MULTI-AGENT ARCHITECTURE OF AN ENVIRONMENT REPRESENTATION SYSTEM FOR AN AUTONOMOUS AGRICULTURAL ROBOT
Abstract
The relevance of this research stems from the need to create effective control systems for autonomous robots capable of operating in uncertain and dynamically changing environments. An environment representation system must address the challenges of localization, mapping, object detection and classification, dynamic prediction, and semantic interpretation. For an autonomous robot to navigate and perform goal-directed actions in its environment, it must understand its environment—without this, it will be unable to effectively plan movements, avoid obstacles, and reach destinations. Existing environment representation methods have limitations when adapting to unfamiliar, unstructured environments. The aim of this study is to develop the concept and architecture of an environment representation system based on a multi-agent neurocognitive architecture for controlling autonomous robots within a heterogeneous human-machine team. The scientific novelty of this study lies in the development of a multi-agent neurocognitive architecture for representing the state of the environment. The proposed approach enables the creation of flexible world models capable of self-organization and scalability with increasing knowledge. The research methodology is based on the use of multi-agent technologies and neurocognitive models. A multi-agent neurocognitive architecture has been developed, including mechanisms for collecting data from sensors, representing objects and subjects in the environment, forming a mechanism for constructing cause-and-effect relationships, and sharing knowledge between members of a heterogeneous human-machine team. The developed architecture enables the scalability of decision-making systems and facilitates knowledge sharing between team members. A promising direction for further research is improving the system's safety mechanisms. The results of this study can be used in the development of next-generation autonomous robotic systems.
References
1. Rakhmatillaev J., Bucinskas V., Kabulov N. An integrative review of control strategies in robotics, Ro-botic Systems and Applications, 2025, Vol. 5, No. 2, pp. 50-74. Available at: https://doi.org/10.21595/ rsa.2025.25014.
2. Cao C., et al. Representation granularity enables time-efficient autonomous exploration in large, complex worlds, Science Robotics, 2023, Vol. 8, No. 80, eadf0970. Available at: https://doi.org/10.1126/ sciro-botics.adf0970.
3. Lluvia I., Lazkano E., Ansuategi A. Active mapping and robot exploration: A survey, Sensors, 2021, Vol. 21, No. 7, pp. 2445. Available at: https://doi.org/10.3390/s21072445.
4. Magalhães S.A., Moreira A.P., Santos F.N.D., Dias J. Active perception fruit harvesting robots - A systematic review, Journal of Intelligent & Robotic Systems, 2022, Vol. 105, No. 1, pp. 14. Available at: https://doi.org/10.1007/s10846-022-01595-3.
5. Verkholantsev D.V. Algoritmy aktivnogo vospriyatiya vneshney sredy dlya avtonomnogo mobil'nogo robota [Algorithms for active perception of the external environment for an autonomous mobile robot], Sistemnaya inzheneriya i infokommunikatsii [Systems Engineering and Infocommunications], 2025, No. 1(1), pp. 11-16. Available at: https://doi.org/10.5281/zenodo.15110923.
6. Belyakov M.E., Diane S. Algoritmy vizual'nogo analiza vneshney sredy avtonomnym mobil'nym robot-om v zadache uborki territorii [Algorithms for visual analysis of the external environment by an autono-mous mobile robot in the task of cleaning the territory], Russian Technological Journal, 2023, Vol. 11(4), pp. 26-35. Available at: https://doi.org/10.32362/2500-316X-2023-11-4-26-35.
7. Warutumo D., et al. Perceptual Distortions and Autonomous Representation Learning in a Minimal Robotic System, arXiv preprint arXiv:2507.07845, 2025. Available at: https://doi.org/10.48550/arXiv.2507.07845.
8. Joo S.-H.,Manzoor S., Rocha Y.G., Bae S.-H., Lee K.-H., Kuc T.-Y., Kim M. Autonomous navigation framework for intelligent robots based on a semantic environment modeling, Applied Sciences, 2020, Vol. 10, No. 9, pp. 3219. Available at: https://doi.org/10.3390/app10093219.
