Modern Transportation Systems Research Articles

Automated Car: Intelligent Maneuver

Abstract: Automated vehicles are rapidly evolving to meet the demands of modern transportation systems, aiming for enhanced safety, efficiency, and user experience. Autonomous vehicles are also a big part of these technologies. The most important action of a driver has to do is to follow the lanes on the way to the destination. This research presents Intelligent Maneuver, a sophisticated framework integrating four key functionalities crucial for automated car navigation: object avoidance, traffic light detection, self-parking, and lane detection. Leveraging advanced computer vision techniques and sensors fusion our framework enables vehicles to navigate complex urban environments autonomously

SiG: A Siamese-Based Graph Convolutional Network to Align Knowledge in Autonomous Transportation Systems

Domain knowledge is gradually renovating its attributes to exhibit distinct features in autonomy, propelled by the shift of modern transportation systems (TS) toward autonomous TS (ATS) comprising three progressive generations. The knowledge graph (KG) and its corresponding versions can help depict the evolving TS. Given that KG versions exhibit asymmetry primarily due to variations in evolved knowledge, it is imperative to harmonize the evolved knowledge embodied by the entity across disparate KG versions. Hence, this article proposes a siamese-based graph convolutional network (GCN) model, namely SiG , to address unresolved issues of low accuracy, efficiency, and effectiveness in aligning asymmetric KGs. SiG can optimize entity alignment in ATS and support the analysis of future-stage ATS development. Such a goal is attained through (a) generating unified KGs to enhance data quality, (b) defining graph split to facilitate entire-graph computation, (c) enhancing a GCN to extract intrinsic features, and (d) designing a siamese network to train asymmetric KGs. The evaluation results suggest that SiG surpasses other commonly employed models, resulting in average improvements of 23.90% and 37.89% in accuracy and efficiency, respectively. These findings have significant implications for TS evolution analysis and offer a novel perspective for research on complex systems limited by continuously updated knowledge.

Liner shipping network design problem in modern transportation system of Russia

The liner shipping network design problem is considered in the paper. This problem is particularly relevant in the current global political and economic conditions, where finding optimal solutions for business becomes crucial for survival. State-of-the-art formulations and methods for solving the problem in domestic and international scientific papers are discussed. Four types of liner services such as simple service, “butterfly”, “pendulum” and complex service are described. A simple service that can be reduced to the traveling salesman problem is primarily focused on. Our own formulation of the problem is proposed and an example of liner shipping network description, based on the proposed formulation, is provided. In the example, presented in the paper, a container line, based on a single domestic seaport (Vladivostok) and four seaports in China, is demonstrated. It should be noticed, that the problem includes several optimization sub-problems (such as multi-commodity flow problem), solving which is important for finding best solutions for the designed shipping line, but is outside the bounds of this research. The liner services as a sequence of vessel calls to ports are described; and some results of the foregoing generation process are discussed. The optimal solution is selected from the set of generated solutions. It represents a particular case that simultaneously has the lowest costs for implementing the container line and the highest number of serviced container flows. It is noted that this solution is optimal only within the generated solution space and may not be optimal for the considered example of the problem.

Assessment Possibilities for Trajectory Fusion of Two Vehicles in the Case of Automated Vehicles

Because of the increasing integration of automation and cutting-edge technology into modern transportation systems, the development of efficient and dependable Automated Vehicles (AVs) has become an important area of research. One of the most important characteristics of AVs is their ability to perceive and navigate complex environments safely. The process of combining trajectory data from multiple vehicles, known as trajectory fusion, has the potential to improve AV perception. The feasibility of implementing trajectory fusion in the context of two autonomous vehicles coexisting in the same operational environment is investigated in this study. The primary goal of this research is to investigate the effectiveness of trajectory fusion in increasing the environmental awareness of Automated Vehicles (AVs), while also investigating its implications for the decision-making mechanisms that govern these vehicles. The MATLAB Simulink simulation platform was essential in carrying out this investigation. The intricate dynamics of trajectory fusion within the context of dual AVs were meticulously analyzed and evaluated using this software.

