Exploring Window-Level Drone Delivery in Urban Air Logistics
DOI:
https://doi.org/10.54097/1b1x0z19Keywords:
Window-level UAVs delivery; sensor fusion; urban air logistics.Abstract
Window-level UAVs delivery applies to the emerging field of urban air logistics, enabling autonomous UAVs to deliver packages directly to building windows. However, unprecedented levels of precision, perception, and adaptability in complex, GPS-denied environments are required to achieve reliable window-level operation. This paper provides a systematic review of the key technological advances making this challenging scenario possible. How the fusion of visual, LiDAR, and inertial sensing, which is enhanced by deep learning and semantic SLAM, enables centimeter-level localization among urban canyons. Robust window detection is addressed through hybrid methods that combine geometric efficiency with deep semantic understanding, improving accuracy under architectural repetition and occlusion. Furthermore, intelligent navigation strategies have been developed to support real-time obstacle avoidance and smooth trajectory generation in cluttered airspace. These incorporate reinforcement learning with dynamic window constraints and factor graph optimization. Critical challenges remain in sensor resilience, energy efficiency during vertical operation, generalization across diverse urban forms, and scalable multi-UAV coordination despite progress. This review integrates current advancements and highlights future research needs, thereby providing a foundational reference for the development of reliable, precise, scalable and adaptable window-level UAV delivery systems in smart cities.
Downloads
References
[1] Zhang, X., Tian, Y., Lin, F., Liu, Y., Ma, J., Szatmáry, K. S., & Wang, F. Y. (2025). LogisticsVLN: Vision-Language Navigation For Low-Altitude Terminal Delivery Based on Agentic UAVs. arXiv preprint arXiv:2505.03460.
[2] Tomasz Dudek, Karolina Kaśkosz, Optimizing drone logistics in complex urban industrial infrastructure, Transportation Research Part D: Transport and Environment, Volume 140, 2025, 104610, ISSN 1361-9209, https://doi.org/10.1016/j.trd.2025.104610.
[3] Rinaldi, M., Primatesta, S., Bugaj, M., Rostáš, J., & Guglieri, G. (2024). Urban Air Logistics with Unmanned Aerial Vehicles (UAVs): Double-Chromosome Genetic Task Scheduling with Safe Route Planning. Smart Cities, 7(5), 2842-2860.
[4] O. Y. Al-Jarrah, A. S. Shatnawi, M. M. Shurman, O. A. Ramadan and S. Muhaidat, "Exploring Deep Learning-Based Visual Localization Techniques for UAVs in GPS-Denied Environments," in IEEE Access, vol. 12, pp. 113049-113071, 2024.
[5] Norbelt, M., Luo, X., Sun, J., & Claude, U. (2025). UAV Localization in Urban Area Mobility Environment Based on Monocular VSLAM with Deep Learning. Drones, 9(3), 171.
[6] Bodi MA, Zhenbao LIU, Feihong JIANG, Wen ZHAO, Qingqing DANG, Xiao WANG, Junhong ZHANG, Lina WANG, Reinforcement learning based UAV formation control in GPS-denied environment, Chinese Journal of Aeronautics, Volume 36, Issue 11, 2023, Pages 281-296, ISSN 1000-9361.
[7] S.M. Iman Zolanvari, Debra F. Laefer, Slicing Method for curved façade and window extraction from point clouds, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 119, 2016, Pages 334-346, ISSN 0924-2716.
[8] Shengming Li, Linsong Xue, Lin Feng, Cuili Yao, Dong Wang, Hybrid Convolutional-Transformer framework for drone-based few-shot weakly supervised object detection, Computers and Electrical Engineering, Volume 102, 2022, 108154, ISSN 0045-7906.
[9] Nordmark, N., & Ayenew, M. (2021). Window Detection In Facade Imagery: A Deep Learning Approach Using Mask R-CNN. ArXiv, abs/2107.10006.
[10] Li, CK., Zhang, HX., Liu, JX. et al. Window Detection in Facades Using Heatmap Fusion. J. Comput. Sci. Technol. 35, 900–912 (2020).
[11] Chuanbo Wu, Wangneng Yu, Guangze Li, Weiqiang Liao, Deep reinforcement learning with dynamic window approach based collision avoidance path planning for maritime autonomous surface ships, Ocean Engineering, Volume 284, 2023, 115208, ISSN 0029-8018.
[12] R. Chai, A. Tsourdos, A. Savvaris, S. Wang, Y. Xia and S. Chai, "Fast Generation of Chance-Constrained Flight Trajectory for Unmanned Vehicles," in IEEE Transactions on Aerospace and Electronic Systems, vol. 57, no. 2, pp. 1028-1045, April 2021.
[13] P. Yang and W. Wen, "Tightly Joining Positioning and Control for Trustworthy Unmanned Aerial Vehicles Based on Factor Graph Optimization in Urban Transportation," 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, Spain, 2023, pp. 3589-3596.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
