<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Computational nanotechnology</journal-id><journal-title-group><journal-title xml:lang="en">Computational nanotechnology</journal-title><trans-title-group xml:lang="ru"><trans-title>Computational nanotechnology</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2313-223X</issn><issn publication-format="electronic">2587-9693</issn><publisher><publisher-name xml:lang="en">YUR-VAK</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">309698</article-id><article-id pub-id-type="doi">10.33693/2313-223X-2025-12-1-34-47</article-id><article-id pub-id-type="edn">LQAATJ</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>INFORMATION TECHNOLOGY AND TELECOMMUNICATION</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ И ТЕЛЕКОММУНИКАЦИИ</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Statistical Learning of Robotic Demonstration Trajectories Based on Multicriteria Segmentation and Multi-Demonstration Alignment (HSMM)</article-title><trans-title-group xml:lang="ru"><trans-title>Статистическое обучение траекториям роботизированных демонстраций на основе многофакторной сегментации и согласования нескольких показов (HSMM)</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0003-1359-2180</contrib-id><contrib-id contrib-id-type="scopus">59144647300</contrib-id><contrib-id contrib-id-type="spin">4254-9225</contrib-id><name-alternatives><name xml:lang="en"><surname>Gao</surname><given-names>Tianci</given-names></name><name xml:lang="ru"><surname>Гао</surname><given-names>Тяньцы</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Postgraduate Student of the Department of System Analysis, Control Science, and Information Processing</p></bio><bio xml:lang="ru"><p>аспирант кафедры ИУ1 «Системы автоматического управления»</p></bio><email>Gaotianci0088@gmail.com</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="spin">2264-1653</contrib-id><name-alternatives><name xml:lang="en"><surname>Dmitriev</surname><given-names>Dmitry D.</given-names></name><name xml:lang="ru"><surname>Дмитриев</surname><given-names>Дмитрий Дмитриевич</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Cand. Sci. (Eng.); Associate Professor of the Department of System Analysis, Control Science, and Information Processing</p></bio><bio xml:lang="ru"><p>кандидат технических наук, доцент кафедры ИУ1 «Системы автоматического управления»</p></bio><email>dddbmstu@gmail.com</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-6703-6735</contrib-id><contrib-id contrib-id-type="scopus">6602995907</contrib-id><contrib-id contrib-id-type="spin">2860-1736</contrib-id><name-alternatives><name xml:lang="en"><surname>Neusypin</surname><given-names>Konstantin A.</given-names></name><name xml:lang="ru"><surname>Неусыпин</surname><given-names>Константин Авенирович</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Dr. Sci. (Eng.), Professor of the Department of System Analysis, Control Science, and Information Processing</p></bio><bio xml:lang="ru"><p>доктор технических наук, профессор кафедры ИУ1 «Системы автоматического управления»</p></bio><email>neysipin@mail.ru</email><xref ref-type="aff" rid="aff1"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Bauman Moscow State Technical University</institution></aff><aff><institution xml:lang="ru">Московский государственный технический университет имени Н.Э. Баумана</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2025-06-19" publication-format="electronic"><day>19</day><month>06</month><year>2025</year></pub-date><volume>12</volume><issue>1</issue><fpage>34</fpage><lpage>47</lpage><history><date date-type="received" iso-8601-date="2025-09-18"><day>18</day><month>09</month><year>2025</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2025, Yur-VAK</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2025, Юр-ВАК</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="en">Yur-VAK</copyright-holder><copyright-holder xml:lang="ru">Юр-ВАК</copyright-holder><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://www.urvak.ru/contacts/</ali:license_ref></license></permissions><self-uri xlink:href="https://journals.rcsi.science/2313-223X/article/view/309698">https://journals.rcsi.science/2313-223X/article/view/309698</self-uri><abstract xml:lang="en"><p>Statistical Learning of Robotic Demo Trajectories Based on Multicriteria Segmentation and Multi-Demonstration Alignment (HSMM) addresses