Abstract:

This article presents a visual navigation system for small Unmanned Aerial Vehicles (UAVs) designed to operate in environments where GNSS signals may be unreliable or disrupted due to a range of factors, including jamming systems, adverse weather conditions, or environmental obstacles. The primary goal of this work is to enable UAVs to autonomously continue their missions under GNSS interference, ensuring reliable navigation in challenging conditions. The proposed solution combines map-based and map-less navigation methods, utilizing ORB and LoFTR algorithms to enhance positioning accuracy through visual feature matching. The study introduces the development of a PROXY component, which facilitates seamless switching between GNSS and visual navigation modes, preserving mission continuity without interruption. Simulations demonstrate the system’s ability to maintain acceptable localization accuracy despite GNSS signal disruption. This solution provides an adaptable alternative for UAV navigation in GNSS-compromised environments, enhancing UAV capabilities for autonomous operation in varied and challenging scenarios.