Hasil untuk "Highway engineering. Roads and pavements"

Mark Looi

The rapid advance of Generative AI into software development prompts this empirical investigation of perceptual effects on practice. We study the usage patterns of 147 professional developers, examining perceived correlates of AI tools use, the resulting productivity and quality outcomes, and developer readiness for emerging AI-enhanced development. We describe a virtuous adoption cycle where frequent and broad AI tools use are the strongest correlates of both Perceived Productivity (PP) and quality, with frequency strongest. The study finds no perceptual support for the Quality Paradox and shows that PP is positively correlated with Perceived Code Quality (PQ) improvement. Developers thus report both productivity and quality gains. High current usage, breadth of application, frequent use of AI tools for testing, and ease of use correlate strongly with future intended adoption, though security concerns remain a moderate and statistically significant barrier to adoption. Moreover, AI testing tools' adoption lags that of coding tools, opening a Testing Gap. We identify three developer archetypes (Enthusiasts, Pragmatists, Cautious) that align with an innovation diffusion process wherein the virtuous adoption cycle serves as the individual engine of progression. Our findings reveal that organizational adoption of AI tools follows such a process: Enthusiasts push ahead with tools, creating organizational success that converts Pragmatists. The Cautious are held in organizational stasis: without early adopter examples, they don't enter the virtuous adoption cycle, never accumulate the usage frequency that drives intent, and never attain high efficacy. Policy itself does not predict individuals' intent to increase usage but functions as a marker of maturity, formalizing the successful diffusion of adoption by Enthusiasts while acting as a gateway that the Cautious group has yet to reach.

Jingyue Li, André Storhaug

With the advancement of Agentic AI, researchers are increasingly leveraging autonomous agents to address challenges in software engineering (SE). However, the large language models (LLMs) that underpin these agents often function as black boxes, making it difficult to justify the superiority of Agentic AI approaches over baselines. Furthermore, missing information in the evaluation design description frequently renders the reproduction of results infeasible. To synthesize current evaluation practices for Agentic AI in SE, this study analyzes 18 papers on the topic, published or accepted by ICSE 2026, ICSE 2025, FSE 2025, ASE 2025, and ISSTA 2025. The analysis identifies prevailing approaches and their limitations in evaluating Agentic AI for SE, both in current research and potential future studies. To address these shortcomings, this position paper proposes a set of guidelines and recommendations designed to empower reproducible, explainable, and effective evaluations of Agentic AI in software engineering. In particular, we recommend that Agentic AI researchers make their Thought-Action-Result (TAR) trajectories and LLM interaction data, or summarized versions of these artifacts, publicly accessible. Doing so will enable subsequent studies to more effectively analyze the strengths and weaknesses of different Agentic AI approaches. To demonstrate the feasibility of such comparisons, we present a proof-of-concept case study that illustrates how TAR trajectories can support systematic analysis across approaches.

Ahmed Bahaaulddin A. Alwahhab, Vian Sabeeh, Ali Abdulmunim Ibrahim Al-kharaz

Roads and highways represent a crucial lifeline between communities in all countries. They have to be healthy enough for safe and effective transportation. The traditional ways of inspecting roads by human inspectors consume time, and the inspection results may be subjective. For this reason, researchers are motivated to automate pavement distress detection to help the road monitoring and maintenance process. Additionally, many researchers have tried to present models to detect distress on road infrastructure. However, these models face accuracy challenges and overfitting because of the nature and complications of distress images. This paper proposes a model that combines pre-trained VGG16 with a multi-head attention layer. The proposed paradigm began with smoothing as a pre-processing step to eliminate the granular effect of the asphalt gravel and make asphalt damage more distinct. Then, data augmentation was conducted to improve model generalization by adding various distress scenes to the dataset in geometric, color, and intensity cases. This work also contributes to the broader body of research by collecting a local dataset that contains three types of asphalt distress (cracks, potholes, and ruts). The proposed model was tested using three benchmarked datasets in addition to the locally collected one, and it showed efficiency in detecting asphalt distress using offline and real-time images. The model achieved an accuracy 1.00 in the Pavmentscapes dataset, outperforming the UNET model, and a fully connected network was trialed with the same dataset. With the Deep Crack dataset, our model scored an accuracy of 1.00. In contrast, ResNet achieved an accuracy of 0.72 on the same dataset. The NHA12D dataset was also used to test the proposed model and achieved an accuracy of 1.00, but the VGG16 without an attention layer used on that dataset scored only 0.64. All previous obvious tests prove that the proposed VGG16 and multi-head attention paradigm outperform the earlier models. Additionally, the proposed model has undergone a real-time test on local roads. The future directions are to try to make the self-attention mechanism more explainable and implement an attention layer for multi-scales.

