Dynamic pose graph SLAM: Long-term mapping in low dynamic environments
Maintaining a map of an environment that changes over time is a critical challenge in the development of persistently autonomous mobile robots. Many previous approaches to mapping assume a static world. In this work we incorporate the time dimension into the mapping process to enable a robot to main...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2013
|
| Online Access: | http://hdl.handle.net/1721.1/78911 https://orcid.org/0000-0002-8863-6550 |
| _version_ | 1826207717484658688 |
|---|---|
| author | Walcott-Bryant, Aisha Kaess, Michael Johannsson, Hordur Leonard, John Joseph |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Walcott-Bryant, Aisha Kaess, Michael Johannsson, Hordur Leonard, John Joseph |
| author_sort | Walcott-Bryant, Aisha |
| collection | MIT |
| description | Maintaining a map of an environment that changes over time is a critical challenge in the development of persistently autonomous mobile robots. Many previous approaches to mapping assume a static world. In this work we incorporate the time dimension into the mapping process to enable a robot to maintain an accurate map while operating in dynamical environments. This paper presents Dynamic Pose Graph SLAM (DPG-SLAM), an algorithm designed to enable a robot to remain localized in an environment that changes substantially over time. Using incremental smoothing and mapping (iSAM) as the underlying SLAM state estimation engine, the Dynamic Pose Graph evolves over time as the robot explores new places and revisits previously mapped areas. The approach has been implemented for planar indoor environments, using laser scan matching to derive constraints for SLAM state estimation. Laser scans for the same portion of the environment at different times are compared to perform change detection; when sufficient change has occurred in a location, the dynamic pose graph is edited to remove old poses and scans that no longer match the current state of the world. Experimental results are shown for two real-world dynamic indoor laser data sets, demonstrating the ability to maintain an up-to-date map despite long-term environmental changes. |
| first_indexed | 2024-09-23T13:53:52Z |
| format | Article |
| id | mit-1721.1/78911 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:53:52Z |
| publishDate | 2013 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/789112022-09-28T16:54:34Z Dynamic pose graph SLAM: Long-term mapping in low dynamic environments Walcott-Bryant, Aisha Kaess, Michael Johannsson, Hordur Leonard, John Joseph Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Department of Mechanical Engineering Walcott-Bryant, Aisha Kaess, Michael Johannsson, Hordur Leonard, John Joseph Maintaining a map of an environment that changes over time is a critical challenge in the development of persistently autonomous mobile robots. Many previous approaches to mapping assume a static world. In this work we incorporate the time dimension into the mapping process to enable a robot to maintain an accurate map while operating in dynamical environments. This paper presents Dynamic Pose Graph SLAM (DPG-SLAM), an algorithm designed to enable a robot to remain localized in an environment that changes substantially over time. Using incremental smoothing and mapping (iSAM) as the underlying SLAM state estimation engine, the Dynamic Pose Graph evolves over time as the robot explores new places and revisits previously mapped areas. The approach has been implemented for planar indoor environments, using laser scan matching to derive constraints for SLAM state estimation. Laser scans for the same portion of the environment at different times are compared to perform change detection; when sufficient change has occurred in a location, the dynamic pose graph is edited to remove old poses and scans that no longer match the current state of the world. Experimental results are shown for two real-world dynamic indoor laser data sets, demonstrating the ability to maintain an up-to-date map despite long-term environmental changes. United States. National Oceanic and Atmospheric Administration (Grant NA06OAR4170019) United States. Office of Naval Research (Grant N00014-10-1-0936) United States. Office of Naval Research (Grant N00014-12-10020) 2013-05-16T18:39:44Z 2013-05-16T18:39:44Z 2013-05-16 2012-10 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-1737-5 2153-0858 http://hdl.handle.net/1721.1/78911 Walcott-Bryant, Aisha et al. “Dynamic pose graph SLAM: Long-term mapping in low dynamic environments.” Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2012): 1871–1878. https://orcid.org/0000-0002-8863-6550 en_US http://dx.doi.org/10.1109/IROS.2012.6385561 Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Walcott-Bryant, Aisha Kaess, Michael Johannsson, Hordur Leonard, John Joseph Dynamic pose graph SLAM: Long-term mapping in low dynamic environments |
| title | Dynamic pose graph SLAM: Long-term mapping in low dynamic environments |
| title_full | Dynamic pose graph SLAM: Long-term mapping in low dynamic environments |
| title_fullStr | Dynamic pose graph SLAM: Long-term mapping in low dynamic environments |
| title_full_unstemmed | Dynamic pose graph SLAM: Long-term mapping in low dynamic environments |
| title_short | Dynamic pose graph SLAM: Long-term mapping in low dynamic environments |
| title_sort | dynamic pose graph slam long term mapping in low dynamic environments |
| url | http://hdl.handle.net/1721.1/78911 https://orcid.org/0000-0002-8863-6550 |
| work_keys_str_mv | AT walcottbryantaisha dynamicposegraphslamlongtermmappinginlowdynamicenvironments AT kaessmichael dynamicposegraphslamlongtermmappinginlowdynamicenvironments AT johannssonhordur dynamicposegraphslamlongtermmappinginlowdynamicenvironments AT leonardjohnjoseph dynamicposegraphslamlongtermmappinginlowdynamicenvironments |