infojournalИнформатика и образованиеInformatics and education0234-04532658-7769Publishing House Education and Informatics10.32517/0234-0453-2020-35-1-59-67infojournal-507Research ArticleИНФОРМАТИЗАЦИЯ ОБРАЗОВАНИЯINFORMATIZATION OF EDUCATIONАлгоритм автоматического управления навигацией мобильного робота на основе нечеткой нейронной сети в промышленном интернете вещейMobile robot automatic navigation control algorithm based on fuzzy neural network in industrial Internet of things environmenthttps://orcid.org/0000-0001-6751-7598ПэйП.PeiP.

Пэй Пинг, аспирант кафедры «Информационные системы и технологии», Международный институт дистанционного образования

Pei Ping, postgraduate student at the Department “Information Systems and Technologies”, International Institute of Distant Education

peiping123456.love@gmail.comПетренкоЮ. Н.PetrenkoYu. N.

Петренко Юрий Николаевич, пожизненный член IEEE, канд. тех. наук, доцент, доцент кафедры «Информационные системы и технологии», Международный институт дистанционного образования

Yury N. Petrenko, IEEE Life Member, Candidate of Sciences (Engineering), Docent, Associate Professor at the Department “Information Systems and Technologies”, International Institute of Distant Education

ypetrenko@bntu.byБелорусский национальный технический университетБеларусьBelarusian National Technical UniversityBelarus202010032020115967Copyright © Пэй П., Петренко Ю.Н., 20202020Пэй П., Петренко Ю.Н.Pei P., Petrenko Y.N.This work is licensed under a Creative Commons Attribution 4.0 License.https://info.infojournal.ru/jour/article/view/507

С появлением технологии беспроводной связи 5G важным и постоянно развивающимся направлением робототехники становятся мобильные роботы, которые широко используются в пространстве промышленного интернета вещей (Industrial Internet of Things — IIoT), в сельском хозяйстве, в армии, на транспорте. Технология автоматического управления навигацией — ядро в этих областях исследований, а также ключевая технология для достижения интеллектуализации иавтономизации мобильного робота.

В данной статье подробно рассматриваются и исследуются технологии нейронных сетей и их применение в управлении навигацией, предлагается способ для повышения уровня интеллектуализации мобильного робота с самоорганизацией обучения, придания адаптивных возможностей для решения автономной задачи навигации мобильного робота в сложных неопределенных и неизвестных переменных средах с использованием нейронной сети в сочетании с другими интеллектуальными алгоритмами, такими как обучение с подкреплением и т. п. Решение задачи управления навигацией мобильного робота с использованием нечеткой нейронной сети может обеспечить более эффективную производительность управления в режиме реального времени за счет изменения веса сети путем самообучения в соответствии с априорными знаниями навигации экспертов-операторов.

Mobile robot is an important developing direction in the field of robotics, it is widely used in Industrial Internet of Things (IIoT) environment, agriculture, military, transportation, services with the coming of 5G wireless communication technology. Automatic navigation control technology is the core in these research areas, which is also the key technology for mobile robot to achieve intelligentization and autonomation.

The article discusses and researches the neural network technology and its application in mobile robot navigation control. For the characteristics and research of mobile robot navigation problem, it finds the way to improve the mobile robot intelligentization, level of the self-organization, self-learning and adaptive capability. The combination of neural network with other intelligent algorithms solves autonomous navigation problem of the mobile robot in the complex uncertain environments and unknown variable environments. The mobile robot navigation control problem using fuzzy neural network can achieve a more effective real-time navigation control performance through amending the network weights by self-study according to the navigation priori knowledge of human experts.