9. Pavelina Yu.A., Popov I.Yu. Metod kollektivnogo analiza vneshney sredy avtonomnymi agentami v usloviyakh nepolnoty dannykh na osnove algoritma zhukov-usachey [Method of collective analysis of the external environment by autonomous agents under conditions of incomplete data based on the long-horn beetle algorithm], Nauchno-tekhnicheskiy vestnik informatsionnykh tekhnologiy, mekhaniki i optiki [Scientific and Technical Bulletin of Information Technologies, Mechanics and Optics], 2025, Vol. 25, No. 6,
pp. 1160-1167. Available at: https://doi.org/10.17586/2226-1494-2025-25-6-1160-1167.
10. Chen C., et al. A comprehensive survey of convergence analysis of beetle antennae search algorithm and its applications, Artificial Intelligence Review, 2024, Vol. 57, No. 6, pp. 141. Available at: https://doi.org/10.1007/s10462-024-10789-0.
11. Shan X., et al. Hybrid Strategy Improved Beetle Antennae Search Algorithm and Application, Applied Sciences, 2024, Vol. 14, No. 8, pp. 3286. Available at: https://doi.org/10.3390/app14083286.
12. Mamedova B.A.G., Ibadov S.S. Nechetkaya logika v upravlenii mobil'nymi robotami metody [Fuzzy logic in the control of mobile robots], Natsional'naya assotsiatsiya uchenykh [National Association of Scientists], 2022, No. 75-2, pp. 27-29.
13. Khairudin M., et al. The mobile robot control in obstacle avoidance using fuzzy logic controller, Indone-sian Journal of Science and Technology, 2020, Vol. 5, No. 3, pp. 334-351.
14. Riman C.F., Abi-Char P.E. Fuzzy logic control for mobile robot navigation in automated storage, Inter-national Journal of Mechanical Engineering and Robotics Research, 2023, Vol. 12, No. 5, pp. 313-323.
15. Wei Q., et al. Copeft: Fast adaptation framework for multi-agent collaborative perception with parameter-efficient fine-tuning, Proceedings of the AAAI Conference on Artificial Intelligence, 2025, Vol. 39, No. 22, pp. 23351-23359.
16. Nagoev Z.V. Intellektika, ili myshlenie v zhivykh i iskusstvennykh sistemakh [Intelligence, or thinking in living and artificial systems]. Nal'chik: Izd-vo KBNTS RAN, 2013, 211 p.
17. Bzhikhatlov K.Ch., Pshenokova I.A., Makoev A.R. Kontseptsiya sozdaniya sistemy upravleniya mul'tia-gentnoy robototekhnicheskoy sistemoy sel'skokhozyaystvennogo naznacheniya na baze neyrokogni-tivnykh algoritmov [Concept of creating a control system for a multi-agent robotic system for agricultural purposes based on neurocognitive algorithms], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2024, No. 3(239), pp. 6-18.
18. Nagoev Z., Bzhikhatlov K., Pshenokova I., Unagasov A. Algorithms and Software for Simulation of Intelligent Systems of Autonomous Robots Based on Multi-agent Neurocognitive Architectures, In: Ronzhin, A., Savage, J., Meshcheryakov, R. (eds), Interactive Collaborative Robotics. ICR 2024. Lec-ture Notes in Computer Science, 2024, Vol. 14898. Springer, Cham. DOI: https://doi.org/10.1007/978-3-031-71360-6_29.
19. Pshenokova I.A., Bzhikhatlov K.Ch., Unagasov A.A., Abazokov M.A. Mul'tiagentnyy algoritm sbora dannykh s meteostantsii dlya prognozirovaniya urozhaynosti i sostoyaniya posevov [Multi-agent algo-rithm for collecting data from a weather station to forecast crop yields and conditions], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2022, No. 1(225), pp. 91-101.
20. Pshenokova I.A., Nagoeva O.V., Apshev A.Z., Enes A.Z. Formirovanie dinamicheskikh prichinno-sledstvennykh zavisimostey pri upravlenii povedeniem intellektual'nogo agenta na osnove formalizma mul'tiagentnykh neyrokognitivnykh arkhitektur [Formation of dynamic cause-and-effect dependencies in controlling the behavior of an intelligent agent based on the formalism of multi-agent neurocognitive ar-chitectures], Izvestiya Kabardino-Balkarskogo nauchnogo tsentra RAN [News of the Kabardino-Balkarian Scientific Center of the RAS], 2022, No. 5(109), pp. 73-80. DOI: 10.35330/1991-6639-2022-5-109-73-80.
