<?xml version="1.0" encoding="UTF-8"?>
<article article-type="research-article" dtd-version="1.3" xml:lang="ru" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="https://metafora.rcsi.science/xsd_files/journal3.xsd">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">moitvivt</journal-id>
      <journal-title-group>
        <journal-title xml:lang="ru">Моделирование, оптимизация и информационные технологии</journal-title>
        <trans-title-group xml:lang="en">
          <trans-title>Modeling, Optimization and Information Technology</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="epub">2310-6018</issn>
      <publisher>
        <publisher-name>Издательство</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="doi">10.26102/2310-6018/2026.53.2.009</article-id>
      <article-id pub-id-type="custom" custom-type="elpub">2210</article-id>
      <title-group>
        <article-title xml:lang="ru">Исследование неопределенности в многоагентном мониторинге дорожного покрытия</article-title>
        <trans-title-group xml:lang="en">
          <trans-title>Research on uncertainty in multi-agent road surface monitoring</trans-title>
        </trans-title-group>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0001-6192-5029</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Подберёзкин</surname>
              <given-names>Александр Александрович</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Podberezkin</surname>
              <given-names>Aleksandr Aleksandrovich</given-names>
            </name>
          </name-alternatives>
          <email>a.podberezkin@gmail.com</email>
          <xref ref-type="aff">aff-1</xref>
        </contrib>
      </contrib-group>
      <aff-alternatives id="aff-1">
        <aff xml:lang="ru">Московский автомобильно-дорожный государственный технический университет</aff>
        <aff xml:lang="en">Moscow Automobile and Road Construction State Technical University</aff>
      </aff-alternatives>
      <pub-date pub-type="epub">
        <day>01</day>
        <month>01</month>
        <year>2026</year>
      </pub-date>
      <volume>1</volume>
      <issue>1</issue>
      <elocation-id>10.26102/2310-6018/2026.53.2.009</elocation-id>
      <permissions>
        <copyright-statement>Copyright © Авторы, 2026</copyright-statement>
        <copyright-year>2026</copyright-year>
        <license license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/">
          <license-p>This work is licensed under a Creative Commons Attribution 4.0 International License</license-p>
        </license>
      </permissions>
      <self-uri xlink:href="https://moitvivt.ru/ru/journal/article?id=2210"/>
      <abstract xml:lang="ru">
        <p>Актуальность исследования обусловлена тем, что в платформах мониторинга дорожной инфраструктуры ошибки на уровне детектирования и интерпретации состояния объектов способны переходить в ошибки нормативных и управленческих решений, особенно в реальных условиях съемки (тени, блики, влажное/заснеженное покрытие, загрязнения, неоднозначные границы дефектов), где возрастает риск неверной классификации и локализации. Это критично при пороговой нормативной оценке, поскольку небольшая погрешность может привести к смене категории состояния и, как следствие, к необоснованному назначению ремонтных мероприятий либо к пропуску опасного дефекта. В связи с этим статья направлена на исследование учета неопределенности детектирования дефектов дорожного покрытия в многоагентном контуре мониторинга, где результаты наблюдений передаются между компонентами вместе с контекстом обработки через Model Context Protocol как единый протокол обмена событиями, метаданными и параметрами интерпретации. Ведущим подходом является построение вычислительного конвейера, включающего предварительную обработку видеоданных, детектирование дефектов, вычисление показателя неопределенности H(p) по распределению вероятностей классов, присвоение статуса «автоматически/валидация/уточнение», последующую нормативную