Data Association for Semantic World Modeling from Partial Views
Autonomous mobile-manipulation robots need to sense and interact with objects to accomplish high-level tasks such as preparing meals and searching for objects. To achieve such tasks, robots need semantic world models, defined as object-based representations of the world involving task-level attribu...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Sage Publications
2015
|
| Online Access: | http://hdl.handle.net/1721.1/92929 https://orcid.org/0000-0002-9944-7587 https://orcid.org/0000-0002-8657-2450 https://orcid.org/0000-0001-6054-7145 |
| _version_ | 1826194523310522368 |
|---|---|
| author | Wong, Lok Sang Lawson Kaelbling, Leslie P. Lozano-Perez, Tomas |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Wong, Lok Sang Lawson Kaelbling, Leslie P. Lozano-Perez, Tomas |
| author_sort | Wong, Lok Sang Lawson |
| collection | MIT |
| description | Autonomous mobile-manipulation robots need to sense and interact with objects to accomplish high-level tasks such as preparing meals and searching for objects. To achieve such tasks, robots need semantic world models, defined as object-based representations of the world involving task-level attributes. In this work, we address the problem of estimating world models from semantic perception modules that provide noisy observations of attributes. Because attribute detections are sparse, ambiguous, and are aggregated across different viewpoints, it is unclear which attribute measurements are produced by the same object, so data association issues are prevalent. We present novel clustering-based approaches to this problem, which are more efficient and require less severe approximations compared to existing tracking-based approaches. These approaches are applied to data containing object type-and-pose detections from multiple viewpoints, and demonstrate comparable quality using a fraction of the computation time. |
| first_indexed | 2024-09-23T09:57:24Z |
| format | Article |
| id | mit-1721.1/92929 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:57:24Z |
| publishDate | 2015 |
| publisher | Sage Publications |
| record_format | dspace |
| spelling | mit-1721.1/929292022-09-26T14:48:13Z Data Association for Semantic World Modeling from Partial Views Wong, Lok Sang Lawson Kaelbling, Leslie P. Lozano-Perez, Tomas Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Wong, Lok Sang Lawson Wong, Lok Sang Lawson Kaelbling, Leslie P. Lozano-Perez, Tomas Autonomous mobile-manipulation robots need to sense and interact with objects to accomplish high-level tasks such as preparing meals and searching for objects. To achieve such tasks, robots need semantic world models, defined as object-based representations of the world involving task-level attributes. In this work, we address the problem of estimating world models from semantic perception modules that provide noisy observations of attributes. Because attribute detections are sparse, ambiguous, and are aggregated across different viewpoints, it is unclear which attribute measurements are produced by the same object, so data association issues are prevalent. We present novel clustering-based approaches to this problem, which are more efficient and require less severe approximations compared to existing tracking-based approaches. These approaches are applied to data containing object type-and-pose detections from multiple viewpoints, and demonstrate comparable quality using a fraction of the computation time. National Science Foundation (U.S.) (NSF Grant No. 1117325) United States. Office of Naval Research (ONR MURI grant N00014-09-1-1051) United States. Air Force Office of Scientific Research (AFOSR grant FA2386-10-1-4135) Singapore. Ministry of Education (Grant to the the Singapore-MIT International Design Center) 2015-01-16T15:12:44Z 2015-01-16T15:12:44Z 2015-01-16 Article http://purl.org/eprint/type/JournalArticle 0278-3649 1741-3176 http://hdl.handle.net/1721.1/92929 Wong, L.S. Lawson, Leslie Pack Kaelbling, and Tomas Lozano-Perez. "Data Association for Semantic World Modeling from Partial Views." International Journal of Robotics Research, June 2015; 34 (7) : 1064–1082. https://orcid.org/0000-0002-9944-7587 https://orcid.org/0000-0002-8657-2450 https://orcid.org/0000-0001-6054-7145 en_US http://dx.doi.org/10.1177/0278364914559754 International Journal of Robotics Research Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Sage Publications Wong |
| spellingShingle | Wong, Lok Sang Lawson Kaelbling, Leslie P. Lozano-Perez, Tomas Data Association for Semantic World Modeling from Partial Views |
| title | Data Association for Semantic World Modeling from Partial Views |
| title_full | Data Association for Semantic World Modeling from Partial Views |
| title_fullStr | Data Association for Semantic World Modeling from Partial Views |
| title_full_unstemmed | Data Association for Semantic World Modeling from Partial Views |
| title_short | Data Association for Semantic World Modeling from Partial Views |
| title_sort | data association for semantic world modeling from partial views |
| url | http://hdl.handle.net/1721.1/92929 https://orcid.org/0000-0002-9944-7587 https://orcid.org/0000-0002-8657-2450 https://orcid.org/0000-0001-6054-7145 |
| work_keys_str_mv | AT wongloksanglawson dataassociationforsemanticworldmodelingfrompartialviews AT kaelblinglesliep dataassociationforsemanticworldmodelingfrompartialviews AT lozanopereztomas dataassociationforsemanticworldmodelingfrompartialviews |