Hasil untuk "Highway engineering. Roads and pavements"

Hao Li, Haoxiang Zhang, Ahmed E. Hassan

The future of software engineering--SE 3.0--is unfolding with the rise of AI teammates: autonomous, goal-driven systems collaborating with human developers. Among these, autonomous coding agents are especially transformative, now actively initiating, reviewing, and evolving code at scale. This paper introduces AIDev, the first large-scale dataset capturing how such agents operate in the wild. Spanning over 456,000 pull requests by five leading agents--OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code--across 61,000 repositories and 47,000 developers, AIDev provides an unprecedented empirical foundation for studying autonomous teammates in software development. Unlike prior work that has largely theorized the rise of AI-native software engineering, AIDev offers structured, open data to support research in benchmarking, agent readiness, optimization, collaboration modeling, and AI governance. The dataset includes rich metadata on PRs, authorship, review timelines, code changes, and integration outcomes--enabling exploration beyond synthetic benchmarks like SWE-bench. For instance, although agents often outperform humans in speed, their PRs are accepted less frequently, revealing a trust and utility gap. Furthermore, while agents accelerate code submission--one developer submitted as many PRs in three days as they had in three years--these are structurally simpler (via code complexity metrics). We envision AIDev as a living resource: extensible, analyzable, and ready for the SE and AI communities. Grounding SE 3.0 in real-world evidence, AIDev enables a new generation of research into AI-native workflows and supports building the next wave of symbiotic human-AI collaboration. The dataset is publicly available at https://github.com/SAILResearch/AI_Teammates_in_SE3. > AI Agent, Agentic AI, Coding Agent, Agentic Coding, Software Engineering Agent

Armin Ariamajd, Raquel López-Ríos de Castro, Andrea Volkamer

The increasing importance of Computational Science and Engineering has highlighted the need for high-quality scientific software. However, research software development is often hindered by limited funding, time, staffing, and technical resources. To address these challenges, we introduce PyPackIT, a cloud-based automation tool designed to streamline research software engineering in accordance with FAIR (Findable, Accessible, Interoperable, and Reusable) and Open Science principles. PyPackIT is a user-friendly, ready-to-use software that enables scientists to focus on the scientific aspects of their projects while automating repetitive tasks and enforcing best practices throughout the software development life cycle. Using modern Continuous software engineering and DevOps methodologies, PyPackIT offers a robust project infrastructure including a build-ready Python package skeleton, a fully operational documentation and test suite, and a control center for dynamic project management and customization. PyPackIT integrates seamlessly with GitHub's version control system, issue tracker, and pull-based model to establish a fully-automated software development workflow. Exploiting GitHub Actions, PyPackIT provides a cloud-native Agile development environment using containerization, Configuration-as-Code, and Continuous Integration, Deployment, Testing, Refactoring, and Maintenance pipelines. PyPackIT is an open-source software suite that seamlessly integrates with both new and existing projects via a public GitHub repository template at https://github.com/repodynamics/pypackit.

Blessing Agyei Kyem, Joshua Kofi Asamoah, Armstrong Aboah

The accurate detection and segmentation of pavement distresses, particularly tiny and small cracks, are critical for early intervention and preventive maintenance in transportation infrastructure. Traditional manual inspection methods are labor-intensive and inconsistent, while existing deep learning models struggle with fine-grained segmentation and computational efficiency. To address these challenges, this study proposes Context-CrackNet, a novel encoder-decoder architecture featuring the Region-Focused Enhancement Module (RFEM) and Context-Aware Global Module (CAGM). These innovations enhance the model's ability to capture fine-grained local details and global contextual dependencies, respectively. Context-CrackNet was rigorously evaluated on ten publicly available crack segmentation datasets, covering diverse pavement distress scenarios. The model consistently outperformed 9 state-of-the-art segmentation frameworks, achieving superior performance metrics such as mIoU and Dice score, while maintaining competitive inference efficiency. Ablation studies confirmed the complementary roles of RFEM and CAGM, with notable improvements in mIoU and Dice score when both modules were integrated. Additionally, the model's balance of precision and computational efficiency highlights its potential for real-time deployment in large-scale pavement monitoring systems.

Blessing Agyei Kyem, Joshua Kofi Asamoah, Anthony Dontoh et al.

