Simultaneous Localization and Mapping with Sparse Extended Information Filters

By Sebastian Thrun, Yufeng Liu, Daphne Koller, Andrew Y. Ng, Zoubin Ghahramani, H. F. Durrant-Whyte. Int. J. Robotics Res., 2004

786 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/21cd8ab04da98b819fa1cd222126c42291613f1f

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

Multiple‐Robot Simultaneous Localization and Mapping: A Review (2016, methodology): “EIF-SLAM (Thrun et al., 2004a) (Hahnel et al.”
Globally consistent 3D mapping with scan matching (2008, methodology): “Thrun reviews in [29] existing techniques, i.e., maximum likelihood estimation [12], expectation maximization [10] [30], extended Kalman filter [9] or (sparse extended) information filter [33].”
Factor Graphs for Robot Perception (2017, background): “[188] and others that the information matrix is the matrix of a Markov random field associated with the SLAM problem.”
Optical techniques for 3D surface reconstruction in computer-assisted laparoscopic surgery (2013, methodology): “(Thrun et al., 2004) proposes a sparsification method which represents the probability density in information form.”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, neutral): “It is also possible to make the information matrix sparser by breaking the weak links between data [42] which ensures”
Learning to fly by crashing (2017, methodology): “Another way to collect this data is by commanding the drone to autonomously navigate the environment by SLAM based approaches [24], [25] and collect failure cases.”
The SLAM problem: a survey (2008, background): “Finally, EKF is relatively slow when estimating high dimensional maps, because every single vehicle measurement generally effects all parameters of the Gaussian, therefore the updates requires prohibitive times when dealing with environments with many landmarks [18].”
Multi-Level Surface Maps for Outdoor Terrain Mapping and Loop Closing (2006, background): “Furthermore, several authors have considered the problem of simultaneous mapping and localization (SLAM) in an outdoor environment [4], [6], [27].”
Fast iterative alignment of pose graphs with poor initial estimates (2006, background): “demonstrated that the information matrix can be effectively sparsified [3].”
Exactly Sparse Delayed-State Filters for View-Based SLAM (2006, methodology): “In particular, published approaches include the sparse extended information filter (SEIF) [34], the thin junction-tree filter (TJTF) [35], and Treemap filters [37].”
Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters (2007, methodology): “[35] proposed a method to correct the poses of robots based on the inverse of the covariance matrix.”
Simultaneous localization and mapping: part I (2006, methodology): “While EKF-SLAM and FastSLAM are the two most important solution methods, newer alternatives, which offer much potential, have been proposed, including the use of the information-state form [43].”
6D SLAM—3D mapping outdoor environments (2007, methodology): “Thrun reviews Thrun, 2002 existing techniques, i.e., maximum likelihood estimation Frese & Hirzinger, 2001; Folkesson & Christensen, 2003, expectation maximization Thrun, Burgard & Fox, 1997, extended Kalman filter Dissanayake, Newman, Clark, Currant-Whyte & Csorba, 2001 or sparse extended informati”