Hierarchical SLAM: real-time accurate mapping of large environments

By Carlos Estrada, José Neira, Juan D. Tardós. IEEE Transactions on robotics, 2005

461 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Environmental Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4f9721cdace25978a2f59c979c67b65edc0063fa

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 Environmental Engineering

In Signal Processing

Citations in the corpus

Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, unknown): “an idea that dates back to the initial attempts to tackle large-scale maps [30, 99, 296].”
Mapping Large Loops with a Single Hand-Held Camera (2007, methodology): “Then, the Iterated Extended Kalman Filter [20] is used for re-estimating the transformations between the maps that from the loop, as proposed in [1].”
1-Point RANSAC for extended Kalman filtering: Application to real-time structure from motion and visual odometry (2010, background): “This problem can be solved by dividing the large global map to smaller maps with mutual position information (Estrada et al., 2005; Clemente et al., 2007; Bosse et al., 2004; Williams et al., 2009).”
Factor Graphs for Robot Perception (2017, background): “[161] improved the work in [60] by fusing the local maps in a hierarchical way, which has a nested dissection flavor.”
Autonomous multi-floor indoor navigation with a computationally constrained MAV (2011, methodology): “Akin to the methods of [16], we apply an optimization based on an Iterative Extended Kalman Filter (IEKF) to create a globally consistent pose graph configuration.”
Multiple‐Robot Simultaneous Localization and Mapping: A Review (2016, methodology): “, in which each robot builds local maps using an EKF, and then the spatial consistency of the maps of the robots is achieved by an optimization process (Estrada et al., 2005).”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, unknown): “The first possibility to avoid, or at least reduce, the divergence is to divide the map in submaps [31].”
Disambiguating visual relations using loop constraints (2010, background): “Upgrading the relative orientations between sub-maps to absolute orientations in a common coordinate frame using explicit loop constraints is proposed in [5].”
Appearance-Based Loop Closure Detection for Online Large-Scale and Long-Term Operation (2013, background): “(in the sense that the time required to process new observations remains lower or equal to the time to acquire them, as in [5], [13], [14], and [47]), independently of the scale of the mapped en-”
Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure (2016, background): “Submaps date back to much earlier work in SLAM (e.g. [32–34]), but have only recently been considered in the context of dense 3D modelling.”
The SLAM problem: a survey (2008, methodology): “There exist various V-SLAM approaches for terrestrial applications [3] [4] [14] [15], most of them deal with the uncertainties by using Kalman Filters (KF) and its variation Extended Kalman Filters (EKF) [3] [14] [15], and another group of papers uses some improved information filter [16] [17] [20] ”