MACNS: A generic graph neural network integrated deep reinforcement learning based multi-agent collaborative navigation system for dynamic trajectory planning

Multi-agent collaborative navigation is prevalent in modern transportation systems, including delivery logistics, warehouse automation, and personalised tourism, where multiple moving agents (e.g., robots and people) must meet at a common destination from different starting points. However, traditional methods face challenges in efficiently and accurately optimising routes for multiple moving agents (e.g., robots). These include dynamically adjusting the common destination in response to changing traffic conditions, encoding the real-world map, and the training speed. Therefore, we propose a generic Multi-Agent Collaborative Navigation System (MACNS) to address those challenges. First, we formalise the solution of the problem and challenges into a Markov Decision Process (MDP), which is further developed as a training environment where a Deep Reinforcement Learning (DRL) agent can learn patterns efficiently. Second, the proposed framework integrates a Graph Neural Network (GNN) into the policy network of Proximal Policy Optimisation for the homogeneous decision-making of each individual agent, showing excellent generalisation, extensibility and convergence speed. Finally, we demonstrate how MACNS can be applied and implemented in a real-world use case: tour groups gathering and picking up. Extensive simulations and real-world tests validate the effectiveness of the MACNS-based use case, showcasing its superiority over other state-of-the-art PPO-related methods.

Hamlet: Hierarchical Multi-Objective Reinforcement Learning Method for Charging Power Control of Electric Vehicles With Dynamic Quantity

Electric vehicle (EV) is emerging as an effective choice to reduce carbon emissions in the modern transportation system. However, the large access of EVs brings tremendous passive influence on the stability and performance of power grid operation. Thus, it is valuable to investigate the charging power management method to improve charging experience of EV drivers while maintaining normal bus voltage of the power system. This paper builds the charging power control problem of multiple EVs as a hierarchical Markov decision process (MDP) model and propose a hierarchical multi-objective reinforcement learning method (Hamlet) to obtain the real-time charging power control decisions. Specifically, by treating EVs with the same remaining charging time as the same agent, this paper addresses the dynamic state and action spaces issue and significantly reduce the input dimension of both state and action spaces. Besides, this paper quantifies drivers’ anxiety about the battery volume and distributes the comfort reward over the entire charging interval, which overcomes the delayed comfort reward issue. In order to alleviate the influence of multiple objectives on training stability, this paper develops a multi-objective learning method to dynamically adjust the optimization direction. Simulation results on IEEE 33 bus and 69 bus test feeders prove the validity of the proposed method in mitigating voltage fluctuation, minimizing bill payment and maximizing battery comfort.

A review of the problem of modeling the aerodynamics of small-sized ekranoplanes

A characteristic trend in the development of modern transport systems is the widespread introduction of unmanned technologies. One of the new vehicles that are promising for use as high-speed unmanned aerial vehicles are ekranoplanes (WIG crafts). Such devices use the principle of dynamic support above the surface. Therefore, the processes of aerodynamics are decisive for their reliable and effective operation. The presented work considers the problem of modeling aerodynamic processes during the movement of the vehicle near the surface. In contrast to studies in an unrestricted flow, the presence of a surface leads to a number of features that determine the need for special approaches to both physical and mathematical experiments. It is established that each of the methods can ensure the similarity of the modeled processes to the real ones within the defining limits. A brief review of methods of numerical modeling of ekranoplan aerodynamics is presented. The approaches, which based on the Navier-Stokes equations and method of discrete singularities, are considered. There are examples of calculation of the processes of wing aerodynamics herein. The advantages and disadvantages of viscous and inviscid models for research are shown.

Addressing the occupancy problem of Soekarno-Hatta Airport rail link during its first five years of operation

Airport rail links have long been acknowledged as a crucial component of the modern transportation system. Their attractiveness among air travellers stems from their convenience, speed, and environmental benefits. Despite their advantages, these services often face several occupancy problems that hinder their effectiveness and efficiency. Soekarno-Hatta airport rail link’s operation in 2018-2022 has been marked by low occupancy. This study aims to assess the realisations of several critical attributes of a successful airport rail link service according to TRB studies in the context of the Soekarno-Hatta airport rail link. In this context, it was shown that only four of the seven key attributes have met the minimal level to attain such goals. Despite numerous strategies undertaken during the period, which coincides with the COVID-19 pandemic, most fall under the operating or service adjustments category. The minimal realisations of the seven key attributes confirm the low occupancy levels, yet efforts to increase the ridership were limited during the pandemic. These findings provide avenues for a more successful transfer of operations from PT Railink to PT Kereta Commuter Indonesia with the clear intention of boosting the rail link’s ridership. Alongside several expansion plans by the Directorate General of Railways, the findings shall help public policymakers promote a modal shift and pave the way towards a broader integration with other modes of public transportation in the Jabodetabek region.

