Real-time Simultaneous Localization and Mapping for UAV: A Survey

Simultaneous Localization and Mapping (SLAM) refers to the problem of using various sensors like laser scanner, RGB cameras, RGB-D cameras, etc, to estimate the position of the robot, and concurrently construct the 2D/3D map of the environment. The SLAM community has made great progress in the past few decades. So far the 2D SLAM problem with range finders is considered as solved, while the real-time 3D SLAM, especially robust and high quality visual SLAM on UAVs, remains an open problem. This article aims to give a picture of the evolution and very recent development of SLAM algorithms, and emphasis is given on real-time SLAM methods that are suitable for Unmanned Aerial Vehicles (UAVs).