Adaptive generalized ZEM-ZEV feedback guidance for planetary landing via a deep reinforcement learning approach
© 2020 IAA Precision landing on large and small planetary bodies is a technology of utmost importance for future human and robotic exploration of the solar system. In this context, the Zero-Effort-Miss/Zero-Effort-Velocity (ZEM/ZEV) feedback guidance algorithm has been studied extensively and is sti...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2021
|
| Online Access: | https://hdl.handle.net/1721.1/135439 |
| _version_ | 1826195922401361920 |
|---|---|
| author | Furfaro, Roberto Scorsoglio, Andrea Linares, Richard Massari, Mauro |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Furfaro, Roberto Scorsoglio, Andrea Linares, Richard Massari, Mauro |
| author_sort | Furfaro, Roberto |
| collection | MIT |
| description | © 2020 IAA Precision landing on large and small planetary bodies is a technology of utmost importance for future human and robotic exploration of the solar system. In this context, the Zero-Effort-Miss/Zero-Effort-Velocity (ZEM/ZEV) feedback guidance algorithm has been studied extensively and is still a field of active research. The algorithm, although powerful in terms of accuracy and ease of implementation, has some limitations. Therefore with this paper we present an adaptive guidance algorithm based on classical ZEM/ZEV in which machine learning is used to overcome its limitations and create a closed loop guidance algorithm that is sufficiently lightweight to be implemented on board spacecraft and flexible enough to be able to adapt to the given constraint scenario. The adopted methodology is an actor-critic reinforcement learning algorithm that learns the parameters of the above-mentioned guidance architecture according to the given problem constraints. |
| first_indexed | 2024-09-23T10:17:38Z |
| format | Article |
| id | mit-1721.1/135439 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:17:38Z |
| publishDate | 2021 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1354392023-09-19T19:00:47Z Adaptive generalized ZEM-ZEV feedback guidance for planetary landing via a deep reinforcement learning approach Furfaro, Roberto Scorsoglio, Andrea Linares, Richard Massari, Mauro Massachusetts Institute of Technology. Department of Aeronautics and Astronautics © 2020 IAA Precision landing on large and small planetary bodies is a technology of utmost importance for future human and robotic exploration of the solar system. In this context, the Zero-Effort-Miss/Zero-Effort-Velocity (ZEM/ZEV) feedback guidance algorithm has been studied extensively and is still a field of active research. The algorithm, although powerful in terms of accuracy and ease of implementation, has some limitations. Therefore with this paper we present an adaptive guidance algorithm based on classical ZEM/ZEV in which machine learning is used to overcome its limitations and create a closed loop guidance algorithm that is sufficiently lightweight to be implemented on board spacecraft and flexible enough to be able to adapt to the given constraint scenario. The adopted methodology is an actor-critic reinforcement learning algorithm that learns the parameters of the above-mentioned guidance architecture according to the given problem constraints. 2021-10-27T20:23:28Z 2021-10-27T20:23:28Z 2020 2021-05-05T18:37:13Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/135439 en 10.1016/J.ACTAASTRO.2020.02.051 Acta Astronautica Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV MIT web domain |
| spellingShingle | Furfaro, Roberto Scorsoglio, Andrea Linares, Richard Massari, Mauro Adaptive generalized ZEM-ZEV feedback guidance for planetary landing via a deep reinforcement learning approach |
| title | Adaptive generalized ZEM-ZEV feedback guidance for planetary landing via a deep reinforcement learning approach |
| title_full | Adaptive generalized ZEM-ZEV feedback guidance for planetary landing via a deep reinforcement learning approach |
| title_fullStr | Adaptive generalized ZEM-ZEV feedback guidance for planetary landing via a deep reinforcement learning approach |
| title_full_unstemmed | Adaptive generalized ZEM-ZEV feedback guidance for planetary landing via a deep reinforcement learning approach |
| title_short | Adaptive generalized ZEM-ZEV feedback guidance for planetary landing via a deep reinforcement learning approach |
| title_sort | adaptive generalized zem zev feedback guidance for planetary landing via a deep reinforcement learning approach |
| url | https://hdl.handle.net/1721.1/135439 |
| work_keys_str_mv | AT furfaroroberto adaptivegeneralizedzemzevfeedbackguidanceforplanetarylandingviaadeepreinforcementlearningapproach AT scorsoglioandrea adaptivegeneralizedzemzevfeedbackguidanceforplanetarylandingviaadeepreinforcementlearningapproach AT linaresrichard adaptivegeneralizedzemzevfeedbackguidanceforplanetarylandingviaadeepreinforcementlearningapproach AT massarimauro adaptivegeneralizedzemzevfeedbackguidanceforplanetarylandingviaadeepreinforcementlearningapproach |