Autonomous Navigation Method for UAV Based on the Fusion of Laser SLAM and AprilTag

Abstract

To improve the accuracy and efficiency of autonomous navigation for indoor UAV's (Unmanned Aerial Vehicle) in complex substation environments, this paper proposes a multi-sensor fusion-based autonomous navigation method. An indoor UAV platform integrating multi-dimensional LiDAR, depth cameras, and edge computing devices was designed and built. The method uses AprilTag markers as visual references and constructs maps based on laser SLAM(Simultaneous Localization And Mapping) technology. A relocation scheme that incorporates AprilTag information is proposed, and Dijkstra and DWA (Dynamic Window Approach) algorithms are used to plan the global and local navigation paths of the UAV, respectively. In a GPS-denied environment, the system achieves precise UAV localization and environmental point cloud mapping, ensuring accurate positioning and path planning. Multi-scenario experiments in a ROS (Robot Operating System) environment demonstrate that this method provides high positioning accuracy and strong robustness.