интерпретацию и агрегацию по участкам дорожной сети. Для обеспечения воспроизводимости каждый прогон фиксируется как унифицированный «контекст эксперимента» (идентификатор сцены/кадра, версия модели, параметры порогов, статус решения), что позволяет сопоставимо сравнивать режимы и выполнять аудит причин расхождений. Верификация основана на сравнении нормативных решений с экспертной оценкой и анализе зависимости доли ошибочных нормативных решений от порога автоматического принятия решения по H(p), при этом риск-ориентированная логика переводит высоконеопределенные детекции в режим валидации и снижает вероятность ошибок в пограничных случаях. Показано, что протоколирование контекста через Model Context Protocol и учет H(p) повышают воспроизводимость экспериментов и обоснованность нормативной интерпретации, уменьшая риск ошибочной приоритизации ремонта за счет отделения сомнительных наблюдений и сохранения причин принятого решения.</p>
      </abstract>
      <trans-abstract xml:lang="en">
        <p>The relevance of this study is determined by the fact that, in road-infrastructure monitoring platforms, errors at the stage of detection and interpretation of object conditions can propagate into normative and managerial decision errors, especially under real-world acquisition conditions (shadows, glare, wet/snow-covered pavement, contamination, and ambiguous defect boundaries), where the risk of misclassification and inaccurate localization increases. This is critical for threshold-based normative assessment, since even small inaccuracies may change the condition category and, consequently, lead either to unjustified maintenance assignments or to missing hazardous defects. Therefore, this paper investigates the use of detection uncertainty for road-surface defect monitoring within a multi-agent pipeline, where observation results are transferred between components together with the processing context via the Model Context Protocol as a unified mechanism for exchanging events, metadata, and interpretation parameters. The main approach is to build a computational pipeline that includes video-data preprocessing, defect detection, computation of the uncertainty indicator H(p) from the class-probability distribution, assignment of the status "automatic/validation/refinement" subsequent normative interpretation, and aggregation over road-network segments. To ensure reproducibility, each run is recorded as a unified "experiment context" (scene/frame identifier, model version, threshold parameters, decision status), enabling comparable mode-to-mode evaluation and auditing of discrepancy causes. Verification is based on comparing normative decisions with expert assessment and analyzing how the share of erroneous normative decisions depends on the automatic-decision threshold for H(p), while the risk-oriented logic routes high-uncertainty detections to validation and reduces the probability of errors in borderline cases. The results show that context logging via Model Context Protocol and accounting for H(p) improve experimental reproducibility and the soundness of normative interpretation, decreasing the risk of incorrect maintenance prioritization by separating ambiguous observations and preserving the decision rationale.</p>
      </trans-abstract>
      <kwd-group xml:lang="ru">
        <kwd>многоагентная система</kwd>
        <kwd>мониторинг дорожного покрытия</kwd>
        <kwd>дефекты дорожного покрытия</kwd>
        <kwd>компьютерное зрение</kwd>
        <kwd>неопределенность детектирования</kwd>
        <kwd>нормативная интерпретация</kwd>
        <kwd>протоколирование контекста</kwd>
      </kwd-group>
      <kwd-group xml:lang="en">
        <kwd>multi agent system</kwd>
        <kwd>road surface monitoring</kwd>
        <kwd>road surface defects</kwd>
        <kwd>computer vision</kwd>
        <kwd>detection uncertainty</kwd>
        <kwd>normative interpretation</kwd>
        <kwd>context logging</kwd>
      </kwd-group>
      <funding-group>
