Cross-Session 3D LiDAR and Camera Fusion for Robust Localization of Unmanned Aerial Vehicles in GPS-Denied Environments

2026-06-27

AI Summary

This work addresses the challenge of high-precision drone localization in GPS-denied or signal-constrained environments—such as indoors, tunnels, and urban canyons—by proposing a lightweight multimodal fusion approach that integrates 3D LiDAR with monocular RGB camera data. Leveraging a cross-session fusion mechanism, the system aggregates historical visual and geometric information from multiple agents, significantly enhancing localization consistency and map completeness while operating under a simplified sensor suite that excludes stereo cameras or global shutters. The method primarily relies on LiDAR odometry for motion tracking and employs monocular image feature matching to correct accumulated drift, maintaining robust performance even in feature-sparse scenes. Experimental results demonstrate localization accuracy comparable to GPS-based solutions, confirming the approach’s robustness and practicality in complex environments.

Abstract

Accurate localization of unmanned aerial vehicles (UAVs) is essential for applications such as structural health monitoring, especially in environments where Global Positioning System (GPS) signals are denied or unreliable, like indoor spaces, tunnels, urban canyons, or areas beneath large structures. To address this challenge, we propose Cross-Fusion, a novel method for real-time UAV localization that integrates data from a 3D Light Detection and Ranging (LiDAR) and a monocular camera. A key contribution is its cross-session fusion strategy, which integrates visual and geometric information collected from multiple agents during routine baseline surveys to improve localization consistency and map completeness. The system employs LiDAR-based odometry for motion tracking and image-based feature matching via a single red-green-blue (RGB) camera to correct drift and improve accuracy. Unlike visual-inertial systems, Cross-Fusion maintains a simple sensor setup and avoids the complexity of stereo or global shutter configurations. Experimental results demonstrate that Cross-Fusion achieves localization accuracy comparable to GPS-based methods and performs reliably in challenging feature-sparse environments.

Problem

• UAV localization
• GPS-denied environments
• 3D LiDAR
• camera fusion
• robust localization

Innovation

• cross-session fusion
• 3D LiDAR-camera fusion
• GPS-denied localization
• monocular visual-inertial odometry
• UAV localization