Mohammed Latif Siddiq, Arvin Islam-Gomes, Natalie Sekerak et al.

Reproducibility is a cornerstone of scientific progress, yet its state in large language model (LLM)-based software engineering (SE) research remains poorly understood. This paper presents the first large-scale, empirical study of reproducibility practices in LLM-for-SE research. We systematically mined and analyzed 640 papers published between 2017 and 2025 across premier software engineering, machine learning, and natural language processing venues, extracting structured metadata from publications, repositories, and documentation. Guided by four research questions, we examine (i) the prevalence of reproducibility smells, (ii) how reproducibility has evolved over time, (iii) whether artifact evaluation badges reliably reflect reproducibility quality, and (iv) how publication venues influence transparency practices. Using a taxonomy of seven smell categories: Code and Execution, Data, Documentation, Environment and Tooling, Versioning, Model, and Access and Legal, we manually annotated all papers and associated artifacts. Our analysis reveals persistent gaps in artifact availability, environment specification, versioning rigor, and documentation clarity, despite modest improvements in recent years and increased adoption of artifact evaluation processes at top SE venues. Notably, we find that badges often signal artifact presence but do not consistently guarantee execution fidelity or long-term reproducibility. Motivated by these findings, we provide actionable recommendations to mitigate reproducibility smells and introduce a Reproducibility Maturity Model (RMM) to move beyond binary artifact certification toward multi-dimensional, progressive evaluation of reproducibility rigor.

Gerald F. Voigt, M.J. Knutson

The development and selection of the preferred 4R strategy—Resurfacing, Restoration, Recycling, and Reconstruction—are vital to maintaining the structural integrity and functionality of pavements while optimizing costs. Since the Federal-Aid Highway Acts of 1976 and 1981, the focus has shifted towards rehabilitating existing pavements rather than constructing new ones, primarily for economic reasons. To apply a 4R technique effectively, a detailed project survey is essential to gather comprehensive design, traffic, environmental, and distress/condition data. This enables the design engineer to accurately assess the deterioration extent and causes, facilitating the development of cost-effective rehabilitation strategies. Evaluation of pavements incorporates all collected data to narrow down the most efficient solutions by addressing the causes of deterioration rather than merely its symptoms. The selection of the appropriate 4R option hinges on understanding each technique's unique design details and construction requirements, aimed at restoring the pavement to an acceptable condition. The decision-making process, grounded in engineering analysis, evaluates structural adequacy, material deterioration, drainage conditions, and functional adequacy to ensure the longevity of the pavement. Life-cycle cost analysis (LCA) emerges as the cornerstone in choosing the most cost-effective 4R strategy by equating present and future costs while considering the effects of inflation and interest rates. It emphasizes the importance of selecting a real interest rate that reflects long-term economic trends, avoiding biases towards alternatives based on initial costs alone. The comprehensive approach outlined stresses the need for detailed project surveys, evaluations, and considering non-pavement factors in the development of 4R strategies, ensuring the rehabilitation efforts are both effective and economical. This methodological approach ensures the sustainable management of pavement infrastructure, maximizing the use of available resources while maintaining road safety and functionality. (Abstract generated by AI tool ChatGPT 4)

Peng Zhang

Highway asphalt pavements are subject to mechanical stress, deformation, and environmental interactions that lead to damage such as ruts, cracks, water infiltration, and depressions. The role of biomass materials in diagnosing and repairing these damages is explored in this research, emphasizing the integration of advanced analytical methods and bio-based repair technologies. The research begins by analyzing the mechanical and environmental factors contributing to pavement degradation, with a focus on the potential of biomass additives to mitigate these effects. Using the Analytic Hierarchy Process (AHP), road condition indices and damage metrics were quantitatively assessed before and after repair on a section of the Shanghai-Suzhou Expressway. Post-repair results demonstrated a 30-point reduction in the road damage index, highlighting the effectiveness of biomass materials in enhancing pavement functionality and durability. This study underscores the value of sustainable material principles and diagnostic frameworks for optimizing repair strategies. The findings provide actionable insights into leveraging bio-based materials to improve pavement engineering practices and support sustainable infrastructure maintenance.

