AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAM
In robot localisation and mapping, outliers are unavoidable when loop-closure measurements are taken into account. A single false-positive loop-closure can have a very negative impact on SLAM problems causing an inferior trajectory to be produced or even for the optimisation to fail entirely. To add...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2022.789444/full |
| _version_ | 1818754531385671680 |
|---|---|
| author | Milad Ramezani Milad Ramezani Matias Mattamala Maurice Fallon |
| author_facet | Milad Ramezani Milad Ramezani Matias Mattamala Maurice Fallon |
| author_sort | Milad Ramezani |
| collection | DOAJ |
| description | In robot localisation and mapping, outliers are unavoidable when loop-closure measurements are taken into account. A single false-positive loop-closure can have a very negative impact on SLAM problems causing an inferior trajectory to be produced or even for the optimisation to fail entirely. To address this issue, popular existing approaches define a hard switch for each loop-closure constraint. This paper presents AEROS, a novel approach to adaptively solve a robust least-squares minimisation problem by adding just a single extra latent parameter. It can be used in the back-end component of the SLAM system to enable generalised robust cost minimisation by simultaneously estimating the continuous latent parameter along with the set of sensor poses in a single joint optimisation. This leads to a very closely curve fitting on the distribution of the residuals, thereby reducing the effect of outliers. Additionally, we formulate the robust optimisation problem using standard Gaussian factors so that it can be solved by direct application of popular incremental estimation approaches such as iSAM. Experimental results on publicly available synthetic datasets and real LiDAR-SLAM datasets collected from the 2D and 3D LiDAR systems show the competitiveness of our approach with the state-of-the-art techniques and its superiority on real world scenarios. |
| first_indexed | 2024-12-18T05:24:44Z |
| format | Article |
| id | doaj.art-63d79bf3d07d4cd1b498264a8435d121 |
| institution | Directory Open Access Journal |
| issn | 2296-9144 |
| language | English |
| last_indexed | 2024-12-18T05:24:44Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj.art-63d79bf3d07d4cd1b498264a8435d1212022-12-21T21:19:34ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442022-04-01910.3389/frobt.2022.789444789444AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAMMilad Ramezani0Milad Ramezani1Matias Mattamala2Maurice Fallon3Robotics and Autonomous Systems Group, DATA61, CSIRO, Brisbane, QLD, AustraliaDynamic Robot Systems, Oxford Robotics Institute, Department of Engineering Science, University of Oxford, Oxford, United KingdomDynamic Robot Systems, Oxford Robotics Institute, Department of Engineering Science, University of Oxford, Oxford, United KingdomDynamic Robot Systems, Oxford Robotics Institute, Department of Engineering Science, University of Oxford, Oxford, United KingdomIn robot localisation and mapping, outliers are unavoidable when loop-closure measurements are taken into account. A single false-positive loop-closure can have a very negative impact on SLAM problems causing an inferior trajectory to be produced or even for the optimisation to fail entirely. To address this issue, popular existing approaches define a hard switch for each loop-closure constraint. This paper presents AEROS, a novel approach to adaptively solve a robust least-squares minimisation problem by adding just a single extra latent parameter. It can be used in the back-end component of the SLAM system to enable generalised robust cost minimisation by simultaneously estimating the continuous latent parameter along with the set of sensor poses in a single joint optimisation. This leads to a very closely curve fitting on the distribution of the residuals, thereby reducing the effect of outliers. Additionally, we formulate the robust optimisation problem using standard Gaussian factors so that it can be solved by direct application of popular incremental estimation approaches such as iSAM. Experimental results on publicly available synthetic datasets and real LiDAR-SLAM datasets collected from the 2D and 3D LiDAR systems show the competitiveness of our approach with the state-of-the-art techniques and its superiority on real world scenarios.https://www.frontiersin.org/articles/10.3389/frobt.2022.789444/fullrobust cost functionoutlier resilienceback-end optimisationfactor graphleast squares minimisationSLAM |
| spellingShingle | Milad Ramezani Milad Ramezani Matias Mattamala Maurice Fallon AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAM Frontiers in Robotics and AI robust cost function outlier resilience back-end optimisation factor graph least squares minimisation SLAM |
| title | AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAM |
| title_full | AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAM |
| title_fullStr | AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAM |
| title_full_unstemmed | AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAM |
| title_short | AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAM |
| title_sort | aeros adaptive robust least squares for graph based slam |
| topic | robust cost function outlier resilience back-end optimisation factor graph least squares minimisation SLAM |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2022.789444/full |
| work_keys_str_mv | AT miladramezani aerosadaptiverobustleastsquaresforgraphbasedslam AT miladramezani aerosadaptiverobustleastsquaresforgraphbasedslam AT matiasmattamala aerosadaptiverobustleastsquaresforgraphbasedslam AT mauricefallon aerosadaptiverobustleastsquaresforgraphbasedslam |