complex tasks in human-robot interaction and intelligent manufacturing. <italic>The</italic> <italic>research goal</italic> of this study is to automatically extract generalized key segments from multiple robotic demonstration trajectories in the absence of prior annotations and establish statistical and parametric models for universal trajectory reproduction across diverse tasks and conditions. To achieve this, <italic>the</italic> <italic>research tasks</italic> include multicriteria segmentation (speed, curvature, acceleration, direction change), trajectory alignment using Hidden Semi-Markov Models (HSMM), and subsequent implementation of statistical representations (ProMP, GMM/GMR, DMP). The proposed methodology begins with the smoothing of raw data and the identification of key points via topological simplification and non-maximum suppression, then, using HSMM, it ensures consistent segmentation of multiple demonstrations into characteristic segments. The conducted experiments confirm <italic>the</italic> <italic>results</italic> of the approach, demonstrating low reconstruction error while simultaneously improving data compression and preserving key actions, indicating the high efficiency of the method. Finally, the novelty and practical significance of this study can be highlighted by the potential industrial applications (such as welding, painting, etc.), as well as the future prospective expansions of the method to more dynamic and non-stationary scenarios, requiring adaptive and statistically grounded trajectory planning.</p></abstract><trans-abstract xml:lang="ru"><p>Статистическое обучение траекториям роботизированных демонстраций на основе многофакторной сегментации и согласования нескольких показов (HSMM) ориентировано на решение комплексных задач человеко-машинного взаимодействия и интеллектуального производства. Основная <italic>цель исследования</italic> работы заключается в автоматическом выявлении обобщенной структуры ключевых участков из нескольких роботизированных демонстраций при отсутствии априорной разметки данных, а также в построении статистических и параметрических моделей для универсального воспроизведения траектории в разнообразных задачах и условиях. Для достижения этой цели сформулированы <italic>задачи исследования</italic>, включающие многопризнаковую сегментацию (скорость, кривизна, ускорение, изменение направления), выравнивание траекторий с помощью скрытой полумарковской модели и последующую реализацию статистических представлений (ProMP, GMM/GMR, DMP). Предлагаемая методика позволяет сначала осуществлять сглаживание исходных данных и выявление ключевых точек путем их топологического упрощения и подавления немаксимальных значений, а затем, используя HSMM, обеспечивать согласованное разбиение нескольких демонстраций на характерные сегменты. Проведенные эксперименты подтверждают, что полученные <italic>результаты</italic> позволяют достигать низкой ошибки восстановления при одновременном повышении степени сжатия данных и сохранении важных действий, что свидетельствует о высокой эффективности предлагаемого подхода. Наконец, анализируя новизну и практическую значимость работы, можно отметить возможность применения данного решения в промышленном контексте (сварка, окраска и т.д.), а также перспективы расширения метода на более динамичные и нестационарные сценарии, где требуется адаптивное и статистически обоснованное планирование траектории.</p></trans-abstract><kwd-group xml:lang="en"><kwd>robot learning from demonstrations</kwd><kwd>trajectory segmentation</kwd><kwd>probabilistic motion primitives</kwd><kwd>multicriteria analysis</kwd><kwd>Hidden Semi-Markov Model (HSMM)</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>обучение робота по демонстрациям</kwd><kwd>сегментация траектории</kwd><kwd>вероятностные примитивы движения</kwd><kwd>мультипризнаковый анализ</kwd><kwd>скрытая полумарковская модель (HSMM)</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Savitsky A., Golay M.J.E. Smoothing and differentiation of data by simplified least squares methods. Analytical Chemistry. 1964. Vol. 36. No. 8. Pp. 1627–1639. DOI: 10.1021/ac60214a047.</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>Cohen-Steiner D., Edelsbrunner H., Harer J. Stability of persistence diagrams. In: Proceedings of the Twenty-First Annual Symposium on Computational Geometry. ACM, 2005. Pp. 263–271. DOI: 10.1145/1064092.1064133.