        <funding-statement xml:lang="ru">Исследование выполнено без спонсорской поддержки.</funding-statement>
        <funding-statement xml:lang="en">The study was performed without external funding.</funding-statement>
      </funding-group>
    </article-meta>
  </front>
  <back>
    <ref-list>
      <title>References</title>
      <ref id="cit1">
        <label>1</label>
        <mixed-citation xml:lang="ru">Zheng L., Xiao J., Wang Y., et al. Deep learning-based intelligent detection of pavement distress. Automation in Construction. 2024;168. https://doi.org/10.1016/j.autcon.2024.105772</mixed-citation>
      </ref>
      <ref id="cit2">
        <label>2</label>
        <mixed-citation xml:lang="ru">Shang J., Zhang A.A., Dong Z., Zhang H., He A. Automated pavement detection and artificial intelligence pavement image data processing technology. Automation in Construction. 2024;168. https://doi.org/10.1016/j.autcon.2024.105797</mixed-citation>
      </ref>
      <ref id="cit3">
        <label>3</label>
        <mixed-citation xml:lang="ru">Yang X., Zhang J., Liu W., Jing J., Zheng H., Xu W. Automation in road distress detection, diagnosis and treatment. Journal of Road Engineering. 2024;4(1):1–26. https://doi.org/10.1016/j.jreng.2024.01.005</mixed-citation>
      </ref>
      <ref id="cit4">
        <label>4</label>
        <mixed-citation xml:lang="ru">Fani A., Golroo A., Naseri H., Mirhassani S.A., Gandomi A.H. Risk-based pavement maintenance planning considering budget and pavement deterioration uncertainty. Structure and Infrastructure Engineering. 2024;20(10):1437–1450. https://doi.org/10.1080/15732479.2022.2145317</mixed-citation>
      </ref>
      <ref id="cit5">
        <label>5</label>
        <mixed-citation xml:lang="ru">Samadzadegan F., Dadrass Javan F., Ashtari Mahini F., Gholamshahi M., Nex F. Automatic Road Pavement Distress Recognition Using Deep Learning Networks from Unmanned Aerial Imagery. Drones. 2024;8(6). https://doi.org/10.3390/drones8060244</mixed-citation>
      </ref>
      <ref id="cit6">
        <label>6</label>
        <mixed-citation xml:lang="ru">Hu Y., Chen N., Hou Y., Lin X., Jing B., Liu P. Lightweight deep learning for real-time road distress detection on mobile devices. Nature Communications. 2025;16. https://doi.org/10.1038/s41467-025-59516-5</mixed-citation>
      </ref>
      <ref id="cit7">
        <label>7</label>
        <mixed-citation xml:lang="ru">Arya D., Maeda H., Ghosh S.K., Toshniwal D., Sekimoto Y. RDD2022: A multi-national image dataset for automatic road damage detection. Geoscience Data Journal. 2024. https://doi.org/10.1002/gdj3.260</mixed-citation>
      </ref>
      <ref id="cit8">
        <label>8</label>
        <mixed-citation xml:lang="ru">He W., Jiang Zh., Xiao T., Xu Z., Li Y. A Survey on Uncertainty Quantification Methods for Deep Learning. arXiv. URL: https://arxiv.org/abs/2302.13425 [Accessed 24th December 2025].</mixed-citation>
      </ref>
      <ref id="cit9">
        <label>9</label>
        <mixed-citation xml:lang="ru">Andéol L., Fel Th., de Grancey F., Mossina L. Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling. In: Conformal and Probabilistic Prediction with Applications: Proceedings of Machine Learning Research 204, 13–15 September 2023, Limassol, Cyprus. PMLR; 2023. P. 36–55.</mixed-citation>
      </ref>
      <ref id="cit10">
        <label>10</label>
        <mixed-citation xml:lang="ru">Zhang Sh., Bei Zh., Ling T., Chen Q., Zhang L. Research on high-precision recognition model for multi-scene asphalt pavement distresses based on deep learning. Scientific Reports. 2024;14. https://doi.org/10.1038/s41598-024-77173-4</mixed-citation>
      </ref>
      <ref id="cit11">
        <label>11</label>
        <mixed-citation xml:lang="ru">Li Y., Miao N., Ma L., Shuang F., Huang X. Transformer for object detection: review and benchmark. Engineering Applications of Artificial Intelligence. 2023;126. https://doi.org/10.1016/j.engappai.2023.107021</mixed-citation>