Wael A. Altabey

Long-term pavement performance is a key topic in highway engineering. By diving deep into research on pavement systems, we can bring together past, fragmented knowledge and experiences into a solid, comprehensive engineering theory. This essentially helps guide practical work like pavement design, construction, maintenance, and management. In this research, we look at using a mentoring system for automatic monitoring of pavement performance. By placing various sensors in different positions like the road surface, base, and slopes, a sensor network powered by Internet of Things technology is created. This setup allows for accurate and ongoing observation of factors like weather, physical condition, mechanical responses, and structural changes. Given the large volume of data and the need for real-time analysis, a data from sensors measuring temperature, humidity, pressure, asphalt strain, and displacement are used to train a deep learning model based on a Convolutional Neural Network (CNN) algorithm. This model helps predict multi-point displacement in the pavement, which allows us to detect issues like pavement damage. Impressively, the CNN model achieved accuracy, regression rates, and F-score of 93.51%, 91.63%, and 90.64% respectively. To improve the experimental section of a deep learning study, we compared the performance of the proposed model against several established or simpler algorithms (baselines) in the literature such as K-Nearest Neighbors (K-NN), eXtreme Gradient Boosting (XGBoost), and support vector machine (SVM). This contextualizes the model's efficacy and demonstrates its advantage over existing methods. This study showcases how different sensors can support deep learning algorithms in the assessment of pavement performance over the long term.

Bentao Zhou, Yuan-Fu Yao, Xiaoke Geng et al.

Cement-treated large-size macadam base (CTB–50) has a high modulus, high strength, and good durability, which can increase the paving and rolling thickness, reduce the base layers, and enhance the overall structure of the pavement structure. However, there are no studies conducted on the mechanical response of asphalt pavement with a CTB–50 base course such that it can be promoted and applied in pavement engineering using CTB–50. This study analyzed the mechanical response and fatigue life of asphalt pavement structures with different base courses. Subsequently, the typical pavement structure form of asphalt pavement with a CTB–50 base course was recommended, and its effectiveness was verified through two highway engineering projects. The results showed that the base structure reduced from a three-layer CTB–30 base course structure to a two-layer CTB–50 base course structure, and the base layer bottom tensile stress of the asphalt pavement with CTB–50 base course is reduced by 5% compared to that of the asphalt pavement with CTB–30 base course. Based on the principle of equivalent fatigue life, the CTB–50 base layer thickness of the asphalt pavement can be reduced by approximately 6 cm compared to that of the CTB–30 base layer. The recommended pavement structure can reduce one layer in the construction of the base layer and improve the integrity of the asphalt pavement structure. The experimental road paved with the recommended CTB–50 base course pavement structure showed no evident pavement disease, whereas the road section with the CTB–30 base course showed early crack diseases in the asphalt pavement.

Yazhou Qin, Yansong Cui

This study addresses the challenge of accurately correlating the bridge natural frequency with influencing factors during ambient vibration by analysing on-site monitored data. This knowledge gap arises from the combined uncertainties of environmental factors and monitoring equipment noise. To tackle this challenge, the Fourier synchrosqueezed transform technique is employed and validated first by the simulated signal, as well as the Welch method. Then the instantaneous frequency of recorded acceleration at the real bridge is tracked, and a distinct diurnal pattern in the natural frequency is revealed. Then the two-stage strategy is adopted for the regression analysis. Firstly, the regression models between the normalised vibration intensity and the normalised frequency change of the vertical mode are established. Building upon these results, the additional factor, namely the effective wind speed, is considered in the second stage. The multiple linear regression model is established between the natural frequency change, the vibration intensity, and the effective wind speed. A thorough comparison of the results from both regression models reveals in-depth statistical insights. This study confirms that vibration intensity has a negative effect on the bridge natural frequency, i.e., higher vibration intensity leads to a decrease in natural frequency. Besides, the study also shows that while the effective wind speed has a statistically significant impact on the frequency change of the vertical modes, vibration intensity (caused by traffic loads) appears to be a more dominant factor.

Alessio Musco, Giulia Tarsi, Piergiorgio Tataranni et al.