Automated pavement defect detection often struggles to generalize across diverse real-world conditions due to the lack of standardized datasets. Existing datasets differ in annotation styles, distress type definitions, and formats, limiting their integration for unified training. To address this gap, we introduce a comprehensive benchmark dataset that consolidates multiple publicly available sources into a standardized collection of 52747 images from seven countries, with 135277 bounding box annotations covering 13 distinct distress types. The dataset captures broad real-world variation in image quality, resolution, viewing angles, and weather conditions, offering a unique resource for consistent training and evaluation. Its effectiveness was demonstrated through benchmarking with state-of-the-art object detection models including YOLOv8-YOLOv12, Faster R-CNN, and DETR, which achieved competitive performance across diverse scenarios. By standardizing class definitions and annotation formats, this dataset provides the first globally representative benchmark for pavement defect detection and enables fair comparison of models, including zero-shot transfer to new environments.

Leonhard Applis, Yuntong Zhang, Shanchao Liang et al.

The growth of Large Language Model (LLM) technology has raised expectations for automated coding. However, software engineering is more than coding and is concerned with activities including maintenance and evolution of a project. In this context, the concept of LLM agents has gained traction, which utilize LLMs as reasoning engines to invoke external tools autonomously. But is an LLM agent the same as an AI software engineer? In this paper, we seek to understand this question by developing a Unified Software Engineering agent or USEagent. Unlike existing work which builds specialized agents for specific software tasks such as testing, debugging, and repair, our goal is to build a unified agent which can orchestrate and handle multiple capabilities. This gives the agent the promise of handling complex scenarios in software development such as fixing an incomplete patch, adding new features, or taking over code written by others. We envision USEagent as the first draft of a future AI Software Engineer which can be a team member in future software development teams involving both AI and humans. To evaluate the efficacy of USEagent, we build a Unified Software Engineering bench (USEbench) comprising of myriad tasks such as coding, testing, and patching. USEbench is a judicious mixture of tasks from existing benchmarks such as SWE-bench, SWT-bench, and REPOCOD. In an evaluation on USEbench consisting of 1,271 repository-level software engineering tasks, USEagent shows improved efficacy compared to existing general agents such as OpenHands CodeActAgent. There exist gaps in the capabilities of USEagent for certain coding tasks, which provides hints on further developing the AI Software Engineer of the future.

Andriy Belyatynsky, Kostyantyn Mamonov, Lyudmyla Kovalenko et al.

Introduction. The relevance of the research topic is due to the need to develop measures to ensure the development of construction enterprises (BE), using modern intellectual economic systems. Problem Statement. Proposed measures to ensure the development of construction enterprises, which are aimed at the formation and implementation of intelligent economic systems, the creation of a basis for the growth of the completeness and quality of economic support, the use of geo-informational tools, the construction and improvement of the security and information system, the improvement of social security and standards. Purpose. Economic and mathematical modeling of the development of construction enterprises, taking into account the peculiarities of the formation of intelligent economic systems. Materials and methods. The article achieves the goal of economic-mathematical modeling of the integral indicator of the development of construction enterprises, taking into account the peculiarities of the formation of intelligent economic systems. Solved tasks regarding the assessment of the integral indicator of BP development; development of an economic-mathematical model of the influence of the integral factor of the formation of intellectual economic systems on the general indicator of the development of construction enterprises; formation of measures regarding the development of construction enterprises based on the results of economic and mathematical modeling of the relevant factors.

Dmytro Bespalov, Mykhailo Korol, Vitalii Tereshchuk

Introduction. In the modern world, the transport infrastructure of cities faces significant challenges related to the growth of traffic intensity, congestion and the need to ensure road safety. Among the wide range of engineering solutions and technologies aimed at solving these problems, it is worth highlighting the issue of justifying the choice of planning solutions in places of the highest concentration of traffic flows - transport hubs. International experience shows that the construction of roundabouts is one of the ways to optimize traffic, reduce congestion and improve road safety. Therefore, it is important to consider this type of planning solutions for transport hubs in terms of the feasibility of their use on the city's street and road network. Problem Statement. One of the main principles of traffic management at high-intensity intersections is the arrangement of signalized or roundabouts. In the conditions of dense urban development, the issue of justifying the choice of intersection design solutions is of particular relevance, because due to the significant cost per unit area of urban territory, its alienation for a transport infrastructure element is a very complex issue, the solution of which requires a comprehensive assessment of all options using various methods for evaluating the choice of intersection design solutions on the city road network. One of these methods is microsimulation, which can be used to calculate LOS (Level of Service), transport and operational, environmental and energy characteristics, etc. within individual elements of the road network. Despite the considerable attention paid to the design of roundabouts and regulated intersections in domestic regulatory documents and scientific research, there is currently no clear argumentation to justify the choice of their planning solutions. In this regard, it is important to assess the effectiveness of both types of planning solutions depending on changes in traffic intensity within them in order to obtain the main indicators of their performance for further consideration when justifying the choice of planning solutions for transport hubs. Purpose. Analysis of efficiency, determination of advantages and disadvantages of planning solutions of transport hubs by the type of roundabout and signalized intersection. Materials and methods. The main way to analyze the effectiveness of planning decisions is to use microsimulation using specialized software PTV Vissim.