      </ref>
      <ref id="cit12">
        <label>12</label>
        <mixed-citation xml:lang="ru">Huseljic D., Herde M., Hahn P., Müjde M., Sick B. Systematic Evaluation of Uncertainty Calibration in Pretrained Object Detectors. International Journal of Computer Vision. 2025;133:1033–1047. https://doi.org/10.1007/s11263-024-02219-z</mixed-citation>
      </ref>
      <ref id="cit13">
        <label>13</label>
        <mixed-citation xml:lang="ru">Schlegel M., Sattler K.-U. Capturing end-to-end provenance for machine learning pipelines. Information Systems. 2025;132. https://doi.org/10.1016/j.is.2024.102495</mixed-citation>
      </ref>
      <ref id="cit14">
        <label>14</label>
        <mixed-citation xml:lang="ru">Gireesh E.D., Gurupur V.P. Information Entropy Measures for Evaluation of Reliability of Deep Neural Network Results. Entropy. 2023;25(4). https://doi.org/10.3390/e25040573</mixed-citation>
      </ref>
      <ref id="cit15">
        <label>15</label>
        <mixed-citation xml:lang="ru">Abdar M., Pourpanah F., Hussain S., et al. A review of uncertainty quantification in deep learning: techniques, applications and challenges. Information Fusion. 2021;76:243–297. https://doi.org/10.1016/j.inffus.2021.05.008</mixed-citation>
      </ref>
      <ref id="cit16">
        <label>16</label>
        <mixed-citation xml:lang="ru">Hildebrand M., Brown A., Brown S., Waslander S.L. Assessing Distribution Shift in Probabilistic Object Detection Under Adverse Weather. IEEE Access. 2023;11:44989–45000. https://doi.org/10.1109/ACCESS.2023.3270447</mixed-citation>
      </ref>
      <ref id="cit17">
        <label>17</label>
        <mixed-citation xml:lang="ru">Balanya S.A., Maroñas J., Ramos D. Adaptive temperature scaling for Robust calibration of deep neural networks. Neural Computing and Applications. 2024;36(14):8073–8095. https://doi.org/10.1007/s00521-024-09505-4</mixed-citation>
      </ref>
      <ref id="cit18">
        <label>18</label>
        <mixed-citation xml:lang="ru">Gawlikowski J., Tassi C.R.N., Ali M., et al. A survey of uncertainty in deep neural networks. Artificial Intelligence Review. 2023;56(S1):1513–1589. https://doi.org/10.1007/s10462-023-10562-9</mixed-citation>
      </ref>
      <ref id="cit19">
        <label>19</label>
        <mixed-citation xml:lang="ru">Yelleni S.H., Kumari D., Srijith P.K., Mohan C.K. Monte Carlo DropBlock for modeling uncertainty in object detection. Pattern Recognition. 2024;146. https://doi.org/10.1016/j.patcog.2023.110003</mixed-citation>
      </ref>
      <ref id="cit20">
        <label>20</label>
        <mixed-citation xml:lang="ru">Sharifuzzaman S.A.S.M., Tanveer J., Chen Y., et al. Bayes R-CNN: An Uncertainty-Aware Bayesian Approach to Object Detection in Remote Sensing Imagery for Enhanced Scene Interpretation. Remote Sensing. 2024;16(13). https://doi.org/10.3390/rs16132405</mixed-citation>
      </ref>
      <ref id="cit21">
        <label>21</label>
        <mixed-citation xml:lang="ru">Grafberger S., Groth P., Schelter S. Provenance Tracking for End-to-End Machine Learning Pipelines. In: WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023, 30 April – 04 May 2023, Austin, TX, USA. New York: Association for Computing Machinery; 2023. https://doi.org/10.1145/3543873.3587557</mixed-citation>
      </ref>
      <ref id="cit22">
        <label>22</label>
        <mixed-citation xml:lang="ru">Ostroukh A.V., Kuftinova N.G., Borzenkov A.M., Podberezkin A.A., Ostroukh I.A. Research on Using Deep Learning for Transport Demand Prediction. In: 2024 Intelligent Technologies and Electronic Devices in Vehicle and Road Transport Complex, 13–15 November 2024, Moscow, Russian Federation. IEEE; 2024. P. 1–5. https://doi.org/10.1109/TIRVED63561.2024.10769599</mixed-citation>
      </ref>
    </ref-list>
    <fn-group>
      <fn fn-type="conflict">
        <p>The authors declare that there are no conflicts of interest present.</p>
      </fn>
    </fn-group>
  </back>
</article>