Transportation Research Part C-Emerging Technologies最新文献

Estimating the large-scale Origin–Destination (OD) matrices for multi-modal public transport (PT) in different cities can vary largely based on the network itself, what modes exist, and what traffic data is available. In this study, to overcome the issue of traffic data unavailability and effectively estimate the demand matrix, we employ several data sets like the total boarding and alighting, smart card as well as the General Transit Feed Specification (GTFS) in order to capture the PT dynamic patronage patterns.

First, we propose a new method to model the dynamic large-scale stop-by-stop OD matrix for PT networks by developing a new enhancement of the Gravity Model via graph theory and Shannon’s entropy. Second, we introduce a method entitled “Entropy-weighted Ensemble Cost Features” that incorporates diverse sources of costs extracted from traffic states and the topological information in the network, scaled appropriately. Last, we compare the efficiency of a single travel cost versus various combinations of travel costs when using traditional methods like the Traverse Searching and the Hyman’s method, alongside our proposed “Entropy-weighted” method; we demonstrate the advantages of using topological features as travel costs and prove that our method, coupled with multi-modal PT OD matrix modelling, is superior to traditional methods in improving estimation accuracy, as evidenced by lower MAE, MAPE and RMSE, and reducing computing time.

Autonomous ride-hailing platforms, such as Waymo and Cruise, are quickly expanding their services, but their interactions with the existing ride-hailing companies, such as Uber and Lyft, are rarely discussed. To fill this gap, this paper focuses on the competition between an emerging autonomous ride-hailing platform and a traditional ride-hailing platform by characterizing the equilibrium of their competition and the impact of technology transfer. In particular, we consider an autonomous ride-hailing platform that owns the AV technology and offers ride-hailing services to passengers through a fleet of AVs. In the meanwhile, it competes with a traditional ride-hailing platform that primarily relies on a fleet of human-driver vehicles (HDVs) but may rent a sub-fleet of AVs from the autonomous ride-hailing platform to complement the human-driver fleet (referred to as AV technology transfer). A game-theoretic model is formulated to characterize the competition between the autonomous ride-hailing platform and the traditional ride-hailing platform over a transportation network, encapsulating the passengers’ mode choices, the drivers’ job options, the network traffic flows and the strategic decisions of the platforms. An algorithm is proposed to compute the approximate Nash equilibrium of the game and conduct an ex-post evaluation on the performance of the obtained solutions. The proposed framework and solution algorithm are validated through a realistic case study for Manhattan. Based on numerical simulations, we find that technology transfer of AVs between the two platforms can lead to a win-win situation where both two platforms get a higher profit, but this comes at the cost of reduced surpluses for human drivers and passengers. In the simulation, a critical trade-off is revealed for the autonomous ride-hailing platform: it strategically forfeits some of its market share in ride-hailing services to encourage the traditional ride-hailing platform to rent more AVs, thereby increasing its rental revenue and consequently, the overall profit. Furthermore, we also find it intriguing that as AV technology improves and operational costs decrease, the traditional ride-hailing platform cannot enjoy any benefit in its profit although it has the option of leasing AVs from the autonomous ride-hailing platform at lower operational costs. Instead, it is compelled to rent a larger fleet of AVs from the autonomous ride-hailing platform at a higher rental price, consequently suffering a reduced profit. Conversely, the autonomous ride-hailing platform significantly benefits from the reduced AV operational cost by capturing a larger market share in the ride-hailing market and earning higher revenue from the AV technology transfer.