автоматическое управление навигацией5Gнейронная сетьнечеткая нейронная сетьautomatic navigation control5Gneural networkfuzzy neural networkReferencesPing P., Petrenko Y. N. Аlgoritm gibkogo upravleniya mnozhestvennym dostupom v mobil’noj besprovodnoj sisteme 5G [The flexible multiple access control algorithm in 5th generation mobile wireless system]. Informatika — Informatics, 2018, vol. 15, no. 3, p. 93–101. (In Russian.) Available at: https://inf.grid.by/jour/article/view/419Ping P., Petrenko Y. N. Аlgoritm gibkogo upravleniya mnozhestvennym dostupom v mobil’noj besprovodnoj sisteme 5G [The flexible multiple access control algorithm in 5th generation mobile wireless system]. Informatika — Informatics, 2018, vol. 15, no. 3, p. 93–101. (In Russian.) Available at: https://inf.grid.by/jour/article/view/419KhatibO. Real-time obstacle avoidance for manipulators and mobile robots. Proc. 1985 IEEE Int. Conf. on Robotics and Automation. IEEE, 1985, vol. 5, no. 1, p. 500–505. DOI: 10.1109/ROBOT.1985.1087247KhatibO. Real-time obstacle avoidance for manipulators and mobile robots. Proc. 1985 IEEE Int. Conf. on Robotics and Automation. IEEE, 1985, vol. 5, no. 1, p. 500–505. DOI: 10.1109/ROBOT.1985.1087247Khosla P., Volpe R. Superquadric artificial potentials for obstacle avoidance and approach. Proc. 1988 IEEE Int. Conf. on Robotics and Automation. IEEE, 1988, vol. 10, no. 2, p. 1778–1784. DOI: 10.1109/ROBOT.1988.12323Khosla P., Volpe R. Superquadric artificial potentials for obstacle avoidance and approach. Proc. 1988 IEEE Int. Conf. on Robotics and Automation. IEEE, 1988, vol. 10, no. 2, p. 1778–1784. DOI: 10.1109/ROBOT.1988.12323Glasius R., Komoda A., Gielen S. C. A. M. A biologically inspired neural net for trajectory formation and obstacle avoidance. Biological Cybernetics, 1996, vol. 74, p. 511–520. DOI: 10.1007/BF00209422Glasius R., Komoda A., Gielen S. C. A. M. A biologically inspired neural net for trajectory formation and obstacle avoidance. Biological Cybernetics, 1996, vol. 74, p. 511–520. DOI: 10.1007/BF00209422Leon J. A. F., Tosini M., Acosta G. G. Evolutionary reactive behavior for mobile robots navigation. Proc. IEEE Conf. on Cybernetics and Intelligent Systems. IEEE, 2004, p. 532–537. DOI: 10.1109/ICCIS.2004.1460471Leon J. A. F., Tosini M., Acosta G. G. Evolutionary reactive behavior for mobile robots navigation. Proc. IEEE Conf. on Cybernetics and Intelligent Systems. IEEE, 2004, p. 532–537. DOI: 10.1109/ICCIS.2004.1460471Tuci E., Harvey I., Quinn M. Evolving integrated controllers for autonomous learning robots using dynamic neural networks. ICSAB: Proc. Seventh Int. Conf. on simulation of adaptive behavior on From animals to animats. 2002, p. 282–291.Tuci E., Harvey I., Quinn M. Evolving integrated controllers for autonomous learning robots using dynamic neural networks. ICSAB: Proc. Seventh Int. Conf. on simulation of adaptive behavior on From animals to animats. 2002, p. 282–291.Holland J. H. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT Press, 1992. 228 p.Holland J. H. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT Press, 1992. 228 p.Sutton R. S., Barto A. G. Reinforcement learning: an introduction. MIT Press, 1998. 344 p.Sutton R. S., Barto A. G. Reinforcement learning: an introduction. MIT Press, 1998. 