A Mathematical Framework for Drone-Based Wildfire Search and Rescue Using Grid-Based Coverage Path Planning and Vision-Guided Adaptive Control
DOI:
https://doi.org/10.62051/ead8j784Keywords:
Quadcopter; Wildfire; YOLOv8; Coverage Path Planning; Vision-Guided Control; Precision Airdrop.Abstract
Wildfires in drought-prone forest regions create urgent search-and-rescue challenges, including limited ground access, low coverage efficiency, and high risk to both victims and rescuers. This study proposes and tests an intelligent quadcopter rescue system, Fire Eagle Rescuer, that integrates victim localization, emergency supply delivery, and localized fire-suppression support. The system first discretizes the search environment into a two-dimensional grid and uses an S-shaped coverage path-planning model to ensure systematic area coverage. A YOLOv8-based vision model is then used for fire and trapped-person detection, with ONNX optimization improving onboard inference speed from approximately 3-4 fps to 20-30 fps in the test setting. For target alignment and delivery, the model combines first-order proportional feedback control with a gravity-assisted airdrop model that accounts for linear air resistance. Multi-physics simulation and field-test data indicate that the system can support centimeter-level localization with RTK positioning and achieve high-precision payload delivery under controlled wildfire-simulation conditions. Across ten autonomous test missions, the system deployed 19 fire-suppression capsules and 8 emergency medical kits, demonstrating the practical potential of integrating mathematical path planning, vision-guided control, and airdrop dynamics for drone-based wildfire search and rescue.
Downloads
References
[1] Choset, H. Coverage of Known Spaces: The Boustrophedon Cellular Decomposition. Autonomous Robots 9, 247-253 (2000). https://doi.org/10.1023/A:1008958800904.
[2] Apostolidis, S. D.; Vougiatzis, G.; Kapoutsis, A. C.; Chatzichristofis, S. A.; Kosmatopoulos, E. B. Systematically Improving the Efficiency of Grid-Based Coverage Path Planning Methodologies in Real-World UAVs' Operations. Drones 2023, 7(6), 399. https://doi.org/10.3390/drones7060399.
[3] Diwan, T.; Anirudh, G.; Tembhurne, J. V. Object Detection Using YOLO: Challenges, Architectural Successors, Datasets and Applications. Multimedia Tools and Applications 2023, 82(6), 9243-9275. https://doi.org/10.1007/s11042-022-13644-y.
[4] Jocher, G.; Chaurasia, A.; Qiu, J. Ultralytics YOLO, Version 8.0.0 [Computer software]. Ultralytics, 2023. https://github.com/ultralytics/ultralytics.
[5] Zheng, Z.; Wang, P.; Liu, W.; Li, J.; Ye, R.; Ren, D. Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence 2020, 34(7), 12993-13000. https://doi.org/10.1609/aaai.v34i07.6999.
[6] Li, X.; Wang, W.; Wu, L.; Chen, S.; Hu, X.; Li, J.; Tang, J.; Yang, J. Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection. Advances in Neural Information Processing Systems 33, 2020. arXiv:2006.04388.
[7] ONNX Runtime. Graph Optimizations in ONNX Runtime. Microsoft ONNX Runtime Documentation. Accessed 2026.
[8] ONNX Runtime. Quantize ONNX Models. Microsoft ONNX Runtime Documentation. Accessed 2026.
[9] Chaumette, F.; Hutchinson, S. Visual Servo Control, Part I: Basic Approaches. IEEE Robotics & Automation Magazine 2006, 13(4), 82-90. https://doi.org/10.1109/MRA.2006.250573.
[10] Morales, C. A.; Munoz, J. H.; Vera, C. E. Some Remarks on Projectile Motion with a Linear Resistance Force. arXiv:2310.01776, 2023.
[11] PX4 Autopilot Documentation. ROS with Gazebo Classic Simulation. PX4 User Guide. Accessed 2026.
[12] PX4 Autopilot Documentation. MAVROS Offboard Control Example (Python). PX4 User Guide. Accessed 2026.
[13] NovAtel. Real-Time Kinematics (RTK). An Introduction to GNSS. Hexagon/NovAtel Technical Documentation. Accessed 2026.
[14] Nelson, W. Use of Circular Error Probability in Target Detection. MITRE Corporation Technical Report ESD-TR-88-109 / MTR-10293, 1988.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Transactions on Computer Science and Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