Optimizing Multimodal Transport to Achieve Carbon Neutrality

Shaanxi’s government has issued a circular on optimizing and adjusting the transport structure for multimodal transport development (2022–2025). The circular involves implementing structural reform policies for the supply side of transport logistics, optimizing Shaanxi’s multimodal transport structure, promoting the integration of resources of the Shaanxi transport organization, and strengthening the coordination with regional development. As a result, a modern logistics and transport system that is green, safe, convenient, efficient, and economical, reduces carbon dioxide emissions, and contributes to carbon neutrality can be established. This paper includes an analysis of the general situation of multimodal transport in Shaanxi Province and the existing problems in railway transport, and several countermeasures are proposed.

Challenges of the Integration of Micromobility Vehicles into Modern Traffic and Transportation Systems

This paper presents the main challenges of integrating micromobility vehicles into modern traffic and transportation systems. Although micromobility seems to be an effective concept for the first and last mile, the reality points to the potential problems that the integration of micromobility vehicles can create and that must be resolved appropriately. Micromobility vehicles are characterised by extensive development, which is not accompanied by appropriate legal regulations. The street design has its spatial limitations and usually separates non-motorised and motorised users, which is a notion that could be disrupted by new micromobility options. When it comes to Serbia, the existing legislation does not recognise the majority of micromobility vehicles, which results in the lack of safety of these participants and their place in the street profile. The aim of this paper is to provide guidelines for improving the existing regulations and integrating these vehicles into the traffic system of Serbia, with special reference to general recommendations through which micromobility vehicles can be treated in other countries. The results of this paper can be useful to decision-makers but also to all other participants in the process of developing effective policies and strategies for the integration of micromobility vehicles into traffic and transportation systems.

Integration of Electric Vehicles (EVs) with Electrical Grid and Impact on Smart Charging

Integrating Electric Vehicles (EVs) with the electrical grid is a pivotal aspect of modern transportation systems. This integration poses multifaceted challenges and opportunities, influencing the grid's stability, energy management, and environmental sustainability. Smart charging solutions emerge as a crucial mechanism to address these challenges by optimizing charging patterns, balancing grid demand, and maximizing renewable energy utilization. This abstract delves into the impacts of EV-grid integration, exploring the interplay between smart charging solutions and grid dynamics while considering the implications for energy infrastructure, user behavior, and environmental impact. It also provides a concise overview of EV grid integration's key issues. It highlights the crucial role of smart charging technologies in addressing them and paving the way for a sustainable future of transportation and energy.

The role of artificial intelligence in the development of rail transport

Artificial intelligence plays a revolutionary role in modern transport systems. The article discusses the role of artificial intelligence in railway transport and its potential impact on the sector. This article presents different types of artificial intelligence technologies used in this sector, explores the advantages of artificial intelligence in this field, and discusses the challenges associated with using artificial intelligence in rail transport. Artificial Intelligence is revolutionary in rail transport systems by enhancing efficiency, safety, and overall performance. There are several ways in which AI influences rail transport and its impact on the cognitive load of human resources. These factors are examined in this article.

A neighborhood comprehensive learning particle swarm optimization for the vehicle routing problem with time windows

Vehicle routing problem with time windows (VRPTW), which is a typical NP-hard combinatorial optimization problem, plays an important role in modern logistics and transportation systems. Recent years, heuristic and meta-heuristic algorithms have attracted many researchers’ attentions to solve the VRPTW problems. As an outstanding meta-heuristic algorithm, particle swarm optimization (PSO) algorithm exhibits very promising performance on continuous problems. However, how to adapt PSO to efficiently deal with VRPTW is still challenging work. In this paper, we propose a neighborhood comprehensive learning particle swarm optimization (N-CLPSO) to solve VRPTW. To improve the exploitation capability of N-CLPSO, we introduce a new remove-reinsert neighborhood search mechanism, which consists of the removed operator and the reinsert operator. When performing the removed operator, the probability of adjacency between two customers is calculated by an information matrix (IM), which is constructed based on the customers’ time-space information and elite individuals’ local information. When executing the reinsert operator, the IM and a cost matrix (CM), which is introduced to record the cost of customer insertion, are used to find an optimal insert position. Moreover, to enhance the exploration of N-CLPSO, a semi-random disturbance strategy is proposed, in which elites’ longest common sequences (LCS) are saved, aiming to prevent population degradation. The N-CLPSO algorithm is tested on 56 Solomon benchmark instances, and it attains the optimal solutions on 29 instances. The simulation results and comparison results illustrate that the proposed algorithm outperforms or can compete with the majority of other 3 PSO variants as well as other 12 state-of-the-art algorithms.