Many industrial sectors exploit fossil sources to develop useful and necessary materials for our needs, such as bituminous paving materials. Bitumen, a key component of asphalt mixtures, is derived from oil refining and its properties are influenced by the crude oil source and refining process, resulting in a significant carbon footprint. With growing awareness of resource depletion and environmental concerns, pavement researchers are exploring sustainable alternatives to reduce dependence on fossil sources. This includes a rising trend in using renewable materials like biomasses to produce bio-based binders as substitutes for bitumen, aiming for a more sustainable approach. Biomasses, including vegetal and animal wastes, and waste cooking oils, as substitutes for crude oil in the production of bio-binders. Through thermochemical conversion (TCC), such as pyrolysis, biomasses can be converted into bio-char and bio-oils, which can replace fossil-based components in binders. Researchers have utilized these bio-products to reduce the dependency on fossil fuels in binders. However, there are no set minimum requirements for bio-components in bio-based binders. As the percentage of replaced bitumen increases, various types of binders are produced, including modified bitumen, extended bitumen, and alternative binders, where the fossil replacement is gradual. Overall rheological tests on bio-binders, reveal that those containing bio-char exhibit increased viscosity, stiffness, rutting resistance, and sometimes antioxidant properties. Conversely, bio-binders with bio-oils as bitumen substitutes show poorer performance at high temperatures but improved behavior at low temperatures. These results suggest that bio-binders could provide versatile solutions for various climatic and loading conditions in road construction. However, the development of pavement mixtures based on bio-binders has not been studied in depth and requires further attention to unlock its full potential. As sustainability considerations, including life cycle assessments (LCA) and life cycle cost analyses (LCC), are crucial aspects for future studies. It is essential not only to collect data on the performance characteristics of bio-binders but also to understand their environmental impact and recyclability. In-depth evaluations using methods such as LCA and LCC will provide valuable insights into the overall sustainability and long-term viability of these products.

I Made Sutrisna Ari Kesuma, Arief Setiawan Budi Nugroho, Akhmad Aminullah

Pekerjaan peningkatan jalan menjadi suatu kebutuhan yang tidak dapat dielakkan guna mendapatkan infrastruktur transportasi yang lebih handal. Dukungan perencanaan anggaran dan estimasi biaya yang baik oleh karenanya harus dilakukan. Model persamaan prediksi anggaran dan biaya dengan Artificial Neural Network (ANN) menjadi alternatif solusinya. ANN menuntut rancangan arsitektur jaringan yang tepat guna memperoleh model dengan tingkat akurasi yang tinggi. Penelitian ini bertujuan mengetahui jumlah efektif neuron dalam hidden layer yang memberikan hasil model persamaan ANN dengan tingkat akurasi tinggi dengan nilai Mean Absolute Percentage Error (MAPE) kecil. Pengembangan model didasarkan pada 33 data pekerjaan peningkatan jalan aspal di Provinsi Daerah Istimewa Yogyakarta dari tahun 2010 sampai dengan tahun 2021. Delapan belas variabel proyek yang berpengaruh signifikan terhadap total biaya pekerjaan digunakan sebagai data input model ANN dan dianalisis dengan berbagai variasi data model dan validator. Hasil penelitian menunjukkan bahwa variasi jumlah neuron dalam hidden layer menghasilkan nilai MAPE dengan pola tidak beraturan yang mana tingkat akurasi sangat dipengaruhi oleh data input dan validator. Namun demikian secara umum model dengan jumlah neuron dalam hidden layer 11/­3 kali lipat dari jumlah variabel input menjanjikan hasil akurasi paling tinggi.

Maria Chiara Cavalli, De Chen, Qian Chen et al.

As a vital and integral component of transportation infrastructure, pavement has a direct and tangible impact on socio-economic sustainability. In recent years, an influx of groundbreaking and state-of-the-art materials, structures, equipment, and detection technologies related to road engineering have continually and progressively emerged, reshaping the landscape of pavement systems. There is a pressing and growing need for a timely summarization of the current research status and a clear identification of future research directions in these advanced and evolving technologies. Therefore, Journal of Road Engineering has undertaken the significant initiative of introducing a comprehensive review paper with the overarching theme of “advanced road materials, structures, equipment, and detection technologies”. This extensive and insightful review meticulously gathers and synthesizes research findings from 39 distinguished scholars, all of whom are affiliated with 19 renowned universities or research institutions specializing in the diverse and multidimensional field of highway engineering. It covers the current state and anticipates future development directions in the four major and interconnected domains of road engineering: advanced road materials, advanced road structures and performance evaluation, advanced road construction equipment and technology, and advanced road detection and assessment technologies.

