An Attention-Based Temporal Graph Neural Network for Enhanced Multi-Unmanned Aerial Vehicle Obstacle Prediction
Received: 18 November 2025 | Revised: 22 December 2025 and 10 January 2026 | Accepted: 13 January 2026 | Online: 26 March 2026
Corresponding author: Samah Alzanin
Abstract
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.
Keywords:
obstacle prediction, Temporal Convolutional Network (TCN), Attention Mechanism (AM), Unmanned Aerial Vehicle (UAV), Deep Learning (DL)Downloads
References
S. A. H. Mohsan, M. A. Khan, F. Noor, I. Ullah, and M. H. Alsharif, "Towards the Unmanned Aerial Vehicles (UAVs): A Comprehensive Review," Drones, vol. 6, no. 6, June 2022, Art. no. 147. DOI: https://doi.org/10.3390/drones6060147
A. Ahmed and R. N. Farhan, "Autofocus Vision System Enhancement for UAVs via Autoencoder Generative Algorithm," Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 18867–18872, Dec. 2024. DOI: https://doi.org/10.48084/etasr.8519
P. Shukla, S. Shukla, and A. Kumar Singh, "Trajectory-Prediction Techniques for Unmanned Aerial Vehicles (UAVs): A Comprehensive Survey," IEEE Communications Surveys & Tutorials, vol. 27, no. 3, pp. 1867–1910, June 2025. DOI: https://doi.org/10.1109/COMST.2024.3471671
S. Rezwan and W. Choi, "Artificial Intelligence Approaches for UAV Navigation: Recent Advances and Future Challenges," IEEE Access, vol. 10, pp. 26320–26339, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3157626
X. Jia, P. Wu, L. Chen, Y. Liu, H. Li, and J. Yan, "HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 11, pp. 13860–13875, Nov. 2023. DOI: https://doi.org/10.1109/TPAMI.2023.3298301
K. Wu, Y. Zhou, H. Shi, X. Li, and B. Ran, "Graph-Based Interaction-Aware Multimodal 2D Vehicle Trajectory Prediction Using Diffusion Graph Convolutional Networks," IEEE Transactions on Intelligent Vehicles, vol. 9, no. 2, pp. 3630–3643, Feb. 2024. DOI: https://doi.org/10.1109/TIV.2023.3341071
L. Huajian, D. Wei, F. Kunpeng, W. Chao, and G. Yongzhuo, "PMM-Net: Single-Stage Multi-Agent Trajectory Prediction With Patching-Based Embedding and Explicit Modal Modulation," IEEE Robotics and Automation Letters, vol. 10, no. 7, pp. 6664–6671, July 2025. DOI: https://doi.org/10.1109/LRA.2025.3568623
Z. Wang, J. Zhang, J. Chen, and H. Zhang, "Spatio-Temporal Context Graph Transformer Design for Map-Free Multi-Agent Trajectory Prediction," IEEE Transactions on Intelligent Vehicles, vol. 9, no. 1, pp. 1369–1381, Jan. 2024. DOI: https://doi.org/10.1109/TIV.2023.3329885
Z. Gao, M. Bao, F. Gao, and M. Tang, "Probabilistic multi-modal expected trajectory prediction based on LSTM for autonomous driving," Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, vol. 238, no. 9, pp. 2817–2828, Aug. 2024. DOI: https://doi.org/10.1177/09544070231167906
B. Yang, J. Yang, R. Ni, C. Yang, and X. Liu, "Multi-granularity scenarios understanding network for trajectory prediction," Complex & Intelligent Systems, vol. 9, no. 1, pp. 851–864, Feb. 2023. DOI: https://doi.org/10.1007/s40747-022-00834-2
X. Chen, H. Zhang, Y. Hu, J. Liang, and H. Wang, "VNAGT: Variational Non-Autoregressive Graph Transformer Network for Multi-Agent Trajectory Prediction," IEEE Transactions on Vehicular Technology, vol. 72, no. 10, pp. 12540–12552, Oct. 2023. DOI: https://doi.org/10.1109/TVT.2023.3273230
J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Burlington, MA, USA: Morgan Kaufmann Publishers, 2012.
T. Kipf and M. Welling, "Semi-Supervised Classification with Graph Convolutional Networks," in Proceedings of the 5th International Conference on Learning Representations, 2017.
C. Lea, R. Vidal, A. Reiter, and G. D. Hager, "Temporal Convolutional Networks: A Unified Approach to Action Segmentation," in 14th European Conference on Computer Vision, Amsterdam, Netherlands, 2016, pp. 47–54. DOI: https://doi.org/10.1007/978-3-319-49409-8_7
"UAV Autonomous Navigation Dataset." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/ziya07/uav-autonomous-navigation-dataset.
L. Wang et al., "Image-based obstacle detection methods for the safe navigation of industrial unmanned aerial vehicles," Scientific Reports, vol. 15, no. 1, Oct. 2025, Art. no. 36063. DOI: https://doi.org/10.1038/s41598-025-19904-9
Downloads
How to Cite
License
Copyright (c) 2026 Samah Alzanin
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
