Defense of the dissertation of Қызырқанов Абзал Ермекбайұлы for the degree of Doctor of Philosophy (PhD) in the specialty «8D06104 - Computer Engineering and Software»
In the «L.N. Gumilyov Eurasian national university» Kyzyrkanov Abzal Yermekbayuly will defend a dissertation for the degree of Doctor of Philosophy (PhD) on the topic «Software and algorithmic support of a self-organizing intelligent mobile robots system» according to the educational program «8D06104 - Computer engineering and software».
The dissertation was performed at the Department of Computer and Software Engineering of the L.N. Gumilyov Eurasian national university.
The language of defense is russian
Official reviewers:
Omarov Batyrkhan Sultanovich – Doctor of Philosophy (PhD), specialty: Information and communication technologies, associate professor, al-Farabi Kazakh national university (Almaty, Republic of Kazakhstan).
Aday Shomanov – Doctor of Philosophy (PhD), specialty: 6D060200 – Informatics, Instructor, School of Engineering and Digital Sciences, Nazarbayev university (Astana, Republic of Kazakhstan).
Temporary members of the dissertation council:
Matkarimov Bakhyt Turganbayevich – Doctor of Technical Sciences, specialty: 05.13.15 - Computing Machines and Systems, professor, leading researcher, Private Institution "National laboratory Astana", Nazarbayev university (Astana, Republic of Kazakhstan).
Ten Tatyana Leonidovna – Doctor of Technical Sciences, specialty: 05.13.01 - System analysis, control and information processing, professor of the specialty: 05.13.00 - Informatics, computer engineering and control, Head of the Department of Digital Engineering and IT Analytics, Karaganda university of Kazpotrebsoyuz (Karaganda, Republic of Kazakhstan).
Kalimoldaev Maksat Nuradilovich – Doctor of Physical and Mathematical Sciences, specialty: 05.13.16 - Application of computer technology, mathematical modeling, and mathematical methods in scientific research, professor, advisor to the General Director of RSE "Institute of Information and Computational Technologies" of the Science Committee of MSHE RK (Almaty, Republic of Kazakhstan).
Beloshchitsky Andrey Alexandrovich – Doctor of Technical Sciences, specialty: "Project and Program Management", professor, Vice-rector for Science and Innovation, Astana IT University (Astana, Republic of Kazakhstan).
Scientific consultants:
Atanov Sabyrzhan Kubeisinovich – Doctor of Technical Sciences, professor of the Department of Computer and Software Engineering, L.N. Gumilyov Eurasian national university, specialty: 05.13.11 - Mathematical and software support of computing machines, complexes and computer networks (Astana, Republic of Kazakhstan).
Shadi Aljawarneh – Doctor of Philosophy (PhD), Professor of the Department of Software Security and Software Engineering, Jordan University of Science and Technology (Irbid, Jordan).
The defense will take place on August 23, 2024, at 11:00 AM in the Dissertation Council for the training direction «8D061 – Information and communication technologies» in the specialty «8D06104 – Computer Engineering and Software» of L.N. Gumilyov Eurasian National University.
The Dissertation council meeting will be held offline and online.
Address: Astana, A. Pushkin str., 11, auditorium 222.
Abstract (English): ANNOTATION of the dissertation work of A. E. Kyzyrkanov "Software and algorithmic support of a self-organizing intelligent mobile robots system”, submitted for the degree of Doctor of Philosophy (PhD) in the educational program 8D06104 - Computer engineering and software Relevance of the research topic. The application of robots is relevant in various scientific, technological, and industrial fields, particularly in scenarios that are difficult or impossible for humans to access. These fields include environments with radioactive or chemical contamination, combat zones, underwater exploration, and space research. Numerous studies have focused on developing robots for diverse purposes, leading to the identification of fundamental challenges such as object recognition, environmental modeling, motion planning, and control. However, it is evident that a single robot, regardless of its capabilities, has limited abilities to accomplish complex tasks. To overcome these challenges, the use of robot groups, or swarms, has emerged as a promising solution. Applying robots in groups offers several advantages, including extended operational range by dispersing robots throughout the work area, expanded functionality through individual actuators on each robot, and increased task completion probability through goal redistribution among group members. Consequently, complex tasks like large-scale planetary exploration, underwater and space structure assembly, combat and support operations, and area clearance can be effectively addressed only through collaborative interactions among robots. However, this necessitates addressing new issues related to group management and communication. In order to efficiently solve complex tasks in dynamic and unpredictable environments, robots in a swarm must interact in a coordinated manner. Planning and control methods should be developed to operate in real-time on on-board computing devices. Achieving this requires the swarm