Elizabeth Bjarnason, Mirko Morandini, Markus Borg et al.

The RET (Requirements Engineering and Testing) workshop series provides a meeting point for researchers and practitioners from the two separate fields of Requirements Engineering (RE) and Testing. The goal is to improve the connection and alignment of these two areas through an exchange of ideas, challenges, practices, experiences and results. The long term aim is to build a community and a body of knowledge within the intersection of RE and Testing, i.e. RET. The 2nd workshop was held in co-location with ICSE 2015 in Florence, Italy. The workshop continued in the same interactive vein as the 1st one and included a keynote, paper presentations with ample time for discussions, and a group exercise. For true impact and relevance this cross-cutting area requires contribution from both RE and Testing, and from both researchers and practitioners. A range of papers were presented from short experience papers to full research papers that cover connections between the two fields. One of the main outputs of the 2nd workshop was a categorization of the presented workshop papers according to an initial definition of the area of RET which identifies the aspects RE, Testing and coordination effect.

Jorge E. Pesantez, Adam Behr, E. Sciaudone

This work considers a database of pre-storm morphological factors and documented impacts along a coastal roadway. Impacts from seven storms, including sand overwash and pavement damage, were documented via aerial photography. Pre-storm topography was examined to parameterize the pre-storm morphological factors likely to control whether stormwater levels and waves impact the road. Two machine learning techniques, K-nearest neighbors (KNN) and ensemble of decision trees (EDT), were employed to identify the most critical pre-storm morphological factors in determining the road vulnerability, expressed as a binary variable to impact storms. Pre-processing analysis was conducted with a correlation analysis of the predictors’ data set and feature selection subroutine for the KNN classifier. The EDTs were built directly from the data set, and feature importance estimates were reported for all storm events. Both classifiers report the distances from roadway edge-of-pavement to the dune toe and ocean as the most important predictors of most storms. For storms approaching from the bayside, the width of the barrier island was the second most important factor. Other factors of importance included elevation of the dune toe, distance from the edge of pavement to the ocean shoreline, shoreline orientation (relative to predominant wave angle), and beach slope. Compared to previously reported optimization techniques, both machine learning methods improved using pre-storm morphological data to classify highway vulnerability based on storm impacts.

Yangzezhi Zheng, Yang Zhou, Xiaoming Huang et al.

Magnesium phosphate cement (MPC) cementitious material is a phosphate cement-based material with strength formed by a serious of acid-base neutralization reactions among magnesium oxide, phosphate retarder and water, which has a high early strength and a broad application prospect in the field of pavement rehabilitation. This review collects and organizes the latest progress in the field of research on the influencing factors of mechanical properties of magnesium phosphate cementitious materials worldwide in recent years, and discusses the possibilities of application in airport engineering.The type of phosphate has a great influence on the reaction products, and the strength of the reaction products of ammonium salt is higher. Borax is the most commonly used retarder, and the retarding effect is related to the ratio of boron to magnesium. However, borax retarders have an adverse effect on the strength of MPC. In terms of the influence of mineral admixtures on the properties of MPC, fly ash, silica fume and metakaolin, as common mineral admixtures, have a positive influence on the mechanical properties of MPC, but the mechanism and degree of the influence of the three materials on the strength of MPC are slightly different; Aggregates can also improve the volume stability and mechanical properties of MPC by forming skeleton structure and slowing down the exothermic reaction. In fiber reinforced MPC matrix, steel fiber is the most widely used and the bonding performance between special-shaped steel fiber and MPC matrix is higher than that of straight fiber; basalt fiber has also been proved to be used to improve the mechanical properties of MPC system.

