SLAM (Simultaneous Localization and Mapping)

Autonomous navigation of unmanned aerial vehicles (UAVs) in unstructured industrial environments remains challenging due to irregular geometry, dynamic obstacles and sensor uncertainty. Classical Simultaneous Localization and Mapping (SLAM) systems, though geometrically consistent, often fail under poor initialization, textureless areas or reflective surfaces. To overcome these issues, this work proposes a hybrid transformer-geometric framework that fuses learned scene priors with keyframe-based SLAM.

The article addresses the issues of digital mapping of territories using modern equipment and innovative methods for performing topographic and geodetic work. Objective: To study modern territorial mapping methods and justify mapping approaches using SLAM technology. Methods and Results: The study employed a territorial mapping method using handheld laser scanners with SLAM technology. Terrain reconnaissance was conducted, control geodetic points were established, and fieldwork was performed using a Stonex X120GO scanner.