</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Liu C., Ren B., Fu D., Li M. A GNSS composite interference recognition method based on YOLOv5. In: IEEE 6th International Conference on Civil Aviation Safety and Information Technology (ICCASIT). IEEE, 2024. Pp. 1157–1162. DOI: 10.1109/ICCASIT62299.2024.10828065.</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Liu T., Zhu K., Zeng L. Diagnosis and prognosis of degradation process via hidden semi-Markov model. IEEE/ASME Transactions on Mechatronics. 2018. Vol. 23. No. 3. Pp. 1456–1466. DOI: 10.1109/TMECH.2018.2823320.</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Osa T., Pajarinen J., Neumann G. et al. An algorithmic perspective on imitation learning. Foundations and Trends® in Robotics. 2018. Vol. 7. No. 1–2. Pp. 1–179. DOI: 10.1561/2300000053.</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Calinon S. Gaussians on Riemannian manifolds: Applications for robot learning and adaptive control. IEEE Robotics &amp; Automation Magazine. 2020. Vol. 27. No. 2. Pp. 33–45. DOI: 10.1109/MRA.2020.2980548.</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>Xie J., Yan H., Wang J., Li J., Chen B. Unsupervised approach for multi-modality telerobotic trajectory segmentation. IEEE Internet of Things Journal. 2024. DOI: 10.1109/JIOT.2024.3412134.</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Yu L., Bai S. A modified dynamic movement primitive algorithm for adaptive gait control of a lower limb exoskeleton. IEEE Transactions on Human-Machine Systems. 2024. DOI: 10.1109/THMS.2024.3458905.</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Kulak T., Girgin H., Odobez J.M. et al. Active learning of Bayesian probabilistic movement primitives. IEEE Robotics and Automation Letters. 2021. Vol. 6. No. 2. Pp. 2163–2170. DOI: 10.1109/LRA.2021.3060414.</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Sung H.G. Gaussian mixture regression and classification. Abstract of dis. ... of Dr. Sci. (Philos.). Rice University, 2004.</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Mandlekar A., Zhu Y., Garg A. et al. Roboturk: A crowdsourcing platform for robotic skill learning through imitation. In: Conference on Robot Learning. PMLR, 2018. Pp. 879–893.</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation>Paraschos A., Daniel C., Peters J.R. et al. Probabilistic movement primitives. In: Advances in Neural Information Processing Systems. 2013. P. 26.</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation>Vemuri N., Thaneeru N. Enhancing human-robot collaboration in Industry 4.0 with AI-driven HRI. Power System Technology. 2023. Vol. 47. No. 4. Pp. 341–358. DOI: 10.52783/pst.196.</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation>Bishop C.M., Nasrabadi N.M. Pattern recognition and machine learning. New York: Springer, 2006.</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation>Zhang T., Mo H. Reinforcement learning for robot research: A comprehensive review and open issues. International Journal of Advanced Robotic Systems. 2021. Vol. 18. No. 3. DOI: 10.1177/17298814211007305.</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation>Li G., Jin Z., Volpp M. et al. ProDMP: A unified perspective on dynamic and probabilistic movement primitives. IEEE Robotics and Automation Letters. 2023. Vol. 8. No. 4. Pp. 2325–2332. DOI: 10.1109/LRA.2023.3248443.</mixed-citation></ref><ref id="B17"><label>17.</label><mixed-citation>Wong C.C., Vong C.M. Persistent homology-based graph convolution network for fine-grained 3D shape segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021. Pp. 7098–7107. DOI: 10.1109/ACCESS.2022.3218653.</mixed-citation></ref><ref id="B18"><label>18.</label><mixed-citation>Lu Y., Jiang B., Liu N. et al. CrossPrune: Cooperative pruning for camera – LiDAR fused perception models of autonomous driving. Knowledge-Based Systems. 2024. Vol. 289. Art. 111522. DOI: 10.1016/j.knosys.2024.111522.</mixed-citation></ref><ref id="B19"><label>19.</label><mixed-citation>Neubeck A, Van Gool L. Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR’06). IEEE, 2006. Vol. 3. Pp. 850–855. DOI: 10.1109/ICPR.2006.479.</mixed-citation></ref><ref id="B20"><label>20.</label><mixed-citation>Gervet T., Xian Z., Gkanatsios N. et al. Act3D: 3D feature field transformers for multi-task robotic manipulation. In: 7th Annual Conference on Robot Learning, 2023.</mixed-citation></ref></ref-list></back></article>