Vladislav Kondratovič, Vytautas Palevičius, Donatas Čygas et al.

The rapid advancement of autonomous vehicle (AV) technology heralds a transformative era in mobility, promising to redefine transportation with enhanced efficiency, safety, and sustainability. Realizing this potential necessitates road ecosystem that fosters seamless interactions between AVs, infrastructure, and societal elements. This article assesses road ecosystem criterion groups tailored for AVs, encompassing critical components for their seamless operation. It addresses physical and digital infrastructure, communications, social environment and road users, and legal and economic environments. Integrating these diverse criterion groups creates a holistic framework supporting AV deployment and operation. By assessing the interplay between these groups, the study highlights the most important areas that facilitate seamless AV integration. The analysis examines the importance of current infrastructure for AVs, the effectiveness of communication systems, and the impact of social environment and road users, alongside the regulatory and economic conditions necessary for AV adoption. This article underscores the critical need for a multidisciplinary approach in shaping the future of transportation, paving the way for a seamless and sustainable transition into the era of autonomous mobility.

Volodymyr Kaskiv, Оleksii Sokolov

Introduction. The road construction industry is currently one of the strategic industries of Ukraine, and the issue of quality and availability of basic building materials for road construction is particularly topical, which is directly related to its high material intensity. The known reserves of high-quality raw materials that could be used as asphalt concrete components are constantly decreasing, so it is necessary to look for alternative sources of raw materials for construction materials and explore the possibility of their use. In this regard, the most efficient use of local raw materials is the use of industrial waste, which can be one of the solutions to the problem of shortage of raw materials of inorganic origin. Problem statement. In road construction, when repairing or arranging road pavement layers, in particular asphalt mixtures, the need for carbonate mineral fillers, which are scarce in some regions, is constantly growing. Industrial by-products can be an alternative. One of these materials is fly ash from thermal power plants, which can be used instead of mineral fillers in asphalt mixtures. Objective. To perform a feasibility study of the use of asphalt concrete layers with fly ash. Materials and Methods. Analysis of information sources and the materials market of Ukraine and calculation of the technical and economic efficiency of fly ash application in asphalt mixtures. Results. The technical and economic feasibility of using asphalt concrete layers with fly ash as a filler was calculated. Conclusions. It was found that replacing the standard filler with fly ash in the asphalt mixture reduces its cost by more than 10 %.

Ayda Kamalifar, Carlo Cenedese, Michele Cucuzzella et al.

In this paper, we propose the METANET with service station (METANET-s) model, a second-order macroscopic traffic model that, compared to the classical METANET, incorporates the dynamics of service stations on highways. Specifically, we employ the (so-called) store-and-forward links to model the stop of vehicles and the possible queue forming in the process of merging back into the highway mainstream. We explore the capability of the METANET-s to capture well both traffic back propagation and capacity drops, which are typically caused by the presence of vehicles joining again the mainstream traffic from the service station. Therefore, capturing these effects is crucial to improving the model's predictive capabilities. Finally, we perform a comparative analysis with the Cell Transmission Model with service station (CTM-s), showcasing that the METANET-s describes the traffic evolution much better than its first-order counterpart.