A Review of Non-Destructive Techniques for Lithium-Ion Battery Performance Analysis

Lithium-ion batteries are considered the most suitable option for powering electric vehicles in modern transportation systems due to their high energy density, high energy efficiency, long cycle life, and low weight. Nonetheless, several safety concerns and their tendency to lose charge over time demand methods capable of determining their state of health accurately, as well as estimating a range of relevant parameters in order to ensure their safe and efficient use. In this framework, non-destructive inspection methods play a fundamental role in assessing the condition of lithium-ion batteries, allowing for their thorough examination without causing any damage. This aspect is particularly crucial when batteries are exploited in critical applications and when evaluating the potential second life usage of the cells. This review explores various non-destructive methods for evaluating lithium batteries, i.e., electrochemical impedance spectroscopy, infrared thermography, X-ray computed tomography and ultrasonic testing, considers and compares several aspects such as sensitivity, flexibility, accuracy, complexity, industrial applicability, and cost. Hence, this work aims at providing academic and industrial professionals with a tool for choosing the most appropriate methodology for a given application.

Convolutional Neural Networks Adapted for Regression Tasks: Predicting the Orientation of Straight Arrows on Marked Road Pavement Using Deep Learning and Rectified Orthophotography

Arrow signs found on roadway pavement are an important component of modern transportation systems. Given the rise in autonomous vehicles, public agencies are increasingly interested in accurately identifying and analysing detailed road pavement information to generate comprehensive road maps and decision support systems that can optimise traffic flow, enhance road safety, and provide complete official road cartographic support (that can be used in autonomous driving tasks). As arrow signs are a fundamental component of traffic guidance, this paper aims to present a novel deep learning-based approach to identify the orientation and direction of arrow signs on marked roadway pavements using high-resolution aerial orthoimages. The approach is based on convolutional neural network architectures (VGGNet, ResNet, Xception, and DenseNet) that are modified and adapted for regression tasks with a proposed learning structure, together with an ad hoc model, specially introduced for this task. Although the best-performing artificial neural network was based on VGGNet (VGG-19 variant), it only slightly surpassed the proposed ad hoc model in the average values of the R2 score, mean squared error, and angular error by 0.005, 0.001, and 0.036, respectively, using the training set (the ad hoc model delivered an average R2 score, mean squared error, and angular error of 0.9874, 0.001, and 2.516, respectively). Furthermore, the ad hoc model’s predictions using the test set were the most consistent (a standard deviation of the R2 score of 0.033 compared with the score of 0.042 achieved using VGG19), while being almost eight times more computationally efficient when compared with the VGG19 model (2,673,729 parameters vs VGG19′s 20,321,985 parameters).

Multi-Objective Routing Optimization in Electric and Flying Vehicles: A Genetic Algorithm Perspective

The advent of electric and flying vehicles (EnFVs) has brought significant advancements to the transportation industry, offering improved sustainability, reduced congestion, and enhanced mobility. However, the efficient routing of messages in EnFVs presents unique challenges that demand specialized algorithms to address their specific constraints and objectives. This study analyzes several case studies that investigate the effectiveness of genetic algorithms (GAs) in optimizing routing for EnFVs. The major contributions of this research lie in demonstrating the capability of GAs to handle complex optimization problems with multiple objectives, enabling the simultaneous consideration of factors like energy efficiency, travel time, and vehicle utilization. Moreover, GAs offer a flexible and adaptive approach to finding near-optimal solutions in dynamic transportation systems, making them suitable for real-world EnFV networks. While GAs show promise, there are also limitations, such as computational complexity, difficulty in capturing real-world constraints, and potential sub-optimal solutions. Addressing these challenges, the study highlights several future research directions, including the integration of real-time data and dynamic routing updates, hybrid approaches with other optimization techniques, consideration of uncertainty and risk management, scalability for large-scale routing problems, and enhancing energy efficiency and sustainability in routing. By exploring these avenues, researchers can further improve the efficiency and effectiveness of routing algorithms for EnFVs, paving the way for their seamless integration into modern transportation systems.

Digital Infrastructure Quality Assessment System Methodology for Connected and Automated Vehicles

The rapid integration of Connected and Automated Vehicles (CAVs) into modern transportation systems necessitates a robust and systematic approach to assess the quality of the underlying digital infrastructure. In the presented work, we propose a methodology and evaluation of framework that can be used to assess digital infrastructure segments based on their readiness for the deployment of CAVs. The methodology encompasses a comprehensive framework that collects, processes, and evaluates diverse data sources, including real-time traffic, communication, and environmental data. The proposed framework is developed based on experimental data and provides a systematic approach to assess infrastructure readiness for CAVs. The proposed methodology is applied in a system for detecting the readiness status of digital infrastructure from a Cooperative, Connected, and Automated Mobility (CCAM) perspective. The system can determine the percentage of non-compliance of technical service requirements in terms of latency, bandwidth, and localization accuracy. Thanks to this, we can determine in advance in which state the current digital infrastructure is and which services can be currently operated, and thus locate the segments of the route in which the telecommunication systems need to be supported.

