Towards lifelong feature-based mapping in semi-static environments
The feature-based graphical approach to robotic mapping provides a representationally rich and computationally efficient framework for an autonomous agent to learn a model of its environment. However, this formulation does not naturally support long-term autonomy because it lacks a notion of environ...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
| Online Access: | http://hdl.handle.net/1721.1/107620 https://orcid.org/0000-0001-8964-1602 https://orcid.org/0000-0002-8863-6550 |
| _version_ | 1811094402520580096 |
|---|---|
| author | Rosen, David Matthew Mason, Julian Leonard, John J |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Rosen, David Matthew Mason, Julian Leonard, John J |
| author_sort | Rosen, David Matthew |
| collection | MIT |
| description | The feature-based graphical approach to robotic mapping provides a representationally rich and computationally efficient framework for an autonomous agent to learn a model of its environment. However, this formulation does not naturally support long-term autonomy because it lacks a notion of environmental change; in reality, “everything changes and nothing stands still, ” and any mapping and localization system that aims to support truly persistent autonomy must be similarly adaptive. To that end, in this paper we propose a novel feature-based model of environmental evolution over time. Our approach is based upon the development of an expressive probabilistic generative feature persistence model that describes the survival of abstract semi-static environmental features over time. We show that this model admits a recursive Bayesian estimator, the persistence filter, that provides an exact online method for computing, at each moment in time, an explicit Bayesian belief over the persistence of each feature in the environment. By incorporating this feature persistence estimation into current state-of-the-art graphical mapping techniques, we obtain a flexible, computationally efficient, and information-theoretically rigorous framework for lifelong environmental modeling in an ever-changing world. |
| first_indexed | 2024-09-23T15:59:29Z |
| format | Article |
| id | mit-1721.1/107620 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:59:29Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1076202022-09-29T17:31:42Z Towards lifelong feature-based mapping in semi-static environments Rosen, David Matthew Mason, Julian Leonard, John J Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Mechanical Engineering Rosen, David Matthew Mason, Julian Leonard, John J The feature-based graphical approach to robotic mapping provides a representationally rich and computationally efficient framework for an autonomous agent to learn a model of its environment. However, this formulation does not naturally support long-term autonomy because it lacks a notion of environmental change; in reality, “everything changes and nothing stands still, ” and any mapping and localization system that aims to support truly persistent autonomy must be similarly adaptive. To that end, in this paper we propose a novel feature-based model of environmental evolution over time. Our approach is based upon the development of an expressive probabilistic generative feature persistence model that describes the survival of abstract semi-static environmental features over time. We show that this model admits a recursive Bayesian estimator, the persistence filter, that provides an exact online method for computing, at each moment in time, an explicit Bayesian belief over the persistence of each feature in the environment. By incorporating this feature persistence estimation into current state-of-the-art graphical mapping techniques, we obtain a flexible, computationally efficient, and information-theoretically rigorous framework for lifelong environmental modeling in an ever-changing world. United States. Office of Naval Research (Grant N00014-11-1-0688) National Science Foundation (U.S.) (Grant IIS-1318392) 2017-03-21T15:16:27Z 2017-03-21T15:16:27Z 2016-06 2016-05 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-8026-3 http://hdl.handle.net/1721.1/107620 Rosen, David M., Julian Mason, and John J. Leonard. “Towards Lifelong Feature-Based Mapping in Semi-Static Environments.” IEEE, 2016. 1063–1070. https://orcid.org/0000-0001-8964-1602 https://orcid.org/0000-0002-8863-6550 en_US http://dx.doi.org/10.1109/ICRA.2016.7487237 Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) Other univ. web domain |
| spellingShingle | Rosen, David Matthew Mason, Julian Leonard, John J Towards lifelong feature-based mapping in semi-static environments |
| title | Towards lifelong feature-based mapping in semi-static environments |
| title_full | Towards lifelong feature-based mapping in semi-static environments |
| title_fullStr | Towards lifelong feature-based mapping in semi-static environments |
| title_full_unstemmed | Towards lifelong feature-based mapping in semi-static environments |
| title_short | Towards lifelong feature-based mapping in semi-static environments |
| title_sort | towards lifelong feature based mapping in semi static environments |
| url | http://hdl.handle.net/1721.1/107620 https://orcid.org/0000-0001-8964-1602 https://orcid.org/0000-0002-8863-6550 |
| work_keys_str_mv | AT rosendavidmatthew towardslifelongfeaturebasedmappinginsemistaticenvironments AT masonjulian towardslifelongfeaturebasedmappinginsemistaticenvironments AT leonardjohnj towardslifelongfeaturebasedmappinginsemistaticenvironments |