a Markov decision process (MDP) and solve it by approximate dynamic programming (ADP). We further develop a demand prediction model that can capture the characteristics of DAR travel demand (uncertainty, sparsity, and spatial correlation). Deep quantile regression is adopted to estimate the marginal distribution of each OD pair. These marginals are combined into a joint demand distribution by constructing a Gaussian Copula to capture the spatial demand correlation. A prediction error correction mechanism is proposed to eliminate prediction errors and rectify policies promptly. Based on the model properties, several families of customized pruning strategies are devised to improve the computational efficiency and solution quality of ADP. We solve policies over time in the dynamic environment mixed with actual and stochastic future demands via the ADP algorithm and scenario approach. We propose the value function rolling method and multi-scenario exploration method, to address the deviation of the value function and identify the optimal policy from multiple future demand scenarios. Numerical results demonstrate the importance and benefits of incorporating demand forecasting and spatial correlation into the DAR operation. The improvement due to prediction is significant even when the prediction is imperfect, while the demand prediction can hedge against the negative effects of request cancellation. The real-world application result shows that compared to state-of-the-practice, the overall delivery efficiency can be substantially improved, along with better service quality and fleet size savings.

This paper proposes a novel algorithmic framework to enhance the convergence efficiency of the alternating direction method of multipliers (ADMM) by incorporating the successive over relaxation (SOR) splitting method. The proposed framework holds applicability across various research fields for improving convergence efficiency. Currently, there exist two main methods for decomposing the separate optimization problems: Gauss-Seidel (GS) and Jacobi methods. The SOR method introduced in this paper offers a more efficient alternative. Following the original ADMM algorithm’s framework, we provide a detailed procedure for incorporating the SOR method into the ADMM framework in place of the GS splitting method. This development gives rise to a new method called ADMM-SOR, and then we apply this newly proposed algorithm to solve the deterministic user equilibrium (DUE) problem. Subsequently, to ensure the reliability of the proposed algorithm, we rigorously prove its convergence by leveraging some properties of variational inequalities. Additionally, the impact of the relaxation factor on the efficiency of the ADMM-SOR method is conducted, and we also explore a novel method to self-adjust the relaxation factor during each iteration. The new algorithm is verified based on numerical experiments, revealing that the novel ADMM-SOR framework achieves faster convergence in comparison to the original one, all the while maintaining exceptional parallel performance.

The real-time crash likelihood prediction model is an essential component of the proactive traffic safety management system. Over the years, numerous studies have attempted to construct a crash likelihood prediction model in order to enhance traffic safety, but mostly on freeways. In the majority of the existing studies, researchers have primarily used a deep learning-based framework to identify crash potential. Lately, Transformers have emerged as a potential deep neural network that fundamentally operates through attention-based mechanisms. Transformers exhibit distinct functional benefits over established deep learning models like Recurrent Neural Networks (RNNs), Long Short-Term Memory networks (LSTMs), and Convolutional Neural Networks (CNNs). First, they employ attention mechanisms to accurately weigh the significance of different parts of input data, a dynamic functionality that is not available in RNNs, LSTMs, and CNNs. Second, they are well-equipped to handle dependencies over long-range data sequences, a feat RNNs typically struggle with. Lastly, unlike RNNs, LSTMs, and CNNs, which process data in sequence, Transformers can parallelly process data elements during training and inference, thereby enhancing their efficiency. Apprehending the immense possibility of Transformers, this paper proposes inTersection-Transformer (inTformer), a time-embedded attention-based Transformer model that can effectively predict intersection crash likelihood in real-time. The inTformer is basically a binary prediction model that predicts the occurrence or non-occurrence of crashes at intersections in the near future (i.e., next 15 min). The proposed model was developed by employing traffic data extracted from connected vehicles. Acknowledging the complex traffic operation mechanism at intersection, this study developed zone-specific models by dividing the intersection region into two distinct zones: within-intersection and approach zones, each representing the intricate flow of traffic unique to the type of intersection (i.e., three-legged and four-legged intersections). In the ‘within-intersection’ zone, the inTformer models attained a sensitivity of up to 73%, while in the ‘approach’ zone, the sensitivity peaked at 74%. Moreover, benchmarking the optimal zone-specific inTformer models against earlier studies on crash likelihood prediction at intersections and several established deep learning models trained on the same connected vehicle dataset confirmed the superiority of the proposed inTformer. Further, to quantify the impact of features on crash likelihood at intersections, the SHAP (SHapley Additive exPlanations) method was applied on the best performing inTformer models. The most critical predictors were average and maximum approach speeds, average and maximum control delays, average and maximum travel times, split failure percentage and count, and percent arrival on green.

High demand, rising customer expectations, and government regulations are forcing companies to increase the efficiency and sustainability of urban (last-mile) distribution. Consequently, several new delivery concepts have been proposed that increase flexibility for customers and other stakeholders. One of these innovations is crowdsourced delivery, where deliveries are made by occasional drivers who wish to utilize their surplus resources (unused transport capacity) by making deliveries in exchange for some compensation. The potential benefits of crowdsourced delivery include reduced delivery costs and increased flexibility (by scaling delivery capacity up and down as needed). The use of occasional drivers poses new challenges because (unlike traditional couriers) neither their availability nor their behavior in accepting delivery offers is certain. The relationship between the compensation offered to occasional drivers and the probability that they will accept a task has been largely neglected in the scientific literature. Therefore, we consider a setting in which compensation-dependent acceptance probabilities are explicitly considered in the process of assigning delivery tasks to occasional drivers. We propose a mixed-integer nonlinear model that minimizes the expected delivery costs while identifying optimal assignments of tasks to a mix of professional and occasional drivers and their compensation. We propose an exact two-stage solution algorithm that allows to decompose compensation and assignment decisions for generic acceptance probability functions and show that the runtime of this algorithm is polynomial under mild conditions. Finally, we also study a more general case of the considered problem setting, show that it is NP-hard and propose an approximate linearization scheme of our mixed-integer nonlinear model. The results of our computational study show clear advantages of our new approach over existing ones. They also indicate that these advantages remain in dynamic settings when tasks and drivers are revealed over time and in which case our method constitutes a fast, yet powerful heuristic.

Population synthesis involves generating synthetic yet realistic representations of a target population of micro-agents for behavioral modeling and simulation. Traditional methods, often reliant on target population samples, such as census data or travel surveys, face limitations due to high costs and small sample sizes, particularly at smaller geographical scales. We propose a novel framework based on copulas to generate synthetic data for target populations where only empirical marginal distributions are known. This method utilizes samples from different populations with similar marginal dependencies, introduces a spatial component into population synthesis, and considers various information sources for more realistic generators. Concretely, the process involves normalizing the data and treating it as realizations of a given copula, and then training a generative model before incorporating the information on the marginals of the target population. Utilizing American Community Survey data, we assess our framework’s performance through standardized root mean squared error (SRMSE) and so-called sampled zeros. We focus on its capacity to transfer a model learned from one population to another. Our experiments include transfer tests between regions at the same geographical level as well as to lower geographical levels, hence evaluating the framework’s adaptability in varied spatial contexts. We compare Bayesian Networks, Variational Autoencoders, and Generative Adversarial Networks, both individually and combined with our copula framework. Results show that the copula enhances machine learning methods in matching the marginals of the reference data. Furthermore, it consistently surpasses Iterative Proportional Fitting in terms of SRMSE in the transferability experiments, while introducing unique observations not found in the original training sample.