Mohammadjavad Kazemi, Hainian Wang, Elham Fini

Summary: Bio-based and nature-inspired solutions have been investigated recently to develop sustainable, resilient, and durable construction including but not limited to roadway infrastructures. This paper reviews state-of-the-art studies on self-healing, self-cleaning and self-rejuvenating asphalt, and concrete construction. This review draws three conclusions. (1) Self-healing construction materials have the potential to significantly extend the service life of construction elements. Urban and industrial wastes such as food waste, biomass, metals have been used to create self-healing construction materials that are more environmentally friendly. (2) Self-cleaning construction materials not only remove pollution by repelling water on their superhydrophobic surface, but also cut building and infrastructure maintenance costs, while improving cities' air quality by degrading pollutants such as NOx. Pavement engineers have exploited self-cleaning characteristic to facilitate the de-icing of pavements and lengthening the service life of pavements. (3) Self-rejuvenating materials including bio-oils can revitalize materials and delay aging; bio-oils can also be used to make bio-binders, thereby reducing the need for petroleum-based binders. The optimum concentration of bio-oil for asphalt modification depends on the chemical structure of oils. Still, regardless of dosage, self-rejuvenating binders improve asphalt workability and performance at low temperatures and increase the resistance of the asphalt mix to fatigue and cracking. This review also identified critical research gaps, including (1) the lack of a reliable, unified, and standard method to accurately measure construction materials’ self-healing, self-cleaning and self-rejuvenating properties; (2) the lack of long-term field performance data to conduct comprehensive life cycle assessment and life cycle analysis; (3) the lack of accurate technoeconomic analysis to facilitate market entry of abovementioned solutions. Addressing these gaps and determining contribution of nature-inspired and bio-based technologies to a carbon neutral economy along with issuing carbon certificates can facilitate the widespread application of these technologies while promoting resource conservation and sustainability.

Zhening Huang, Weiwei Chen, Abir Al-Tabbaa et al.

Crack detection plays a key role in automated pavement inspection. Although a large number of algorithms have been developed in recent years to further boost performance, there are still remaining challenges in practice, due to the complexity of pavement images. To further accelerate the development and identify the remaining challenges, this paper conducts a comparison study to evaluate the performance of the state of the art crack detection algorithms quantitatively and objectively. A more comprehensive annotated pavement crack dataset (NHA12D) that contains images with different viewpoints and pavements types is proposed. In the comparison study, crack detection algorithms were trained equally on the largest public crack dataset collected and evaluated on the proposed dataset (NHA12D). Overall, the U-Net model with VGG-16 as backbone has the best all-around performance, but models generally fail to distinguish cracks from concrete joints, leading to a high false-positive rate. It also found that detecting cracks from concrete pavement images still has huge room for improvement. Dataset for concrete pavement images is also missing in the literature. Future directions in this area include filling the gap for concrete pavement images and using domain adaptation techniques to enhance the detection results on unseen datasets.

Christoph Treude

Recommender systems are a valuable tool for software engineers. For example, they can provide developers with a ranked list of files likely to contain a bug, or multiple auto-complete suggestions for a given method stub. However, the way these recommender systems interact with developers is often rudimentary -- a long list of recommendations only ranked by the model's confidence. In this vision paper, we lay out our research agenda for re-imagining how recommender systems for software engineering communicate their insights to developers. When issuing recommendations, our aim is to recommend diverse rather than redundant solutions and present them in ways that highlight their differences. We also want to allow for seamless and interactive navigation of suggestions while striving for holistic end-to-end evaluations. By doing so, we believe that recommender systems can play an even more important role in helping developers write better software.

Sherlock A. Licorish, Christoph Treude, John Grundy et al.

Six months ago an important call was made for researchers globally to provide insights into the way Software Engineering is done in their region. Heeding this call we hereby outline the position Software Engineering in Australasia (New Zealand and Australia). This article first considers the software development methods practices and tools that are popular in the Australasian software engineering community. We then briefly review the particular strengths of software engineering researchers in Australasia. Finally we make an open call for collaborators by reflecting on our current position and identifying future opportunities

Ashkan Behzadian, Tanner Wambui Muturi, Tianjie Zhang et al.

The Data Science for Pavement Challenge (DSPC) seeks to accelerate the research and development of automated vision systems for pavement condition monitoring and evaluation by providing a platform with benchmarked datasets and codes for teams to innovate and develop machine learning algorithms that are practice-ready for use by industry. The first edition of the competition attracted 22 teams from 8 countries. Participants were required to automatically detect and classify different types of pavement distresses present in images captured from multiple sources, and under different conditions. The competition was data-centric: teams were tasked to increase the accuracy of a predefined model architecture by utilizing various data modification methods such as cleaning, labeling and augmentation. A real-time, online evaluation system was developed to rank teams based on the F1 score. Leaderboard results showed the promise and challenges of machine for advancing automation in pavement monitoring and evaluation. This paper summarizes the solutions from the top 5 teams. These teams proposed innovations in the areas of data cleaning, annotation, augmentation, and detection parameter tuning. The F1 score for the top-ranked team was approximately 0.9. The paper concludes with a review of different experiments that worked well for the current challenge and those that did not yield any significant improvement in model accuracy.