EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Attention-Based Temporal Graph Neural Network for Enhanced Multi-Unmanned Aerial Vehicle Obstacle Prediction

Samah Alzanin

Engineering, Technology & Applied Science Research · 04.04.2026 · 16 (2) · 32907-32912

DOI: 10.48084/etasr.16356 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 04.04.2026. Verfasst von Samah Alzanin. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, Unmanned Aerial Vehicles (UAVs) have shown promise for autonomous sensing. UAVs are employed for many applications that comprise mapping, surveillance, tracking, and searching operations. Discovering an effective path between available resources and a target goal is a vital concern and has been the focus of recent research. Various path-planning models are employed to find an effective path for a UAV to navigate from a resource to a goal with obstacle avoidance. Artificial Intelligence (AI) is a growing technology finding applications in multiple industries. The incorporation of AI into UAVs is inducing rapid growth in this area by improving efficacy and flight safety. Machine Learning (ML) models enable UAVs to make real-time decisions in complex environments, achieving optimal solutions under hardware constraints. Various analyses of UAVs have utilized numerous ML approaches to improve the performance of UAVs. This article introduces a novel framework titled Attention-based Temporal Graph Neural Network for Multi-Unmanned Aerial Vehicle Obstacle Prediction (ATGN-MUAVOP). The aim is to accurately classify potential obstacles to improve the efficiency of autonomous UAV navigation. Initially, z-score normalization is used to standardize the input features. For effective obstacle prediction, a Graph Convolutional Network (GCN) method is employed. Furthermore, a Temporal Convolutional Network with an Attention Mechanism (TCN-AM) is applied for classification. The performance validation of the ATGN-MUAVOP methodology illustrates a superior accuracy of 98.28% over existing methods on the UAV Autonomous Navigation dataset.

Zitieren

APA

Alzanin, S. (2026). An Attention-Based Temporal Graph Neural Network for Enhanced Multi-Unmanned Aerial Vehicle Obstacle Prediction. Engineering, Technology & Applied Science Research, 16(2), 32907-32912. https://doi.org/10.48084/etasr.16356

Vancouver

Alzanin S. An Attention-Based Temporal Graph Neural Network for Enhanced Multi-Unmanned Aerial Vehicle Obstacle Prediction. Engineering, Technology & Applied Science Research. 2026;16(2):32907-32912. doi:10.48084/etasr.16356

BibTeX
@article{Alzanin2026,
  author = {Alzanin, Samah},
  title = {An Attention-Based Temporal Graph Neural Network for Enhanced Multi-Unmanned Aerial Vehicle Obstacle Prediction},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {32907--32912},
  doi = {10.48084/etasr.16356}
}
Kostenlos starten →