Received 12.08.2025; Revised 30.10.2025; Accepted 18.11.2025

Published 08.12.2025; First Online 15.12.2025

https://doi.org/10.34229/2707-451X.25.4.9

Previous  |  FULL TEXT (in Ukrainian)  |  Next

 

MSC 68T05, 68U10

Comparison of Neural Network Architectures for Spatial Orientation of Unmanned Aerial Vehicles and Ground Drones

Oleksandr Suslenko

V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine, Kyiv

Correspondence: This email address is being protected from spambots. You need JavaScript enabled to view it.

 

Introduction. Ensuring spatial orientation of unmanned aerial vehicles (UAVs) and ground drones is one of the key tasks in modern robotics and autonomous systems. Traditional methods, such as SLAM or GNSS-IMU integration, have significant limitations in complex environments where sensor data is noisy or satellite signals are unavailable. In such cases, deep learning approaches, in particular neural network architectures for segmentation and object detection, are promising as they enable drones to interpret their surroundings at the semantic level.

Purpose. The purpose of this work is to conduct a comparative analysis of segmentation neural network architectures (U-Net, DeepLabV3+) and object detection architectures (YOLO, SSD, Faster R-CNN) regarding their applicability to solving the problem of spatial orientation of UAVs and ground drones in real time, as well as to identify the advantages and disadvantages of both approaches depending on the operating environment and computational resources.

Methods. The study employed an experimental approach using UAVid datasets and synthetic aerial imagery. To evaluate the effectiveness of the selected architectures, the following indicators were analyzed: accuracy (mIoU, mAP), speed (FPS), and resource requirements (number of parameters, computational complexity). Special attention was given to the use of segmentation models for constructing semantic maps of the environment and object detectors for localizing reference landmarks.

Results. The experiments demonstrated that segmentation architectures (U-Net, DeepLabV3+) provide more precise representation of object shapes and allow the construction of highly detailed maps, which is critical in environments with irregular obstacles (forests, mountainous areas). At the same time, object detectors (YOLO, SSD) showed significantly higher real-time performance, making them more suitable for systems with limited computational resources. Faster R-CNN achieved higher accuracy but lagged in processing speed. It was shown that segmentation models make it possible to estimate traversability between objects and classify surface types, tasks that are unattainable with traditional bounding box detectors.

Conclusions. Segmentation architectures provide drones with richer semantic information for spatial orientation but require higher computational resources and demonstrate lower inference speed. Object detection architectures are capable of real-time operation but at the cost of reduced environmental detail. A combined approach, applying both methods depending on navigation tasks and resource constraints, is considered promising. Future research should focus on developing hybrid multi-output models that combine the advantages of segmentation and detection.

 

Keywords: spatial orientation, unmanned aerial vehicles, neural networks, semantic segmentation, object detection, U-Net, YOLO, DeepLabV3+, Faster R-CNN.

 

Cite as: Suslenko O. Comparison of Neural Network Architectures for Spatial Orientation of Unmanned Aerial Vehicles and Ground Drones. Cybernetics and Computer Technologies. 2025. 4. P. 99–105. (in Ukrainian) https://doi.org/10.34229/2707-451X.25.4.9

 

References

           1.     Jaulin L. A nonlinear set-membership approach for the localization and map building of an underwater robot using interval constraint propagation. IEEE Transactions on Robotics. 2009. Vol. 25, No. 1. P. 88–98. https://doi.org/10.1109/TRO.2008.2010358

           2.     Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Springer, Cham, 2015. P. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28

           3.     Chen L.-C., Zhu Y., Papandreou G., Schroff F., Adam H. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision (ECCV). Springer, 2018. P. 801–818. https://doi.org/10.1007/978-3-030-01234-2_49

           4.     Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. P. 779–788. https://doi.org/10.1109/CVPR.2016.91

           5.     Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C.-Y., Berg A. C. SSD: Single Shot MultiBox Detector. Proceedings of the European Conference on Computer Vision (ECCV). Springer, 2016. P. 21–37. https://doi.org/10.1007/978-3-319-46448-0_2

           6.     Ren S., He K., Girshick R., Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. dvances in Neural Information Processing Systems (NeurIPS). 2015. P. 91–99. https://arxiv.org/abs/1506.01497

           7.     Schiefer F., Kattenborn T., Frick A., Frey J., Schmidtlein S. Mapping forest tree species in high-resolution UAV-based RGB imagery by means of convolutional neural networks. ISPRS Journal of Photogrammetry and Remote Sensing. 2020. Vol. 170. P. 205–215. https://doi.org/10.1016/j.isprsjprs.2020.10.016

           8.     Xia G.-S., Bai X., Ding J., Zhu Z., Belongie S., Luo J., Datcu M., Pelillo M., Zhang L. DOTA: A Large-scale Dataset for Object Detection in Aerial Images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018. P. 3974–3983. https://doi.org/10.1109/CVPR.2018.00418

           9.     Hu S., Liu J., Kang Z. DeepLabV3+/EfficientNet Hybrid Network for Complex Scene Segmentation and Safe Landing Zone Detection. Sensors. 2021. 21 (23). Article 8136. https://doi.org/10.3390/s21238136

       10.     Anagnostis A., Zampogiannis K., et al. Deep Learning-based Semantic Segmentation for UAV-based Orchard and Forest Monitoring. Remote Sensing. 2021. 13 (12). Article 2364. https://doi.org/10.3390/rs13122364

 

 

ISSN 2707-451X (Online)

ISSN 2707-4501 (Print)

Previous  |  FULL TEXT (in Ukrainian)  |  Next