Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models
© 2016 IEEE. Perceptual aliasing is one of the main causes of the failure for simultaneous localization and mapping (SLAM) systems operating in the wild. Perceptual aliasing is a phenomenon where different places generate a similar visual (or, in general, perceptual) footprint. This causes spurious...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/136194 |
| _version_ | 1826217424388620288 |
|---|---|
| author | Lajoie, Pierre-Yves Hu, Siyi Beltrame, Giovanni Carlone, Luca |
| author2 | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems |
| author_facet | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Lajoie, Pierre-Yves Hu, Siyi Beltrame, Giovanni Carlone, Luca |
| author_sort | Lajoie, Pierre-Yves |
| collection | MIT |
| description | © 2016 IEEE. Perceptual aliasing is one of the main causes of the failure for simultaneous localization and mapping (SLAM) systems operating in the wild. Perceptual aliasing is a phenomenon where different places generate a similar visual (or, in general, perceptual) footprint. This causes spurious measurements to be fed to the SLAM estimator, which typically results in incorrect localization and mapping results. This problem is exacerbated by the fact that those outliers are highly correlated, in the sense that perceptual aliasing creates a large number of mutually consistent outliers. Another issue stems from the fact that most state-of-the-art techniques rely on a given trajectory guess (e.g., from odometry) to discern between inliers and outliers, and this makes the resulting pipeline brittle, since the accumulation of error may result in incorrect choices and recovery from failures is far from trivial. This paper provides a unified framework to model perceptual aliasing in SLAM and provides practical algorithms that can cope with outliers without relying on any initial guess. We present two main contributions. The first is a discrete-continuous graphical model (DC-GM) for SLAM: The continuous portion of the DC-GM captures the standard SLAM problem, while the discrete portion describes the selection of the outliers and models their correlation. The second contribution is a semidefinite relaxation to perform inference in the DC-GM that returns estimates with provable sub-optimality guarantees. Experimental results on standard benchmarking datasets show that the proposed technique compares favorably with state-of-the-art methods while not relying on an initial guess for optimization. |
| first_indexed | 2024-09-23T17:03:25Z |
| format | Article |
| id | mit-1721.1/136194 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T17:03:25Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1361942023-11-07T19:51:33Z Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models Lajoie, Pierre-Yves Hu, Siyi Beltrame, Giovanni Carlone, Luca Massachusetts Institute of Technology. Laboratory for Information and Decision Systems © 2016 IEEE. Perceptual aliasing is one of the main causes of the failure for simultaneous localization and mapping (SLAM) systems operating in the wild. Perceptual aliasing is a phenomenon where different places generate a similar visual (or, in general, perceptual) footprint. This causes spurious measurements to be fed to the SLAM estimator, which typically results in incorrect localization and mapping results. This problem is exacerbated by the fact that those outliers are highly correlated, in the sense that perceptual aliasing creates a large number of mutually consistent outliers. Another issue stems from the fact that most state-of-the-art techniques rely on a given trajectory guess (e.g., from odometry) to discern between inliers and outliers, and this makes the resulting pipeline brittle, since the accumulation of error may result in incorrect choices and recovery from failures is far from trivial. This paper provides a unified framework to model perceptual aliasing in SLAM and provides practical algorithms that can cope with outliers without relying on any initial guess. We present two main contributions. The first is a discrete-continuous graphical model (DC-GM) for SLAM: The continuous portion of the DC-GM captures the standard SLAM problem, while the discrete portion describes the selection of the outliers and models their correlation. The second contribution is a semidefinite relaxation to perform inference in the DC-GM that returns estimates with provable sub-optimality guarantees. Experimental results on standard benchmarking datasets show that the proposed technique compares favorably with state-of-the-art methods while not relying on an initial guess for optimization. 2021-10-27T20:34:12Z 2021-10-27T20:34:12Z 2019 2021-04-16T17:16:31Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/136194 en 10.1109/LRA.2019.2894852 IEEE Robotics and Automation Letters Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv |
| spellingShingle | Lajoie, Pierre-Yves Hu, Siyi Beltrame, Giovanni Carlone, Luca Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models |
| title | Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models |
| title_full | Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models |
| title_fullStr | Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models |
| title_full_unstemmed | Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models |
| title_short | Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models |
| title_sort | modeling perceptual aliasing in slam via discrete continuous graphical models |
| url | https://hdl.handle.net/1721.1/136194 |
| work_keys_str_mv | AT lajoiepierreyves modelingperceptualaliasinginslamviadiscretecontinuousgraphicalmodels AT husiyi modelingperceptualaliasinginslamviadiscretecontinuousgraphicalmodels AT beltramegiovanni modelingperceptualaliasinginslamviadiscretecontinuousgraphicalmodels AT carloneluca modelingperceptualaliasinginslamviadiscretecontinuousgraphicalmodels |