МОДЕЛІ ТА МЕТОДИ ІНТЕЛЕКТУАЛЬНОГО КЕРУВАННЯ АВТОНОМНИМ РУХОМ МЕРЕЖІ МОБІЛЬНИХ СИСТЕМ У ДИНАМІЧНОМУ АНТРОПОГЕННОМУ СЕРЕДОВИЩІ

D. V. Patlai

doi:10.32782/2521-6643-2026-2-72.21

D. V. Patlai Odessa Polytechnic National University https://orcid.org/0009-0005-2070-5598

DOI: https://doi.org/10.32782/2521-6643-2026-2-72.21

Keywords: multi-agent system; intelligent control; heterogeneous robotic systems; adaptive coordination; multi-criteria optimization; social navigation; energy efficiency

Abstract

The article develops theoretical and methodological foundations and proposes architectural solutions for intelligent control of autonomous movement in heterogeneous networks of mobile robotic systems. The study addresses the problem of robotic platform operation in dynamic anthropogenic environments characterized by uncertainty, variable infrastructure constraints, and complex social interactions between technical agents and human participants. Such conditions require adaptive coordination mechanisms capable of ensuring safe and efficient collective behavior of heterogeneous autonomous systems. The aim of the research is to develop a unified multi-agent platform that enables synergistic interaction between ground unmanned vehicles (UGV) and unmanned aerial vehicles (UAV) for real-time optimization of logistics and monitoring processes in dynamically changing environments. Particular attention is given to ensuring coordination stability under partial observability and communication limitations. The methodological framework combines graph-theoretic representations of network topology, intelligent trajectory planning methods based on social penalty functions, and multi-criteria optimization techniques. A coordination model is proposed that incorporates dynamic estimation of human flow density and predictive motion vectors of environmental agents. The control architecture integrates hierarchical decision-making mechanisms allowing adaptive redistribution of tasks between heterogeneous agents depending on environmental conditions and operational constraints. The scientific novelty of the research lies in the development of an adaptive agent-selection algorithm based on cascade analysis of physical, meteorological, and social constraints. Unlike existing approaches, the proposed solution integrates principles of social navigation directly into a multi-level network control architecture, enabling reduction of interaction conflicts and improving coordination stability in dense human environments. Simulation-based validation demonstrated the feasibility of the proposed architecture under dynamically changing environmental conditions. The obtained results confirmed stable coordination of heterogeneous agents and adaptability of the control strategy to variations in social density, mission complexity, and communication limitations The practical significance of the study lies in the possibility of applying the developed architectural solutions and mathematical models to scalable autonomous urban logistics systems, last-mile delivery platforms, service robotics, and monitoring of complex infrastructure facilities. Future research directions include software implementation of the proposed methods in robotic simulation environments and quantitative evaluation of energy efficiency, scalability, and network resilience.

References

1. Macenski S., Foote T., Gerkey B., Lalancette S., Woodall W. The Robot Operating System 2: Design, architecture, and uses in the wild. Science Robotics. 2022. Vol. 7, No. 66. https://doi.org/10.1126/scirobotics. abm6074
2. Yang G., An L., Zhao C. Collision/Obstacle Avoidance Coordination of Multi-Robot Systems: A Survey. Actuators. 2025. Vol. 14, No. 2. Art. 85. https://doi.org/10.3390/act14020085
3. Thrun S., Burgard W., Fox D. Probabilistic robotics // Communications of the ACM. 2002. Vol. 45, No. 3. P. 52–57. https://doi.org/10.1145/504729.504754
4. International Organization for Standardization. ISO 8373:2021 Robots and robotic devices – Vocabulary. Geneva : ISO, 2021. URL: https://www.iso.org/standard/75539.html
5. Trautman P., Krause A. Unfreezing the robot: Navigation in dense, interacting crowds. Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2010. P. 797–803. URL: https://doi.org/10.1109/iros.2010.5654369
6. Rudenko A., Palmieri L., Herman M., Kitani K., Gavrila D., Arras K. Human motion trajectory prediction: A survey. The International Journal of Robotics Research. 2020. Vol. 39, No. 8. P. 895–935. https://doi.org/10.1177/0278364920917446
7. Chen C., Liu Y., Kreiss S., Alahi A. Crowd-Robot Interaction: Crowd-Aware Robot Navigation with Attention-Based Deep Reinforcement Learning. Proc. IEEE International Conference on Robotics and Automation (ICRA). 2019. P. 6015–6022. URL: https://doi.org/10.1109/ICRA.2019.8794134
8. Fox D., Burgard W., Thrun S. The dynamic window approach to collision avoidance. IEEE Robotics & Automation Magazine. 1997. Vol. 4, No. 1. P. 23–33. URL: https://ieeexplore.ieee.org/document/580977
9. Dorling K., Heinrichs J., Messier G., Magierowski S. Vehicle routing problems for drone delivery. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2017. Vol. 47, No. 1. P. 70–85. URL: https://ieeexplore.ieee.org/document/7505975
10. Waharte S., Trigoni N. Supporting search and rescue operations with UAVs. Proc. International Conference on Emerging Security Technologies. 2010. P. 142–147. URL: https://ieeexplore.ieee.org/document/5601296
11. Chung S.-J., Paranjape A., Dames P., Shen S., Kumar V. A survey on aerial swarm robotics. IEEE Transactions on Robotics. 2018. Vol. 34, No. 4. P. 837–855. URL: https://ieeexplore.ieee.org/document/8424819
12. Michael N., Fink J., Kumar V. Cooperative manipulation and transportation with aerial robots. Autonomous Robots. 2011. Vol. 30. P. 73–86. https://doi.org/10.1007/s10514-010-9205-0
13. Olfati-Saber R., Fax J., Murray R. Consensus and cooperation in networked multi-agent systems. Proceedings of the IEEE. 2007. Vol. 95, No. 1. P. 215–233. URL: https://ieeexplore.ieee.org/document/4118472
14. Zavlanos M., Pappas G. Distributed formation control with permutation symmetries. Proc. IEEE Conference on Decision and Control. 2007. URL: https://doi.org/10.1109/CDC.2007.4434527
15. Bușoniu L., Babuška R., De Schutter B. A comprehensive survey of multiagent reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics Part C. 2008. Vol. 38, No. 2. P. 156–172. URL: https://doi.org/10.1109/cec.2007.4424494
16. Makridakis S., Spiliotis E., Assimakopoulos V. Statistical and machine learning forecasting methods: Concerns and ways forward. PLoS ONE. 2018. Vol. 13, No. 3. e0194889. https://doi.org/10.1371/journal. pone.0194889
17. Laporte G. Fifty years of vehicle routing. Transportation Science. 2009. Vol. 43, No. 4. P. 408–416. https://doi.org/10.1287/trsc.1090.0301
18. Goodfellow I., Bengio Y., Courville A. Deep Learning. Cambridge : MIT Press, 2016. URL: https://www.deeplearningbook.org
19. Dellaert F., Hutchinson S. Probabilistic robotics: Algorithms and applications // Foundations and Trends in Robotics. 2020. Vol. 8, No. 1–2. P. 1–201. https://doi.org/10.1561/2300000052