Exactly Sparse Delayed-State Filters for View-Based SLAM
By Ryan M. Eustice, Hanumant Singh, John J. Leonard. IEEE Transactions on robotics, 2006
346 citations recorded by the source corpus.
Subfields: Aerospace Engineering, Artificial Intelligence, Ocean Engineering
View Paper: https://www.semanticscholar.org/paper/066d6c2d24c82ef3fc5ea49afdd1256b783fe442
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
- Kurt Konolige
- Wolfram Burgard
- Giorgio Grisetti
- Sajad Saeedi
- Mae L. Seto
- Howard Li
- Andrew J. Davison
- Motilal Agrawal
In Artificial Intelligence
- Mae L. Seto
- Howard Li
- Sajad Saeedi
- Giorgio Grisetti
- Wolfram Burgard
- Rainer Kümmerle
- Nicholas Carlevaris-Bianco
- Arash K. Ushani
In Ocean Engineering
- Wolfram Burgard
- Nicholas Carlevaris-Bianco
- Arash K. Ushani
- Kurt Konolige
- Ryan M. Eustice
- Giorgio Grisetti
- Mae L. Seto
- Howard Li
Citations in the corpus
- Legged Robot State-Estimation Through Combined Forward Kinematic and Preintegrated Contact Factors (2017, methodology): “ally, Simultaneous Localization and Mapping (SLAM) [15], [16], use graphical models (factor graphs) and nonlinear optimization techniques to achieve a probabilistically sound sensor fusion framework and real-time performance by exploiting the sparse structure of the SLAM problem [17], [13].”
- Multiple‐Robot Simultaneous Localization and Mapping: A Review (2016, neutral): “, 1987) (Eustice et al., 2006) (Newman et al.”
- Kalman Filter for Robot Vision: A Survey (2012, background): “SLAM is considered as the key factor in realizing real autonomy for mobile robots [20], [21], [76]–[86].”
- Efficient Sparse Pose Adjustment for 2D mapping (2010, methodology): “The first such approach was proposed by Eustice et al. and denoted Delayed Sparse Information Filter (DSIF) [7].”
- AUV Navigation and Localization: A Review (2014, methodology): “In [24] and [25], the VAN approach is converted to the information form, and it is proven that the view-based ESEIF–SLAM maintains a sparse information matrix without approximations or pruning.”
- FrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping (2008, background): “However, computing relative covariance involves marginalizing all variables in the system Hessian, and is too expensive to be done online [12].”
- University of Michigan North Campus long-term vision and lidar dataset (2016, methodology): “In order to produce the relative odometry factors between poses that are used in our SLAM system, the EKF tracks the current pose of the robot and the pose of the last node added to the graph within a delayed-state framework (Eustice et al., 2006).”