344 p.Tan K. C., Tan K. K., Lee T. H., Zhao S., Chen Y. J. Autonomous robot navigation based on fuzzy sensor fusion and reinforcement learning. Proc. IEEE Int. Symposium on Intelligent Control. IEEE, 2002, vol. 28, no. 6, p. 182–187. DOI: 10.1109/ISIC.2002.1157759Tan K. C., Tan K. K., Lee T. H., Zhao S., Chen Y. J. Autonomous robot navigation based on fuzzy sensor fusion and reinforcement learning. Proc. IEEE Int. Symposium on Intelligent Control. IEEE, 2002, vol. 28, no. 6, p. 182–187. DOI: 10.1109/ISIC.2002.1157759CarpenterG.A., GrossbergS. ART 2: Self-Organization of stable category recognition codes for analog input patterns. Applied Optics, 1987, vol. 26, is. 23, p. 4919–4930. DOI: 10.1364/AO.26.004919CarpenterG.A., GrossbergS. ART 2: Self-Organization of stable category recognition codes for analog input patterns. Applied Optics, 1987, vol. 26, is. 23, p. 4919–4930. DOI: 10.1364/AO.26.004919Jianhong L., Dezhao C. An enhanced ART2 neural network for clustering analysis. Proc. First Int. Workshop on Knowledge Discovery and Data Mining. IEEE, 2008, p. 81–85. DOI: 10.1109/WKDD.2008.117Jianhong L., Dezhao C. An enhanced ART2 neural network for clustering analysis. Proc. First Int. Workshop on Knowledge Discovery and Data Mining. IEEE, 2008, p. 81–85. DOI: 10.1109/WKDD.2008.117Qian X.-D., Wang Z.-O., Wang Y. A method of data clustering based on improved algorithm of ART2. Proc. 2005 Int. Conf. on Machine Learning and Cybernetics. IEEE, 2005, p. 2021–2026. DOI: 10.1109/ICMLC.2005.1527277Qian X.-D., Wang Z.-O., Wang Y. A method of data clustering based on improved algorithm of ART2. Proc. 2005 Int. Conf. on Machine Learning and Cybernetics. IEEE, 2005, p. 2021–2026. DOI: 10.1109/ICMLC.2005.1527277Leon J. A. F., Tosini M., Acosta G. G. Evolutionary reactive behavior for mobile robots navigation. IEEE Conference on Cybernetics and Intelligent System. IEEE, 2004, p. 532–537. DOI: 10.1109/ICCIS.2004.1460471Leon J. A. F., Tosini M., Acosta G. G. Evolutionary reactive behavior for mobile robots navigation. IEEE Conference on Cybernetics and Intelligent System. IEEE, 2004, p. 532–537. DOI: 10.1109/ICCIS.2004.1460471Nelson A. L., Grant E., Galeotti J. M., Rhody S. Maze exploration behaviors using an integrated evolutionary robotic environment. Robotics and Autonomous Systems, 2004, vol. 46, is. 3, p. 159–173. DOI: 10.1016/j.robot.2003.11.002Nelson A. L., Grant E., Galeotti J. M., Rhody S. Maze exploration behaviors using an integrated evolutionary robotic environment. Robotics and Autonomous Systems, 2004, vol. 46, is. 3, p. 159–173. DOI: 10.1016/j.robot.2003.11.002Asada M., Noda S., Tawaratsumida S., Hosoda K. Purposive behavior acquisition for a real robot by vision-based reinforcement learning. Machine Learning, 1996, vol. 23, p. 279–303. DOI: 10.1023/A:1018237008823Asada M., Noda S., Tawaratsumida S., Hosoda K. Purposive behavior acquisition for a real robot by vision-based reinforcement learning. Machine Learning, 1996, vol. 23, p. 279–303. DOI: 10.1023/A:1018237008823Cliff D., Husbands P., Harvey I. Explorations in evolutionary robotics. Adaptive Behavior, 1993, vol. 2, is. 1, p. 73–110. DOI: 10.1177/105971239300200104Cliff D., Husbands P., Harvey I. Explorations in evolutionary robotics. Adaptive Behavior, 1993, vol. 2, is. 1, p. 73–110. DOI: 10.1177/105971239300200104Del R., Millan J. Rapid, safe and incremental learning of navigation strategies. Proc. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics). IEEE, 1996, vol. 26, is. 3, p. 408–420. DOI: 10.1109/3477.499792Del R., Millan J. Rapid, safe and incremental learning of navigation strategies. Proc. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics). IEEE, 1996, vol. 26, is. 3, p. 408–420. DOI: 10.1109/3477.499792Mitchell T.M. Machine learning. New York, McGrawHill, 1997. 432 p.Mitchell T.M. Machine learning. New York, McGrawHill, 1997. 432 p.

The authors declare that there are no conflicts of interest present.