Maritime safety and environmental protection are fundamental considerations within the shipping industry. In this context, port state control (PSC) inspection is globally implemented by port authorities as a mechanism to enforce both maritime safety standards and environmental regulations. This study proposes an innovative optimization framework based on machine learning (ML) and operations research models for high-risk vessel selection, aiming to maximize the efficiency and effectiveness of PSC inspection. The essence of the optimization framework is to accurately rank all ships with respect to their risk levels predicted by ML models. The loss functions of the tailored ML models follow a “smart predict then optimize” (SPO) criterion named cumulative detected deficiency number (CDDN), which is motivated by the characteristics of the decision problem. This inventive measurement transforms the assessment of ranking accuracy to the area of the segmented histogram of the recognized deficiency number, which bypasses the computationally intensive training step of rankings and is easy to compute. Following this, three types of decision tree (DT) models are developed, which differ from each other in the varying integration levels of CDDN. Particularly, we rigorously prove that one integration method yields a tree structure identical to that of traditional DT models. The proposed models are validated and compared with the traditional DT model on different scales of instances from real inspection records at the Hong Kong port. The experiment results indicate that our tailored DT models improve the ship selection efficiency significantly when the decision is complex, i.e., when we need to optimize the selection of a small number of ships for inspection from a large number of foreign visiting ships. Moreover, we also extensively discuss when and why the SPO framework offers a superior decision to optimize vessel selection.

This paper presents an integrated framework for optimizing signal control and vehicle routing. An important feature of the proposed framework is the ability to simultaneously determine signal states and individual vehicle routes in real time. The general objective is to minimize the network travel time, which can be represented as a trade-off between the total route length of all vehicles and traffic conditions at signalized intersections. A two-stage rolling horizon framework is proposed to explicitly describe the relationship between individual vehicle routes and predicted traffic flow dynamics at signalized intersections. The first stage involves a signal optimization problem, while the second stage optimizes a joint signal control and vehicle routing problem. Both stages are formulated as mixed integer linear programming problems. The optimization procedure is decentralized, and the effects of vehicle routing on control performance is considered by incorporating the route length cost into the objective function. Simulation experiments validate the advantages of the proposed framework over advanced signal control strategies and dynamic user-optimal routing strategies in various scenarios. The effectiveness in improving network capacity, alleviating spillback, and decreasing congestion dissipation time under over-saturation conditions is discussed. The results of vehicle routing suggest that the total travel time can be reduced at a low rerouting cost. Sensitivity analyses demonstrate the network control performance under different compliance rates and model coefficients. Moreover, the computational feasibility of the framework is verified.

Container terminals worldwide are experiencing their transitions into automated and intelligent terminals in the face of the ever increasing container handling demand and cost pressure. A key to cost-effective operations in automated container terminals is the efficient AGV scheduling algorithm that enables on-time fulfillment of container loading and discharging tasks. In this paper, we study an integrated task assignment and path planning problem for AGV scheduling in an automated container terminal. We propose a hierarchical solution framework to empower dynamic AGV scheduling, where the higher level employs a reinforcement learning algorithm for dynamic task assignment and the lower level makes use of a tailored path generation algorithm to generate low-cost and conflict-free paths for AGVs to serve the tasks. Additionally, we propose a container matching heuristic and a two-layer grid map to enhance the learning ability of the reinforcement learning algorithm. We compare the performance of the hierarchical solution framework against various benchmark methods on problem instances of practical scales. The results show that our approach is effective in reducing task delays and mitigating path conflicts, making the task assignment and path planning decisions more applicable for AGV scheduling in an automated container terminal.

This paper presents a cooperative two-dimensional trajectory planning algorithm for connected and automated vehicle (CAV) platoons. Specifically, the proposed algorithm generates two-dimensional optimal trajectories for CAVs with car-following relationships cooperatively within a complex road geometry. By extending the simplified Newell’s car-following model, we propose a two-dimensional Newell’s car-following model as an equilibrium car-following policy for CAVs. Based on this, a multi-objective constrained optimization is systematically formulated under a Cartesian coordinate. Due to the constraint’s complexity, a new solving algorithm based on the rapid random tree (RRT) technique is proposed. To test the effectiveness of our proposed models and algorithm, numerical simulation experiments with a real-world road geometry are conducted. Results indicate that our proposed method is able to generate trajectories for CAV platoons which are close to the equilibrium condition with smooth controls, while avoiding road obstacles. We further extend the definition of a one-dimensional car-following control string stability to a two-dimensional case. By this definition, we find that the proposed method can achieve empirical two-dimensional string stability, ensuring that both lateral and longitudinal disturbances are attenuated through vehicular strings.

