VISUAL COORDINATION METHOD FOR AN AUTONOMOUS UNMANNED AERIAL VEHICLE FORMATION
Keywords:
UAV, Visual Coordination, ROS 2, PX4, Adaptive Kalman Filter, Trajectory Prediction, Occlusion HandlingAbstract
This paper addresses the problem of maintaining stable visual coordination in UAV formations with a leader-follower topology under conditions of total target occlusion and the absence of any data input other than visual observation. Although modern deep learning-based predictors demonstrate high accuracy, their computational complexity often limits their deployment on resource-constrained onboard systems. I propose a lightweight coordination framework that combines YOLO (You Only Look Once)-based detection with an Adaptive Kalman Filter (AKF), integrated into the ROS 2 and PX4 ecosystem. The core of the method lies in a dynamic scaling mechanism for the process noise covariance, which allows the system to transition into an inertial prediction mode during the loss of visual contact.
Experimental results obtained in the Gazebo simulation environment demonstrate that the proposed AKF reduces positioning Root Mean Square Error (RMSE) by 50% during non-linear maneuvers compared to standard estimation methods. The system achieved a 97% success rate in maintaining formation in cluttered environments with occlusions lasting up to 5 seconds. These results confirm that the developed method provides a reliable and computationally efficient solution for autonomous UAV operations in complex urban settings without relying on external positioning systems.
References
Lin P.-T., Wu R.-B., Chang S.-C. Leader-Follower UAV Formation Control with Cost-Effective Coordination and Pre-Flight Simulation. Drones. 2026. Vol. 10, no. 4. Art. 286. URL: https://doi.org/10.3390/drones10040286 (date of access: 03.05.2026).
Aurora: Automated ROS2 Integration and Reliability Assessment Testbed for PX4-Based UAVs / A. Authors et al. ResearchGate. 2026. URL: https://www.researchgate.net/publication/399169204 (date of access: 03.05.2026).
Research on UAV Autonomous Trajectory Planning Based on Prediction Information in Crowded Unknown Dynamic Environments / B. Authors et al. Sensors. 2025. Vol. 25, no. 23. Art. 7343. URL: https://doi.org/10.3390/s25237343 (date of access: 03.05.2026).
Comparative Study of YOLOv10, YOLOv11 and YOLOv12 Lightweight Models for Multi-Class Maritime Search and Rescue Using UAV Imagery / C. Authors et al. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2025. Vol. XLVIII-1/W6-2025. P. 199-204. URL: https://doi.org/10.5194/isprs-archives-XLVIII-1-W6-2025-199-2025 (date of access: 03.05.2026).
Trajectory Prediction in Dynamic Object Tracking: A Critical Study / D. Authors et al. arXiv. 2025. URL: https://arxiv.org/abs/2506.19341v1 (date of access: 03.05.2026).
Adaptive Federated Kalman Filtering with Dimensional Isolation for Unmanned Aerial Vehicle Navigation in Degraded Industrial Environments / E. Authors et al. Drones. 2025. Vol. 9, no. 3. Art. 168. URL: https://doi.org/10.3390/drones9030168 (date of access: 03.05.2026).
Genovese A. Interacting Multiple Model (IMM) Filter for UAV Maneuvering Target Tracking: A Performance Study. Journal of Guidance, Control, and Dynamics. 2025. Vol. 48, no. 2. P. 112-125.
