Data association in stochastic mapping using the joint compatibility test

By José Neira, Juan D. Tardós. IEEE Trans. Robotics Autom., 2001

884 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/d0ea626f725603f9719d009f974f1a2381f157d9

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 Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

iSAM: Incremental Smoothing and Mapping (2008, methodology): “This also allows efficient retrieval of additional quantities that may be required for other data association techniques, such as the joint compatibility test [19].”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, positive): “It is the case of the GCBB algorithm (Geometric Constraint Branch and Bound) proposed in [143].”
Robust Mapping and Localization in Indoor Environments Using Sonar Data (2002, methodology): “(10) Measurement z k is furthermore verified using Joint Compatibility (Neira and Tardós 2001), and used to obtain a new estimation of the state using the standard EKF update equations: ˆ x B F k = ˆ x B F k|k−1 + K k (z k − h k (ˆ x B F k|k−1 )) P B F k = (I − K k H k )P B F k|k−1 K k = P B F k|k−1”
Mobile Robot Localisation and Mapping in Extensive Outdoor Environments (2002, methodology): “The branch-and-bound algorithm in [106] constructs the interpretation tree incrementally using depth-first search with a maximum likelihood branching heuristic.”
Visual simultaneous localization and mapping: a survey (2012, methodology): “In the past, the problem of associating measurements with landmarks on the map was solved through algorithms such as Nearest Neighbor, Sequential Compatibility Nearest Neighbor and Joint Compatibility Branch and Bound (Neira and Tardós 2001).”
A Tutorial on Graph-Based SLAM (2010, methodology): “For making data associations in the SLAM front-ends statistical tests such as the χ 2 test or joint compatibility test [23] are often applied.”
Model-free detection and tracking of dynamic objects with 2D lidar (2015, methodology): “JCBB (Neira and Tardos, 2001) is a well-known data association algorithm that takes into account the correlations between observations.”
Probabilistic data association for semantic SLAM (2017, background): “, via joint compatability branch and bound [27] or the Hungarian algorithm [28]).”
Simultaneous Localisation and Mapping ( SLAM ) : Part I The Essential Algorithms (2006, background): “Data Association: The standard formulation of the EKF-SLAM solution is especially fragile to incorrect association of observations to landmarks [35].”
Mapping Large Loops with a Single Hand-Held Camera (2007, methodology): “In this work we have adopted the inverse-depth representation proposed by Montiel et al. [2], which performs undelayed initialization of point features in EKF-SLAM from the first instant they are detected.”
Hierarchical SLAM: real-time accurate mapping of large environments (2005, methodology): “At each step, data association is robustly solved using the joint compatibility test [22], and the local map is updated with standard stochastic mapping techniques [23].”
Incremental smoothing and mapping (2008, methodology): “The joint compatibility branch and bound algorithm by Neira and Tardos [105] has proven particularly successful [2, 131].”
Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters (2007, methodology): “There exist techniques [28] to deal with unknown data association in the SLAM context; however, if these assumptions are violated, the filter is likely to diverge [29].”
Simultaneous Localization and Map Building in Large-Scale Cyclic Environments Using the Atlas Framework (2004, methodology): “For example, the joint compatibility test with branch and bound technique suggested by Neira and Tardós (2001) could also be utilized.”
Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems (2021, methodology): “To mitigate the effect of outliers in single-robot SLAM, early methods are based on RANSAC [56], branch & bound [57], and M-estimation ([58, 59]).”
Simultaneous localization and mapping: part I (2006, background): “IEEE Robotics & Automation Magazine JUNE 2006 104 Data Association The standard formulation of the EKF-SLAM solution is especially fragile to incorrect association of observations to landmarks [35].”