Dynamic Routing of Unmanned Aerial Vehicles: Current State and Development Prospects
Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì · 22.06.2026 · 19 · 27-42
DOI: 10.23939/sisn2026.19.027 ↗Kurz gefasst
Fachartikel in der Zeitschrift Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì, online erschienen am 17.05.2026. Verfasst von Volodymyr Pavlysh und 1 weiteren Autor:innen. Die Arbeit nennt 78 Literaturangaben.
Abstract (Originalsprache)
The paper presents an integrated framework for dynamic routing of unmanned aerial vehicles (UAVs) operating in, uncertain, and rapidly changing environments. After reviewing classical deterministic, sampling complex -based, bio-inspired, machine learning, and hybrid path-planning methods, their limitations with respect to real-time replanning, energy efficiency, and scalability to multi-UAV missions are critically analysed. To address these gaps, the work proposes a neuro-fuzzy routing architecture embedded into the generic perception–prediction–planning–safe execution loop of an autonomous agent. The architecture combines multimodal sensor fusion, world-model learning, and graph-based neural networks with a hierarchical control policy, where a high-level mission planner generates waypoints and a low-level reactive controller ensures fine-grained trajectory tracking and obstacle avoidance. Fuzzy inference of Mamdani and Takagi–Sugeno type is integrated with trainable membership functions and rule bases, yielding an interpretable yet adaptive controller that can be optimised using hybrid learning and reinforcement learning. Control barrier functions and model-predictive control are used to enforce hard safety constraints such as no-fly zones, altitude limits, and collision-free motion. Particular attention is paid to principled treatment of uncertainty, energy-aware optimisation, and mitigation of the simulation-to-reality gap when transferring policies from high-fidelity simulators to real UAV platforms. The paper outlines how the proposed framework can be extended to distributed routing and coordination in UAV swarms via message-passing over communication graphs. Finally, an evaluation protocol is sketched that includes safety, mission performance, energy consumption, calibration of predictive uncertainty, and Sim2Real transfer metrics, and future research directions toward formally certified, scalable, and environmentally aware UAV routing systems are discussed.
Zitieren
APA
Pavlysh, V., & Shakhovska, N. (2026). Dynamic Routing of Unmanned Aerial Vehicles: Current State and Development Prospects. Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì, 19, 27-42. https://doi.org/10.23939/sisn2026.19.027
Vancouver
Pavlysh V, Shakhovska N. Dynamic Routing of Unmanned Aerial Vehicles: Current State and Development Prospects. Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì. 2026;19:27-42. doi:10.23939/sisn2026.19.027
BibTeX
@article{Pavlysh2026,
author = {Pavlysh, Volodymyr and Shakhovska, Natalia},
title = {Dynamic Routing of Unmanned Aerial Vehicles: Current State and Development Prospects},
journal = {Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì},
year = {2026},
volume = {19},
pages = {27--42},
doi = {10.23939/sisn2026.19.027}
}
EUVIMED