to function as a unified entity, with individual robot actions aimed at maximizing the collective impact. Researchers have unanimously concluded that decentralized (distributed) control methods are essential for effective teamwork. This research focuses on coordinating and controlling multiagent robotic systems, specifically addressing key challenges in swarm robotics. The study explores various methodologies and techniques to enhance swarm performance and capabilities across different aspects. One critical aspect is formation control, where methodologies are proposed to achieve desired geometric formations within the swarm. By implementing behavior-based control algorithms, the swarm can achieve coordinated movement and efficient task execution. This approach enables the swarm to handle multiple tasks simultaneously, enhancing overall system performance. Efficient energy consumption is another crucial consideration. This work introduces a methodology to reduce energy usage through selective lidar activation. By intelligently activating lidars based on environmental conditions and task requirements, the swarm can conserve energy while maintaining necessary perception capabilities. This approach improves the swarm's energy efficiency, allowing it to operate for extended periods and perform complex tasks. Additionally, this research proposes strategies to address the issue of potential deadlock situations within multi-agent robotic systems. While navigating towards a target, bypassing obstacles, and making on-the-spot decisions influenced by the external environment, robots may inadvertently converge on the same location. If the external environment remains unchanged, robots following the same algorithm and making identical decisions repeatedly can enter into a loop. To mitigate this problem, an approach called epsilon-greedy is employed. The epsilon-greedy algorithm introduces randomness into the robots' movements, helping them avoid repetitive patterns. This approach, widely used in machine learning, prevents the system from becoming overly adapted to local optima and enhances its adaptability. The essence of this method lies in the system occasionally choosing an "illogical" solution when making decisions with a very small probability, known as epsilon. The leader-follower approach with a virtual leader is utilized to enhance coordination within the swarm. By assigning a virtual leader and maintaining a desired distance relative to it, the swarm achieves coordinated movement and formation maintenance. This approach increases system robustness, as the failure of a single leader does not render the entire system inoperative. This method is particularly advantageous when a centralized leader is not feasible or redundancy is desired. Moreover, this research incorporates fuzzy logic control to make informed navigation decisions. By analyzing lidar data using fuzzy logic, the swarm can navigate effectively, making intelligent decisions based on various inputs and environmental factors. By addressing these individual challenges and employing methods such as formation control, energy consumption reduction through selective lidar activation, deadlock avoidance, leader-follower with a virtual leader, and fuzzy logic control, this research contributes to advancing swarm robotics. The developed methodologies and techniques have practical significance and potential applications in various domains, including search and rescue operations, environmental monitoring, exploration missions, industrial automation, and military applications. These advancements improve coordination, energy efficiency, system robustness, and intelligent decision-making capabilities, enabling the effective utilization of swarm robotics in real-world scenarios. To evaluate the effectiveness of the proposed methodologies, experimental research was conducted using a swarm motion simulator developed with pygame. The swarm's motion was tested in different maps, simulating various real-world scenarios. By conducting experiments in a controlled environment, the performance and capabilities of the swarm were assessed, allowing for a quantitative evaluation of the proposed methodologies. The experimental results provided valuable insights into the effectiveness of coordination and control techniques, formation control strategies, energy consumption reduction methods, deadlock avoidance strategies, leader-follower approaches, and fuzzy logic control. These experiments validated the proposed methodologies and demonstrated their potential for practical applications in swarm robotics. The purpose of the dissertation research is to develop and implement software for controlling and coordinating a swarm of autonomous, self-organizing intelligent mobile robots. Research objectives: - Investigate "leader-follower" management methods to thoroughly study and enhance the efficiency and coordination of swarm dynamics, ensuring optimal movement and adaptability without reliance on a physical leader. - Study methods and models to increase the efficiency of swarm systems, aiming to identify and apply resource management strategies that significantly improve the energy efficiency of the swarm, crucial for long-duration missions. - Analyze the