Shared Autonomous Electric Vehicles (SAEVs) are pivotal for future transportation, offering both promise and challenges upon integration with the power grid. This symbiosis augments power system flexibility, stability and reliability through Vehicle-to-Grid (V2G) services, and optimize transportation efficiency. However, it amplifies the demand for robust charging infrastructure and electricity power during peak periods. This paper proposes a framework employing a sequential receding horizon optimization approach to manage SAEV mobility and charging dynamics. Focused on maximizing transportation service quality while ensuring power grid stability, the model accommodates dynamic trip requests and electricity generation, utilizing a rolling horizon algorithm. Notably, the study explores the potential of SAEVs in fortifying the integration of renewable energy resources (RES) into the power grid. Our research strives to equip policymakers and system planners with a robust tool for crafting efficient and sustainable future urban transportation and energy systems.

Electrification of transport is deemed by many countries worldwide as one of the key strategies to mitigate CO₂ emissions, yet the availability of reliable public charging infrastructure systems represents a potential serious bottleneck to such endeavours. Existing studies exploring battery electric vehicle (BEV) charging behaviour are typically based on either non-representative samples or stated choices experiments. This paper analyses observational data from a representative sample of German BEV owners who provided information on mileage and charging activities over a timeframe of eight weeks. BEV charging patterns, related vehicles kilometres travelled (VKT) and battery charging behaviour are assessed via a multifaceted empirical framework that pairs a hazard survival-based model with a log linear regression approach. A latent class method is also employed to segment BEV owners into different charging segments. The model suggests two types of charging behaviour exist, consisting of regular and irregular chargers. Charging frequencies and patterns are found to be radically different between the two groups under study, with regular chargers estimated to charge their vehicles 1.5 times more than irregular chargers. Lastly, the framework proposed is used to explore how charging behaviour will mutate due to both technology advancements (BEV driving range improvements) and user-centric factors (VKT variations). Neither technological or user factors are predicted to substantially affect the inter-charging duration of irregular chargers, whereas both increasing BEV driving ranges and reducing VKT results in a longer elapsed time between two consecutive charges for regular chargers.

Many infrastructure managers have the goal to increase the capacity of their railway infrastructure due to an increasing demand. While methods for performance calculations of railway line infrastructure are already well established, the determination of railway junction capacity remains a challenge. This work utilizes the concept of queueing theory to develop a method for the capacity calculation of railway junctions, solely depending on their infrastructure layout along with arrival and service rates. The implementation of the introduced approach is based on probabilistic model-checking. It can be used to decide which infrastructure layout to build, i.e. whether an overpass for the analysed railway junction is needed. The developed method addresses the need for fast and reliable timetable-independent railway junction capacity evaluation, catering specifically to the long-term strategic planning of junction infrastructure.

A crash risk evaluation model aims to estimate crash occurrence possibility by establishing the relationships between traffic flow status and crash occurrence. Based upon which, Proactive Traffic Safety Management (PTSM) systems have been developed and implemented. The current crash risk evaluation models relied on high dense traffic detectors, which limited the applications of PTSM to infrastructures with enough sensing devices. To address such application limitation issue, this study employed the widespread abnormal driving event information that is generated by emerging driving monitoring and vehicle connection techniques to develop the crash risk evaluation model. Specifically, to characterize abnormal driving events, a six-tuple embedding method was proposed to store their space, time and kinetics features. Given their irregular and discrete distributions on roadways, a Transformer model with self-attention mechanism was proposed to extract the spatial distribution characteristics. In addition, a time-decay function was integrated to fit the temporal impacts of abnormal driving events on crash risk. Empirical data from a freeway in China were utilized for the analyses. The results showed that abnormal driving events with lower speed, larger acceleration and duration are more likely to cause crashes. The accumulation of multiple events in the time period of less than 3 min would lead to a sharp increase of crash risk. Besides, compared to the average metrics of the widely adopted Convolutional Neural Network (CNN), XGBoost, and logistic regression models, the proposed model achieved higher accuracy (0.841) and AUC (0.777), with average improvement of 2.5 % and 9.1 % respectively.