Paulius Paplauskas, Audrius Vaitkus, Rūta Simanavičienė

Surveying the condition of the pavement is one of the most important processes in managing the road network. The information collected during these surveys allows for the calculation of the Pavement Condition Index, which is a derivative cumulative qualitative indicator that evaluates various pavement characteristics and defects. Deterioration modelling of these measured indicators and calculated indices is a critical element and its most accurate prediction brings the process of pavement management closer to a higher quality process by more efficiently allocating funds and repair work. Many different models – both extremely complex and simple – are used in the world to simulate the condition of individual pavement indicators. However, these models are developed based on the data of a certain country or region and are not suitable in another country due to different requirements for pavement structures and other reasons. In Lithuania, measurements of the quality indicators of road surfaces with new generation survey equipment have been carried out recently but the information stored in the databases about road sections is minimal, and it becomes difficult to adapt the models applied abroad due to the missing information. The aim of this study is to create pavement condition index prediction models by evaluating such quantitative and qualitative indicators as traffic loads, road surface unevenness, type of repair, pavement age, climatic zones, and pavement construction classes.

Janusz Dyduch, Radosław Zawierucha

Abstract: The article concerns the essential conditions of the use of supervision and diagnostic systems in control and telecommunications systems. In the introduction, the factors aff ecting the correct functioning of the SRKI Systems were discussed, attention was also paid to the problem of interference. In the following part, the problem of reliability and safety of control systems, failure reporting systems, as well as technical diagnostics is characterized. Based on the research topic carried out as part of the National Center for Research and Development, solutions for a new technology for implementation on railway lines and a specifi cation of the structure of the support system were presented. Research models based on simulations, expert and statistical systems were indicated. The benefi ts of the project were indicated. Keywords: Surveillance systems; Diagnostics; rm; Control; Telecommunication

Tianpu Zhang, Weilong Ding, Mengda Xing

As one of the important tools for spatial feature extraction, graph convolution has been applied in a wide range of fields such as traffic flow prediction. However, current popular works of graph convolution cannot guarantee spatio-temporal consistency in a long period. The ignorance of correlational dynamics, convolutional locality and temporal comprehensiveness would limit predictive accuracy. In this paper, a novel Attention-based Dynamic Graph Convolutional Recurrent Neural Network (ADGCRNN) is proposed to improve traffic flow prediction in highway transportation. Three temporal resolutions of data sequence are effectively integrated by self-attention to extract characteristics; multi-dynamic graphs and their weights are dynamically created to compliantly combine the varying characteristics; a dedicated gated kernel emphasizing highly relative nodes is introduced on these complete graphs to reduce overfitting for graph convolution operations. Experiments on two public datasets show our work better than state-of-the-art baselines, and case studies of a real Web system prove practical benefit in highway transportation.

Carlo A. Furia, Richard Torkar, Robert Feldt

There is abundant observational data in the software engineering domain, whereas running large-scale controlled experiments is often practically impossible. Thus, most empirical studies can only report statistical correlations -- instead of potentially more insightful and robust causal relations. To support analyzing purely observational data for causal relations, and to assess any differences between purely predictive and causal models of the same data, this paper discusses some novel techniques based on structural causal models (such as directed acyclic graphs of causal Bayesian networks). Using these techniques, one can rigorously express, and partially validate, causal hypotheses; and then use the causal information to guide the construction of a statistical model that captures genuine causal relations -- such that correlation does imply causation. We apply these ideas to analyzing public data about programmer performance in Code Jam, a large world-wide coding contest organized by Google every year. Specifically, we look at the impact of different programming languages on a participant's performance in the contest. While the overall effect associated with programming languages is weak compared to other variables -- regardless of whether we consider correlational or causal links -- we found considerable differences between a purely associational and a causal analysis of the very same data. The takeaway message is that even an imperfect causal analysis of observational data can help answer the salient research questions more precisely and more robustly than with just purely predictive techniques -- where genuine causal effects may be confounded.

Yu Zheng, Hongyuan Su, Jingtao Ding et al.

Millions of slum dwellers suffer from poor accessibility to urban services due to inadequate road infrastructure within slums, and road planning for slums is critical to the sustainable development of cities. Existing re-blocking or heuristic methods are either time-consuming which cannot generalize to different slums, or yield sub-optimal road plans in terms of accessibility and construction costs. In this paper, we present a deep reinforcement learning based approach to automatically layout roads for slums. We propose a generic graph model to capture the topological structure of a slum, and devise a novel graph neural network to select locations for the planned roads. Through masked policy optimization, our model can generate road plans that connect places in a slum at minimal construction costs. Extensive experiments on real-world slums in different countries verify the effectiveness of our model, which can significantly improve accessibility by 14.3% against existing baseline methods. Further investigations on transferring across different tasks demonstrate that our model can master road planning skills in simple scenarios and adapt them to much more complicated ones, indicating the potential of applying our model in real-world slum upgrading. The code and data are available at https://github.com/tsinghua-fib-lab/road-planning-for-slums.

