Simultaneous localization and mapping (SLAM) is the essential technique in mapping environments that are denied to the global navigation satellite systems (GNSSs), such as indoor spaces. In this article, we present a loop-closing continuous-time LIDAR-IMU SLAM for indoor environments. The design of the proposed SLAM is based on arbitrarily-oriented planar features that allow for point to plane matching for local but also global optimization. Moreover, to update the SLAM graph during the optimization, we propose a simple yet elegant loop closure method in the form of merging the planes together. Representing the SLAM map by planes is advantageous due to the abundant existence of planar structures in indoor built environments. The proposed method was validated on a specific configuration of three 2D LIDAR scanners mounted on a wearable platform (backpack). Scanned point clouds were compared against ones obtained from a commercial mobile mapping system (Viametris iMS3D) and a terrestrial laser scanner (RIEGL VZ-400). The experimental results demonstrate that our SLAM system is capable of mapping multi-storey buildings, staircases, cluttered areas and areas with curved walls. Furthermore, our SLAM system offers comparable performance to that of the commercial system as shown by the low deviation between the point clouds generated by both systems. The majority of the cloud-to-cloud absolute distances – about 92% – are less than 3 cm.
|Number of pages||14|
|Journal||ISPRS journal of photogrammetry and remote sensing|
|Early online date||9 Oct 2021|
|Publication status||Published - 1 Nov 2021|