Skip to content
Conference Open access

GHAAT: An End-to-End Autonomous Counter-UAV Framework with Vision Guidance and Net Capture

Oct 2026 · 2026 20th Biennial Baltic Electronics Conference (BEC) · pp. 1-6 · 0 citations · 16 references

Abstract

Unauthorized Unmanned Aerial Vehicle (UAVs) lacking Global Positioning System (GPS) or Radio Frequency (RF) signatures pose significant security challenges. This paper presents Guarding High-value Airspace Against Threats (GHAAT), an autonomous vision-based UAV interception framework integrating detection, localization, guidance, and capture in Robot Operating System (ROS) 2. The proposed system employs a hybrid Image-Based Visual Servoing (IBVS) and Proportional Navigation (PN) guidance strategy for target engagement, while a 9-state Kalman filter provides robust state estimation. Real-time perception is achieved using a You Only Look Once (YOLO)-based model deployed on an NVIDIA Jetson Orin Nano for drone detection and classification. To enable non-destructive neutralization, the platform incorporates a low-cost autonomous CO2-powered net capture mechanism integrated with onboard mission management. The complete system is deployed on a 950 mm hexacopter and has been validated by ground testing and test flights under different lighting and backgrounds. Experimental results demonstrate successful autonomous target interception and capture with an all-up vehicle weight of approximately 6 kg. The proposed framework offers a scalable and cost-effective solution for autonomous aerial monitoring and intervention applications.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.