A Tutorial on Graph-Based SLAM

By Giorgio Grisetti, Rainer Kümmerle, Cyrill Stachniss, Wolfram Burgard. IEEE Intelligent Transportation Systems Magazine, 2010

1,336 citations recorded by the source corpus.

Being able to build a map of the environment and to simultaneously localize within this map is an essential skill for mobile robots navigating in unknown environments in absence of external referencing systems such as GPS. This so-called simultaneous localization and mapping (SLAM) problem has been one of the most popular research topics in mobile robotics for the last two decades and efficient approaches for solving this task have been proposed. One intuitive way of formulating SLAM is to use a graph whose nodes correspond to the poses of the robot at different points in time and whose edges represent constraints between the poses. The latter are obtained from observations of the environment or from movement actions carried out by the robot. Once such a graph is constructed, the map can be computed by finding the spatial configuration of the nodes that is mostly consistent with the measurements modeled by the edges. In this paper, we provide an introductory description to the graph-based SLAM problem. Furthermore, we discuss a state-of-the-art solution that is based on least-squares error minimization and exploits the structure of the SLAM problems during optimization. The goal of this tutorial is to enable the reader to implement the proposed methods from scratch.

Subfields: Aerospace Engineering, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/50d385523ccf32ae41a4c31556129f2e10110d27

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Improving RGB-D SLAM in dynamic environments: A motion removal approach (2017, background): “In this section, we briefly introduce the graph SLAM [31] and”
Using Inertial Sensors for Position and Orientation Estimation (2017, neutral): “Important reasons are also that the estimation problems are nonlinear and that different parametrizations of the orientation need to be considered [47, 77], each with its own specific properties.”
An Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics (2015, methodology): “Whereas smoothing approaches address the full SLAM problem in which the posterior is estimated over the entire path along with the map, and is generally solved using a least square (LS) error minimization technique [49].”
Online global loop closure detection for large-scale multi-session graph-based SLAM (2014, background): “While single session graph-based SLAM has been largely addressed [2]–[4], multi-session SLAM involves having to deal with the fact that robots, over a long period of operation, will eventually be shutdown and moved to another location without knowing it.”
OpenVSLAM: A Versatile Visual SLAM Framework (2019, methodology): “As in ORB– SLAM [10, 11] and ProSLAM [15], the graph-based SLAM algorithm [6] with the indirect method is used in OpenVSLAM.”
SE-Sync: A certifiably correct algorithm for synchronization over the special Euclidean group (2016, methodology): “;:::;x n 2SE(d) given noisy observations of a subset of their pairwise relative transforms x 1 i x j. For example, the foundational problems of pose-graph simultaneous localization and mapping (SLAM) [41,55] (in robotics), camera motion and/or orientation estimation [4,44,79] (in computer vision), a”
RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation (2018, methodology): “However, for single map, based on empirical data, g2o and GTSAM optimization quality is better than TORO, particularly for six ‐ degrees ‐ of ‐ freedom maps.”
School of Electrical and Computer Engineering Oklahoma State University , Stillwater , OK 74078 , USA (methodology): “We incrementally optimize the pose estimations through minimizing the following general cost function [12, 18]:”
A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers (2022, background): “Let us first consider the case of graph-based SLAM, in which the problem is described using a graph representation where nodes represent the robot poses and edges encode the constraints between them; see [2], [3], [4], [5].”
Nonparametric Calibration for Depth Sensors (2015, methodology): “TheSLAMsystem is graph based [2] and uses Generalized ICP [8] to match the point clouds extracted from depth data as a front-end and g2o [4] as optimization backend.”
AUV Navigation and Localization: A Review (2014, background): “[45], [46], and hierarchical optimization for pose graphs on manifolds (HOGMAN) [47].”
Visual SLAM algorithms: a survey from 2010 to 2016 (2017, methodology): “Pose graph optimization has widely been used to suppress the accumulated error by optimizing camera poses [12, 13].”
Visual simultaneous localization and mapping: a survey (2012, methodology): “A tutorial to formulate the SLAM problem by means of graphs can be consulted in (Grisetti et al. 2010).”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, positive): “[98] provide excellent introductions to two of the most popular SLAM libraries; each library also includes a set of examples showcasing real SLAM problems.”
Robust reconstruction of indoor scenes (2015, methodology): “Consider a pose graph with vertices {Pi} and edges {Ri} ∪ {Tij} [23].”
Non-GPS Positioning Systems (2017, methodology): “The maps are constructed through an extension of GraphSLAM [34] by incorporating various technologies such as PDR, Wi-Fi RSS, Bluetooth RSS, LTE Reference Signal Received Power, and magnetic field.”
Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, background): “The simplest way of doing loop closure is by performing pair wise matching for possible loop closure by considering all observations that are within a pre-determined radius from a node in the pose graph [158].”