Concurrent filtering and smoothing: A parallel architecture for real-time navigation and full smoothing
We present a parallelized navigation architecture that is capable of running in real-time and incorporating long-term loop closure constraints while producing the optimal Bayesian solution. This architecture splits the inference problem into a low-latency update that incorporates new measurements us...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Sage Publications
2015
|
| Online Access: | http://hdl.handle.net/1721.1/97575 https://orcid.org/0000-0002-8863-6550 |
| _version_ | 1826191664202383360 |
|---|---|
| author | Williams, Stephen Indelman, Vadim Kaess, Michael Roberts, Richard Leonard, John Joseph Dellaert, Frank |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Williams, Stephen Indelman, Vadim Kaess, Michael Roberts, Richard Leonard, John Joseph Dellaert, Frank |
| author_sort | Williams, Stephen |
| collection | MIT |
| description | We present a parallelized navigation architecture that is capable of running in real-time and incorporating long-term loop closure constraints while producing the optimal Bayesian solution. This architecture splits the inference problem into a low-latency update that incorporates new measurements using just the most recent states (filter), and a high-latency update that is capable of closing long loops and smooths using all past states (smoother). This architecture employs the probabilistic graphical models of factor graphs, which allows the low-latency inference and high-latency inference to be viewed as sub-operations of a single optimization performed within a single graphical model. A specific factorization of the full joint density is employed that allows the different inference operations to be performed asynchronously while still recovering the optimal solution produced by a full batch optimization. Due to the real-time, asynchronous nature of this algorithm, updates to the state estimates from the high-latency smoother will naturally be delayed until the smoother calculations have completed. This architecture has been tested within a simulated aerial environment and on real data collected from an autonomous ground vehicle. In all cases, the concurrent architecture is shown to recover the full batch solution, even while updated state estimates are produced in real-time. |
| first_indexed | 2024-09-23T08:59:27Z |
| format | Article |
| id | mit-1721.1/97575 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:59:27Z |
| publishDate | 2015 |
| publisher | Sage Publications |
| record_format | dspace |
| spelling | mit-1721.1/975752022-09-26T09:38:06Z Concurrent filtering and smoothing: A parallel architecture for real-time navigation and full smoothing Williams, Stephen Indelman, Vadim Kaess, Michael Roberts, Richard Leonard, John Joseph Dellaert, Frank Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Mechanical Engineering Leonard, John Joseph We present a parallelized navigation architecture that is capable of running in real-time and incorporating long-term loop closure constraints while producing the optimal Bayesian solution. This architecture splits the inference problem into a low-latency update that incorporates new measurements using just the most recent states (filter), and a high-latency update that is capable of closing long loops and smooths using all past states (smoother). This architecture employs the probabilistic graphical models of factor graphs, which allows the low-latency inference and high-latency inference to be viewed as sub-operations of a single optimization performed within a single graphical model. A specific factorization of the full joint density is employed that allows the different inference operations to be performed asynchronously while still recovering the optimal solution produced by a full batch optimization. Due to the real-time, asynchronous nature of this algorithm, updates to the state estimates from the high-latency smoother will naturally be delayed until the smoother calculations have completed. This architecture has been tested within a simulated aerial environment and on real data collected from an autonomous ground vehicle. In all cases, the concurrent architecture is shown to recover the full batch solution, even while updated state estimates are produced in real-time. United States. Air Force Research Laboratory. All Source Positioning and Navigation (ASPN) Program (Contract FA8650-11-C-7137) 2015-06-30T14:22:51Z 2015-06-30T14:22:51Z 2014-07 Article http://purl.org/eprint/type/JournalArticle 0278-3649 1741-3176 http://hdl.handle.net/1721.1/97575 Williams, S., V. Indelman, M. Kaess, R. Roberts, J. J. Leonard, and F. Dellaert. “Concurrent Filtering and Smoothing: A Parallel Architecture for Real-Time Navigation and Full Smoothing.” The International Journal of Robotics Research 33, no. 12 (July 14, 2014): 1544–1568. https://orcid.org/0000-0002-8863-6550 en_US http://dx.doi.org/10.1177/0278364914531056 The International Journal of Robotics Research Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Sage Publications Other univ. web domain |
| spellingShingle | Williams, Stephen Indelman, Vadim Kaess, Michael Roberts, Richard Leonard, John Joseph Dellaert, Frank Concurrent filtering and smoothing: A parallel architecture for real-time navigation and full smoothing |
| title | Concurrent filtering and smoothing: A parallel architecture for real-time navigation and full smoothing |
| title_full | Concurrent filtering and smoothing: A parallel architecture for real-time navigation and full smoothing |
| title_fullStr | Concurrent filtering and smoothing: A parallel architecture for real-time navigation and full smoothing |
| title_full_unstemmed | Concurrent filtering and smoothing: A parallel architecture for real-time navigation and full smoothing |
| title_short | Concurrent filtering and smoothing: A parallel architecture for real-time navigation and full smoothing |
| title_sort | concurrent filtering and smoothing a parallel architecture for real time navigation and full smoothing |
| url | http://hdl.handle.net/1721.1/97575 https://orcid.org/0000-0002-8863-6550 |
| work_keys_str_mv | AT williamsstephen concurrentfilteringandsmoothingaparallelarchitectureforrealtimenavigationandfullsmoothing AT indelmanvadim concurrentfilteringandsmoothingaparallelarchitectureforrealtimenavigationandfullsmoothing AT kaessmichael concurrentfilteringandsmoothingaparallelarchitectureforrealtimenavigationandfullsmoothing AT robertsrichard concurrentfilteringandsmoothingaparallelarchitectureforrealtimenavigationandfullsmoothing AT leonardjohnjoseph concurrentfilteringandsmoothingaparallelarchitectureforrealtimenavigationandfullsmoothing AT dellaertfrank concurrentfilteringandsmoothingaparallelarchitectureforrealtimenavigationandfullsmoothing |