EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sensor Data Adaptive Treatment in Time-Varying UAV Medium: Approaches and Methods

Dmytro Borovyk, Mykola Zaretskyi

Engineering, Technology & Applied Science Research · 04.04.2026 · 16 (2) · 33113-33122

DOI: 10.48084/etasr.16045 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 04.04.2026. Verfasst von Dmytro Borovyk und 1 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unmanned Aerial Vehicles (UAVs) that can navigate independently in a variety of situations are in high demand. Thus, distinct UAV configurations that incorporate a range of components, including communication devices, navigation sensors, and additional payloads, are needed, necessitating the development of action models which take into account the dynamic environment and operational goals while limiting the use of resources. The current study presents an integrative review of approaches, methods, concerns, and prospects in the field of adaptive sensor data treatment in a time-varying UAV environment. It provides a comprehensive overview of UAV route planning approaches, such as integrated algorithmic frameworks, biologically inspired approaches, stochastic sampling techniques, and deterministic models. The literature review revealed that sensing accuracy directly affects performance, while substantial research has been conducted to provide trustworthy sensing data to guarantee normal flying. Moreover, it is believed that the prediction accuracy of current filter-based statistical models is independent of the flying conditions. This research highlights the effectiveness of recent data-driven adaptive fusion state-space models in measuring the prediction uncertainty of the system model to prevent degradation in the performance estimation. The study also reviews techniques for adjusting the noise parameter of the statistical model based on the estimated variance, depending on the multi-output Gaussian Process Regression (GPR). The sparse GPR model is proposed for incorporating available characteristics and achieving high estimation accuracy under dynamic operating situations.

Zitieren

APA

Borovyk, D., & Zaretskyi, M. (2026). Sensor Data Adaptive Treatment in Time-Varying UAV Medium: Approaches and Methods. Engineering, Technology & Applied Science Research, 16(2), 33113-33122. https://doi.org/10.48084/etasr.16045

Vancouver

Borovyk D, Zaretskyi M. Sensor Data Adaptive Treatment in Time-Varying UAV Medium: Approaches and Methods. Engineering, Technology & Applied Science Research. 2026;16(2):33113-33122. doi:10.48084/etasr.16045

BibTeX
@article{Borovyk2026,
  author = {Borovyk, Dmytro and Zaretskyi, Mykola},
  title = {Sensor Data Adaptive Treatment in Time-Varying UAV Medium: Approaches and Methods},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {33113--33122},
  doi = {10.48084/etasr.16045}
}
Kostenlos starten →