method for determining the boundaries of the swarm for management purposes, to develop an obstacle avoidance strategy prioritizing agents at the edges, contributing to more efficient movement and improved navigational capabilities. - Develop intelligent methods for optimizing the movement of swarm robots, to enhance adaptive navigation and increase decision-making efficiency in obstacle avoidance under complex conditions. - Implement algorithmic and software systems for self-organizing intelligent mobile robots, to create a robust foundation that ensures autonomous and self-organizing behavior, enhancing the efficiency of task execution in various conditions. The object of study in this research is a swarm of autonomous, self-organizing intelligent mobile robots with decentralized management. The subject of this study is the algorithms for coordination and management of the robot swarm. The research methodology of this thesis involves a systematic approach to achieving its objectives. The study begins with an extensive literature review to explore existing approaches and gain a thorough understanding of algorithms and methods for controlling and coordinating robots, multi-agent robotic systems, and swarms of robots. Building upon this knowledge, the research introduces novel methodologies specifically designed for the coordination and control of a swarm of autonomous, self-organizing intelligent mobile robots. These methodologies incorporate several key components, including a leader-follower technique with a virtual leader, a behavior-based approach, the selective lidar activation approach, fuzzy logic-based turn direction calculation, and the epsilon greedy algorithm to address challenges such as collision avoidance and preventing infinite loops during motion. The effectiveness of the proposed method is evaluated through simulation experiments, which were conducted using a motion simulator developed in Python programming language with the assistance of PyGame. By employing this research methodology, the study aims to contribute to the field of robotics by offering an innovative and comprehensive solution for coordinating and controlling a swarm of autonomous robots. The scientific novelty of the proposed doctoral dissertation is encapsulated in the following key aspects: - A modified "leader-follower" method with a virtual leader has been developed. This approach enhances swarm coordination, allowing for the maintenance of specific geometric formations and ensuring operational continuity even when individual robots fail. - An intelligent method for modeling the behavior of swarm systems using behavior weight adjustments has been developed. The application of fuzzy logic enables the dynamic adaptation of swarm behavior to environmental changes in real time. - The e-greedy algorithm in swarm robotics has been proposed. This algorithm addresses the issue of looping by introducing randomness into decision-making, thereby improving the operational efficiency of the swarm in complex conditions. - A method for swarm movement with selective lidar activation has been developed. This method reduces energy consumption by activating lidars only when necessary, enhancing energy efficiency and extending the lifespan of autonomous mobile robot swarms. - A method for calculating angular velocity based on fuzzy logic has been developed. This technique allows for precise and adaptive movement control in dynamically changing conditions, improving maneuverability and obstacle avoidance. - An algorithmic and software system for self-organizing intelligent mobile robots has been developed. This system implements all the aforementioned methods, enabling robotic swarms to effectively self-organize and autonomously perform tasks. Provisions submitted for defense: - A modified "leader-follower" method with a virtual leader. This method allows swarms to maintain a specific geometric shape and continue coordinated movement even when individual robots fail, using a virtual leader to improve system stability. - An intelligent method for modeling swarm system behavior. The implementation of fuzzy logic enables swarms to automatically adjust their behavior weights, providing an adaptive response to environmental changes for effective swarm behavior. - The application of the e-greedy algorithm in swarm robotics. The e-greedy algorithm introduces controlled randomness into decision-making processes, offering a strategy to avoid repetitive loops in robot trajectories, thereby enhancing the swarm's ability to move more optimally in complex conditions. - A swarm movement method with selective lidar activation. This method proposes a strategic reduction in energy consumption by activating lidars only, when necessary, directly contributing to operational sustainability and longevity of swarm systems through energy use optimization. - Calculation of angular velocity based on fuzzy logic. The use of fuzzy logic for calculating angular velocity allows for more precise and adaptive movement control in dynamically changing conditions. - The development of algorithmic and software systems for self-organizing intelligent mobile robots. This comprehensive system implements all the aforementioned methods, enabling robotic