Comparison of Various SLAM Systems for Mobile Robot in an Indoor Environment
Maksim Filipenko, Ilya Afanasyev
TL;DR
This study evaluates multiple ROS-based SLAM systems on a common indoor dataset collected with a Labcar UGV equipped with 2D lidar, a monocular camera, and a ZED stereo camera. Absolute Trajectory Error and a suite of metrics reveal that Cartographer (2D lidar) achieves the smallest RMSE, with LSD-SLAM and monocular ORB-SLAM also performing well, while ZED-fu tends to underperform in this setup; among visual methods, RTAB-map and ORB-SLAM provide competitive localization with distinct map characteristics. The results underscore the trade-offs between dense direct SLAM approaches and sparse feature-based visual SLAM, as well as the benefit of global optimization and loop closure for robustness. Practically, the findings guide sensor-backend selection for indoor robots under varying computational constraints and sensor suites.
Abstract
This article presents a comparative analysis of a mobile robot trajectories computed by various ROS-based SLAM systems. For this reason we developed a prototype of a mobile robot with common sensors: 2D lidar, a monocular and ZED stereo cameras. Then we conducted experiments in a typical office environment and collected data from all sensors, running all tested SLAM systems based on the acquired dataset. We studied the following SLAM systems: (a) 2D lidar-based: GMapping, Hector SLAM, Cartographer; (b) monocular camera-based: Large Scale Direct monocular SLAM (LSD SLAM), ORB SLAM, Direct Sparse Odometry (DSO); and (c) stereo camera-based: ZEDfu, Real-Time Appearance-Based Mapping (RTAB map), ORB SLAM, Stereo Parallel Tracking and Mapping (S-PTAM). Since all SLAM methods were tested on the same dataset we compared results for different SLAM systems with appropriate metrics, demonstrating encouraging results for lidar-based Cartographer SLAM, Monocular ORB SLAM and Stereo RTAB Map methods.