Performance evaluation of the cloud computing application for IoT-based public transport systems

The object of research is cloud computing as an element of the server infrastructure for intelligent public transport systems. Given the increasing complexity and requirements for modern transportation, the application of the Internet of Things concept has a high potential to improve efficiency and passenger comfort. Since the load generated in IoT systems is dynamic and difficult to predict, the use of traditional infrastructure with dedicated servers is suboptimal. This study considers the use of cloud computing as the main server infrastructure for the above systems. The paper investigates the main cloud platforms that can be used to develop such systems and evaluates their advantages and disadvantages. The authors developed the overall architecture of the system and evaluated the performance and scalability of individual components of the server infrastructure. To test the system, a software emulator was developed that simulates the controller module installed in vehicles. Using the developed emulator, stress tests were conducted to analyze and confirm the ability to scale and process input data by the proposed architecture. The test scenarios were developed and conducted on the basis of the existing public transportation system in Kyiv, Ukraine. The experimental results showed that the proposed IoT architecture is able to scale efficiently according to the load generated by the connected devices. It has been found that when the number of incoming messages increases from 40 to 6000, the average message processing time remains unchanged, and the error rate does not increase, which is an indicator of stable system operation. The obtained results can be used in the development of modern public transport systems, as well as for the modernization of existing ones

Train schedule optimization for commuter-metro networks

The interconnection and synchronization among different transport modes have been more and more attractive as the modern transportation system is moving towards Mobility-as-a-Service. In this study, we address the train scheduling problem for “commuter rail-metro” systems, where the trains from commuter rail lines can go directly into metro systems to provide seamless services for passengers. To optimize the schedule of trains for both commuter rail lines and metro lines, we propose a job shop scheduling model where precedence constraints from commuter-metro networks are taken into account and develop a mixed-integer programming (MIP) model with quadratic constraints. Our model considers the orders of different types of trains and the safety constraints, due to different types of signalling equipment in commuter and metro systems. Since these constraints involve a set of IF-THEN rules, we prove that these constraints can be equivalently reformulated as linear inequalities, without adding new variables. To solve the proposed model efficiently, we design an iterative solution framework, which generates a feasible solution using dynamic programming, next solves a MIP model, then calculates the train speed profiles, and if train speed profiles violate the safety constraints, re-optimizes the MIP model with modified alternative constraints. To verify the effectiveness of the proposed approaches, numerical experiments are performed on small and real-world instances based on the Beijing metro Line 1 and the Batong Line operational data.

Spatial–Temporal Analysis of Vehicle Routing Problem from Online Car-Hailing Trajectories

With the advent of the information age and rapid population growth, the urban transportation environment is deteriorating. Travel-route planning is a key issue in modern sustainable transportation systems. When conducting route planning, identifying the spatiotemporal disparities between planned routes and the routes chosen by actual drivers, as well as their underlying reasons, is an important method for optimizing route planning. In this study, we explore the spatial–temporal differences between planned routes and actual routes by studying the popular roads which are avoided by drivers (denoted as: PRAD) from car-hailing trajectories. By applying an improved Hidden Markov Model (HMM) map-matching algorithm to the original trajectories, we obtain the Origin-Destination (OD) matrix of vehicle travel and its corresponding actual routes, as well as the planned routes generated by the A* routing algorithm. We utilize the Jaccard index to quantify the similarity between actual and planned routes for the same OD pairs. The causes of PRADs are detected and further analyzed from the perspective of traffic conditions. By analyzing ride-hailing trajectories provided by DiDi, we examine the route behavior of drivers in Wuhan city on weekdays and weekends and discuss the relationship between traffic conditions and PRADs. The results indicate that the average accuracy of GNSS trajectory point-to-road map-matching reaches 88.83%, which is approximately 12% higher than the accuracy achieved by the HMM map-matching method proposed by Hu et al. Furthermore, the analysis of PRAD causes reveals that PRADs occurring on weekdays account for approximately 65% and are significantly associated with traffic congestion and accidents during that time. The findings of this study provide insights for future research on sustainable transportation systems and contribute to the development of improved route-planning strategies.