Journal of Radio Electronics. eISSN 1684-1719. 2026. ¹6

Contents

Full text in Russian (pdf)

Russian page

 

 

DOI: https://doi.org/10.30898/1684-1719.2026.6.1

 

 

 

A method for synthesizing a multi-agent architecture

for unmanned aerial systems

based on modular procedural memory

 

I.A. Slepova, A.L. Feder

 

Mozhaisky Military Aerospace Academy,

197198, Sankt-Peterburg, Zhdanovskaya str., 13

 

The paper was received May 3, 2026.

 

Abstract. The article presents a method for synthesizing the multi-agent architecture of unmanned aircraft systems based on modular procedural memory. The aim of the study is to develop a formalized mechanism for the dynamic layout of behavioral modules of swarm agents of unmanned aircraft systems without the use of neural network learning methods. An algebraic model of a multi-agent system is proposed. Each module of procedural memory is formalized as a set of four, including preconditions, postconditions, an executive unit, and a type of synchronization. Synthesis of architecture through a heuristic algorithm for purposefully selecting compatible procedures in the dependency graph. Simulation modeling was carried out on the scenario of a swarm of 50 agents. The scientific novelty lies in the application of procedural abstraction as the basis for the dynamic synthesis of the architecture of swarm control systems. The results obtained are applicable in the tasks of distributed monitoring, search and rescue operations and autonomous patrolling.

Key words: multi-agent systems; unmanned aerial systems; procedural memory; swarm algorithms; distributed planning; architecture synthesis; procedural abstraction; dynamic assembly; dependency graph; swarm control.

Corresponding author: Feder Aleksandr Lvovich, article_feder@mail.ru

 

References

1. Dorri A. et al. Multi-agent systems: A survey // Ieee Access. – 2018. – Ò. 6. – Ñ. 28573-28593. https://doi.org/10.1109/ACCESS.2018.2831228

2. Leonov A.V., Chaplyshkin V.A. Swarm intelligence for UAV control in FANET // Molodoy uchenyy. – 2016. – ¹. 12. – Ñ. 314-317. (In Russian)

3. Tsviyovich A., Bykovtsev Yu., Man'ko S. Hybrid algorithm for exploring an unknown environment by mobile robots based on ABC, PSO, and Boids algorithms with memory and inter-swarm exchange mechanisms // Sistemnaya inzheneriya i infokommunikatsii. – 2026. – ¹. 2. – Ñ. 11-18. (In Russian)

4. Tikhonov M.K. Comparative analysis of deep reinforcement learning algorithms DDPG, PPO, and SAC for autonomous vehicle control in the CARLA simulator // Nauchnyy rezultat. Informatsionnye tekhnologii. – 2024. – Ò. 9. – ¹. 2. – Ñ. 69-74. https://doi.org/10.18413/2518-1092-2024-9-2-0-8 (In Russian)

5. Skobelev P.O. et al. Application of ontology in an intelligent system for distributed control of a group of small spacecraft // Izvestiya Samarskogo nauchnogo tsentra Rossiyskoy akademii nauk. – 2015. – Ò. 17. – ¹. 2-5. – Ñ. 1119-1130. (In Russian)

6. Demidov R.A., Zegzhda P.D. Unified model of multilevel information security threats in networks with dynamic topology // Intellektual'nye tekhnologii na transporte. – 2019. – ¹. 2 (18). – Ñ. 10-14. (In Russian)

7. Ermilov A.S., Saltykova O.A. Multi-agent control systems for a group of unmanned aerial vehicles // Naukoemkie tekhnologii v kosmicheskikh issledovaniyakh Zemli. – 2025. – Ò. 17. – ¹. 1. – Ñ. 4-10. https://doi.org/10.36724/2409-5419-2025-17-1-4-10 (In Russian)

8. Van Dyke Parunak H., Brueckner S. Entropy and self-organization in multi-agent systems // Proceedings of the fifth international conference on Autonomous agents. – 2001. – Ñ. 124-130.

9. Wooldridge M. An introduction to multiagent systems. – John wiley & sons, 2009.

10. Zakharov N.S., Kharisov A.R. Numerical simulation of swarm control algorithms for autonomous groups of unmanned aerial vehicles // Vestnik nauki. – 2025. – Ò. 3. – ¹. 6 (87). – Ñ. 1935-1945. (In Russian)

11. Petrenko V.I. et al. Task distribution in a clustered target field for homogeneous and heterogeneous groups of UAVs // Robototekhnika i tekhnicheskaya kibernetika. – 2023. – Ò. 11. – ¹. 2. – Ñ. 99-109. https://doi.org/10.31776/RTCJ.11203 (In Russian)

12. Bellemare M.G., Dabney W., Munos R.A distributional perspective on reinforcement learning // International conference on machine learning. – Pmlr, 2017. – Ñ. 449-458.

13. Alonso-Mora J. et al. Collision avoidance for aerial vehicles in multi-agent scenarios // Autonomous Robots. – 2015. – Ò. 39. – ¹. 1. – Ñ. 101-121.

For citation:

Slepova I.A., Feder A.L. A method for synthesizing a multi-agent architecture for unmanned aerial systems based on modular procedural memory // Journal of Radio Electronics. – 2026. – ¹. 6. https://doi.org/10.30898/1684-1719.2026.6.1 (In Russian)