swarms to efficiently self-organize and autonomously perform tasks. Theoretical and practical significance of the study: The research conducted in this study holds considerable theoretical and practical significance in the field of robotics and swarm intelligence. It addresses the challenges associated with coordinating and controlling a swarm of autonomous, self-organizing intelligent mobile robots, making noteworthy contributions to the advancement of swarm systems and the potential mass utilization of autonomous mobile robots in large groups. From a theoretical perspective, this study delves into the realm of algorithms and methods for swarm control, multi-agent robotic systems, and coordination within complex and dynamic environments. The introduction of a novel algorithm specifically tailored for swarm coordination and control represents a substantial theoretical contribution, offering a fresh perspective on achieving efficient and intelligent behavior within a swarm. The practical significance of this study is equally remarkable. The developed methodologies provide a practical solution for effectively coordinating and controlling a swarm of autonomous robots, enabling their collaborative performance in complex tasks. The algorithm's ability to optimize energy consumption by selectively activating lidars enhances the practicality and sustainability of robotic systems. The study's methodology also bears significant practical importance. The systematic approach, encompassing thorough literature review, algorithm design, and simulation experiments, ensures rigorous evaluation and validation of the proposed algorithm. The outcomes derived from the simulation experiments further contribute to the algorithm's practical applicability, guiding its potential implementation in real-world robotic systems. To summarize, the theoretical and practical significance of this study lies in the development and implementation of a novel algorithm for coordinating and controlling a swarm of autonomous, self-organizing intelligent mobile robots. The algorithm's contributions to the field of swarm robotics, including its theoretical underpinnings, practical applicability, and sustainability aspects, position it as a valuable addition to the existing body of knowledge. Approbation of the results of the dissertation: - Seminars of doctoral students of the Department "Computer and Software Engineering". - 2023 IEEE International Conference on Smart Information Systems and Technologies (2023 IEEE SIST), 4-6 May - 7th International Conference on Digital Technologies in Education, Science and Industry, DTESI 2022 Almaty, 20-21 October 2022 - 2022 International Conference on Smart Information Systems and Technologies 25-26 November. - 2021 IEEE International Conference on Smart Information Systems and Technologies, Nur-Sultan, 28-30 April 2021. Publications: - Article published in a scientific journal indexed by Scopus: - Toibazarov, D., Baiseitov, G., Kyzyrkanov, A., Aljawarneh, S., & Atanov, S. (2023). DEVELOPMENT OF CONTROL SOFTWARE FOR SELFORGANIZING INTELLIGENT MOBILE ROBOTS. Eastern-European Journal of Enterprise Technologies, 122(9). In the collection of conferences included in the Scopus database - Kyzyrkanov A. E., Atanov S. K., Aljawarneh S. A., Tursynova N. A. Movement Coordination of Swarm Robotic Systems. CEUR Workshop Proceedings, 7th International Conference on Digital Technologies in Education, Science and Industry, DTESI 2022 Almaty, 20-21 October 2022, Том 3382 ISSN:1613-0073. - Kyzyrkanov, A., Atanov, S., Aljawarneh, S., Tursynova, N., & Kassymkhanov, S. Algorithm of Coordination of Swarm of Autonomous Robots. SIST 2023 - 2023 IEEE International Conference on Smart Information Systems and Technologies, Proceedings Pages 539 - 5442023 2023 IEEE International Conference on Smart Information Systems and Technologies, SIST 2023 Astana - 4 May 2023 through 6 May 2023 DOI:10.1109/SIST58284.2 023.10223555 - Aidarbekov A., Shakhmetova G., Asmaganbetova K., Bekish Z., Kyzyrkanov A., Salimzhanov A. Informational Technologies in Film Production - How ICT shaping Media Industry. 2021 IEEE 4th International Conference on Advanced Information and Communication Technologies, AICT 2021 – Proceedings, 21–25 September 2021. ISBN:978-166540618-5 DOI:10.1109/AICT52120. 2021.9628901 - Asmaganbetova K., Yeleussizova N., Ceng Micheme A., Aidarbekov A., Kyzyrkanov A., Burissova D. Academic - Industry Partnership: Development IT Sector in Kazakhstan. SIST 2021–2021 IEEE International Conference on Smart Information Systems and Technologies, Nur-Sultan, 28-30 April 2021. ISBN: 978-172817470-9 DOI:10.1109/SIST50301.2 021.9465937 - Articles published in scientific journals recommended by the Committee for Quality Assurance in the Sphere of Education and Science of the Ministry of Education and Science of the Republic of Kazakhstan: - Kyzyrkanov A.E., Atanov S.K., Aljawarneh Sh., Otarbay Zh. Coordination algorithm for a swarm of autonomous mobile robots. Republican scientific and technical journal "University Works - Proceedings of the University" of the Non-Profit Joint-Stock Company "Karaganda Technical University named after Abylkas Saginov", No. 4(93), 2023, pages 448-454. ISSN (Online): 2959–5894 DOI: https://doi.org/10.51889/2022–1.1728–7901.07. - Kyzyrkanov, A., Atanov, S. A., Aljawarneh, S., Tursynova, N., Otarbay, Z., & Khairosheva, K. (2023). METHOD OF COORDINATION OF MOTION OF SWARM ROBOTIC SYSTEMS. Scientific Journal of Astana IT University, 76-85. - Kyzyrkanov, A., Atanov, S., Kasymkhanov, S., Orynbek, A., & Sansyzbay, Q. (2023). CONTROL AND COORDINATION OF MOBILE AUTONOMOUS ROBOT GROUP. Vestnik KazATK, 125(2), 412-421. - Kyzyrkanov A., Bakyt M., Musiralieva Sh., Balbayev G., Tulesheva G. Problems of identifying and ranking the objects of critical information infrastructure of cellular networks in the Republic of Kazakhstan. Vestnik KazATK No. 3 (126), 2023. - certificates of state registration of rights to a copyright object - Computer program: Software for simulation of multiagent swarm systems with a virtual leader. Certificate of State registration of copyright rights No. 22540 dated December 22, 2021. - Computer program: Software for simulation of multiagent swarm systems with a virtual leader. Certificate of State registration of copyright rights No. 22539 dated December 22, 2021. - Certificate of State registration of copyright rights Methods of standardization and authentication in modeling authorization in mobile communication networks. Certificate of State registration of copyright rights No. 34263 dated April 4, 2023. - Computer program: Software implementation of the swarm movement algorithm of intelligent mobile robots with selective activation of lidars based on fuzzy logic. Certificate of State registration of copyright rights No. 41056 dated December 6, 2023. Structure and scope of work. The dissertation consists of an introduction, six chapters, a conclusion, a list of sources used, and appendices. The work is presented on 115 pages, appendices contain 43 figures and 1 table. The introduction provides an overview of the research context and significance, stating the objectives and goals of the study. It also outlines the organizational structure of the dissertation. The first section is presents a comprehensive literature review and analysis of the current state of swarm robotics, discussing relevant theories, concepts, and research findings in the field.. The second section focuses on the application of the leader-follower approach in controlling the formation of the swarm. It explores the concept of a virtual leader and develops a methodology for maintaining formation using the leader-follower approach The third section presents the development of a method for coordinating the movement of swarm robots. It encompasses the design and implementation of algorithms for selecting observer robots, calculating the turn direction of the swarm using fuzzy logic control, and determining the overall velocity of the swarm. The fourth section explores the usage of the epsilon-greedy algorithm to prevent infinite loops in the swarm's motion. It discusses the implementation and integration of this algorithm into the swarm system to ensure efficient and non-repetitive movement. The fifth section focuses on the development of a method for calculating the movement of swarm robots using a behavior-based approach. It includes the design and implementation of algorithms for maintaining formation, avoiding collisions, and ensuring coordinated swarm movement. The sixth section presents the experimental modeling, analysis, and evaluation of the developed methods. The conclusion provides a summary of the research findings, conclusions drawn from the study, and recommendations for further research in the field of self-organizing intelligent mobile robots systems. Practical research materials are included in the appendix.
'/%3e%3cpath%20fill-rule='evenodd'%20clip-rule='evenodd'%20d='M17.5427%2012.684C17.1383%2011.7889%2016.7126%2011.771%2016.3278%2011.7553C16.0132%2011.7419%2015.6529%2011.7427%2015.2932%2011.7427C14.9333%2011.7427%2014.3483%2011.8774%2013.8537%2012.4152C13.3587%2012.9531%2011.9639%2014.2533%2011.9639%2016.8978C11.9639%2019.5426%2013.8987%2022.098%2014.1684%2022.4569C14.4383%2022.8153%2017.9033%2028.4156%2023.3907%2030.5701C27.9513%2032.3606%2028.8793%2032.0045%2029.8692%2031.9149C30.8591%2031.8253%2033.0633%2030.6149%2033.5133%2029.3597C33.9632%2028.1048%2033.9632%2027.0291%2033.8282%2026.8043C33.6932%2026.5803%2033.3333%2026.4459%2032.7933%2026.1771C32.2534%2025.9083%2029.5992%2024.6078%2029.1043%2024.4286C28.6093%2024.2494%2028.2494%2024.1598%2027.8894%2024.6979C27.5295%2025.2355%2026.4954%2026.4459%2026.1804%2026.8043C25.8655%2027.1635%2025.5505%2027.2083%2025.0105%2026.9395C24.4706%2026.6699%2022.7318%2026.1029%2020.6691%2024.2717C19.0641%2022.8472%2017.9806%2021.0877%2017.6656%2020.5496C17.3506%2020.012%2017.6318%2019.7209%2017.9027%2019.4529C18.1451%2019.2121%2018.4426%2018.8254%2018.7126%2018.5116C18.982%2018.1977%2019.072%2017.9737%2019.252%2017.6153C19.4319%2017.2564%2019.342%2016.9425%2019.207%2016.6737C19.072%2016.405%2018.0228%2013.7468%2017.5427%2012.684Z'%20fill='white'/%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_181_11959'%20x1='22.8525'%20y1='42.8177'%20x2='22.8525'%20y2='0.921701'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%2320B038'/%3e%3cstop%20offset='1'%20stop-color='%2360D66A'/%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
