Robust map optimization using dynamic covariance scaling

By Pratik Agarwal, Gian Diego Tipaldi, Luciano Spinello, Cyrill Stachniss, Wolfram Burgard. IEEE International Conference on Robotics and Automation, 2013

298 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Environmental Engineering, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/b011c84aa50765d59c9e03c2f42bea8458b52dc6

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 Ocean Engineering

Citations in the corpus

Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments (2021, background): “CC outperformed the others in challenging regions with few false positives (red), which can potentially be treated using existing robust back-ends [45, 48, 49].”
QuadricSLAM: Dual Quadrics From Object Detections as Landmarks in Object-Oriented SLAM (2018, methodology): “1For a discussion of SLAM methods robust to data association errors see the relevant literature such as [27], [28].”
PROBE-GK: Predictive robust estimation using generalized kernels (2016, unknown): “These approaches, often grouped under the title of M-estimation, aim to maintain a quadratic influence of small errors, while reducing the contribution of larger errors.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, unknown): “navoidable that wrong loop closures are fed to the backend. Wrong loop closures can severely corrupt the quality of the MAP estimate [295]. In order to deal with this issue, a recent line of research [2, 50, 187, 234, 295] proposes techniques to make the SLAM back-end resilient against spurious meas”
Real-time loop closure in 2D LIDAR SLAM (2016, background): “Alternative approaches to outliers include [16] M nearest (T ξ h k ), (BBS) where W is the search window and M nearest is M extended to all of R 2 by rounding its arguments to the nearest grid point first, that is extending the value of a grid points to the corresponding pixel.”
Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems (2021, background): “[61] build on the same idea and develop the dynamic covariance scaling method.”
Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection (2019, methodology): “[42], Pfingsthorn and Birk [43] propose local methods for PGO.”
3-D Mapping With an RGB-D Camera (2014, background): “Most recently similar approaches for discounting edges during optimization have been published [43], [44].”