A. Bieliatynskyi, Shilin Yang, V. Pershakov et al.

Abstract The purpose of research work should be considered the practical aspects study of environmental pollution near highways with dust particles generated during repair work. The results of the study reflect the entire scope of research work carried out in order to determine the optimal composition of the concrete mixture for road repair work, which makes it possible to achieve a reduction in the emission of dust particles into the roadside environment and improve the environmental situation in the roadside. Also in this study, recommendations were proposed for the elimination of polluting factors and the elimination of negative consequences for the environment. The results and conclusions of this scientific study are of significant practical importance for road maintenance workers who professionally solve the issues of pavement repair, as well as for researchers conducting scientific research in the direction of studying environmental safety problems during road repair work.

Badrinarayan Rath

Article history: Received 10 Oct 2021 Revised 06 Feb 2022 Accepted 22 Feb 2022 Nowadays road construction is rapidly increasing on-demand to meet several medium and long terms development programs. A huge amount of natural resources, types of machinery and fuels are used in road construction. Using material resources and fuel an efficient manner, reducing in emission of greenhouse gases and controlling various impacts on the environment are important tasks in the road construction industry. In the present research, several environmental impacts related to the construction of asphalt paved highways in Ethiopia have been determined using the Life Cycle Assessment Approach for common pavement materials and construction activities. A deep focus has been given towards the extraction and processing of sand and gravel for preparation of base and sub-base; transportation of these input raw materials; consumption of fuels by various road construction machinery; direct or indirect emissions of carbon dioxide and other pollutants to atmosphere etc. Various suitable methods have been used to calculate the impacts of raw materials, fuel and machinery on various categories such as global warming potential, ozone depletion potential, terrestrial acidification potential, freshwater eutrophication, freshwater ecotoxicity etc. From the investigation, it has been suggested to use recycled materials for substituting gravel as base or sub-base materials and biodiesel for substituting diesel in the transportation trucks and dumpers. These types of new recycled materials may greatly help in assisting the evaluation of sustainable pavement construction. The present case study may help for potential changes in asphalt pavement construction to improve environmental sustainability.

Mariusz Wesołowski, Krzysztof Blacha, Agata Kowalewska

Abstract: The load-bearing capacity of natural airport surfaces directly affects the safety of air operations. Natural airport surfaces at military airports are front seat belts, work belts and side seat belts. The load-bearing capacity of the natural airport pavements must be high enough to prevent damage to the aircraft from the runway, damage to the underground infrastructure of the airport, and to enable quick restoration of the airport's operational capacity by efficient removal of the aircraft from the natural surface by airport services. That is why it is so important to have a quick and effective method of strengthening natural surfaces. The article proposes to improve the load-bearing capacity of natural airport pavements by using geogrids (airport gratings) pressed into the existing pavement. Keywords: Carrying capacity; Natural airport pavement; Safety Conducting air operations

Tomasz Nowobilski, Mariusz Szóstak

Abstract: Unmanned aerial vehicles (UAVs) are devices that are commonly used in various industries. Their availability makes them also a helpful tool for an engineer on a modern construction site. The article presents the possibility of using unmanned aerial vehicles for the inspection of the technical condition of the scaffolding with an area of approx. 1.500 m2. As a result of the conducted UAV trials, a lot of valuable information was obtained, which was then subjected to a detailed analysis in order to identify critical elements of the scaffolding that posed a threat to work safety. An additional effect of the analysis is the developed point cloud, which shows the detailed geometry of the scaffolding and enables the analysis of the deformation of the structure. Keywords: Unmanned aerial vehicle; Drone, Scaffolding; Construction industry; Occupational health and safety

Peter Berger, Michał Dąbrowski

Abstract: A typical solution for the construction of transportation infrastructure around the world is the economic adjustment of their course to the natural terrain. Hence, road and railway construction on embankments or in indentations is typical. Recent climate change is triggering extreme conditions and weather events that have a significant impact on the stability of slopes. Such disturbances may manifest themselves in gradual long-term subsidence, or in sudden, unforeseen landslides and collapses, and constitute a serious threat to human life. Keywords: Monitoring system; Slope; Embankment; Safety in railway issues