Optimal Tasking of Ground-Based Sensors for Space Situational Awareness Using Deep Reinforcement Learning
Space situational awareness (SSA) is becoming increasingly challenging with the proliferation of resident space objects (RSOs), ranging from CubeSats to mega-constellations. Sensors within the United States Space Surveillance Network are tasked to repeatedly detect, characterize, and track these RSO...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2022
|
| Online Access: | https://hdl.handle.net/1721.1/145993 |
| _version_ | 1826192730366148608 |
|---|---|
| author | Siew, Peng Mun Linares, Richard |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Siew, Peng Mun Linares, Richard |
| author_sort | Siew, Peng Mun |
| collection | MIT |
| description | Space situational awareness (SSA) is becoming increasingly challenging with the proliferation of resident space objects (RSOs), ranging from CubeSats to mega-constellations. Sensors within the United States Space Surveillance Network are tasked to repeatedly detect, characterize, and track these RSOs to retain custody and estimate their attitude. The majority of these sensors consist of ground-based sensors with a narrow field of view and must be slew at a finite rate from one RSO to another during observations. This results in a complex combinatorial problem that poses a major obstacle to the SSA sensor tasking problem. In this work, we successfully applied deep reinforcement learning (DRL) to overcome the curse of dimensionality and optimally task a ground-based sensor. We trained several DRL agents using proximal policy optimization and population-based training in a simulated SSA environment. The DRL agents outperformed myopic policies in both objective metrics of RSOs’ state uncertainties and the number of unique RSOs observed over a 90-min observation window. The agents’ robustness to changes in RSO orbital regimes, observation window length, observer’s location, and sensor properties are also examined. The robustness of the DRL agents allows them to be applied to any arbitrary locations and scenarios. |
| first_indexed | 2024-09-23T09:28:03Z |
| format | Article |
| id | mit-1721.1/145993 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T09:28:03Z |
| publishDate | 2022 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | mit-1721.1/1459932023-06-30T15:49:41Z Optimal Tasking of Ground-Based Sensors for Space Situational Awareness Using Deep Reinforcement Learning Siew, Peng Mun Linares, Richard Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Space situational awareness (SSA) is becoming increasingly challenging with the proliferation of resident space objects (RSOs), ranging from CubeSats to mega-constellations. Sensors within the United States Space Surveillance Network are tasked to repeatedly detect, characterize, and track these RSOs to retain custody and estimate their attitude. The majority of these sensors consist of ground-based sensors with a narrow field of view and must be slew at a finite rate from one RSO to another during observations. This results in a complex combinatorial problem that poses a major obstacle to the SSA sensor tasking problem. In this work, we successfully applied deep reinforcement learning (DRL) to overcome the curse of dimensionality and optimally task a ground-based sensor. We trained several DRL agents using proximal policy optimization and population-based training in a simulated SSA environment. The DRL agents outperformed myopic policies in both objective metrics of RSOs’ state uncertainties and the number of unique RSOs observed over a 90-min observation window. The agents’ robustness to changes in RSO orbital regimes, observation window length, observer’s location, and sensor properties are also examined. The robustness of the DRL agents allows them to be applied to any arbitrary locations and scenarios. 2022-10-26T17:26:23Z 2022-10-26T17:26:23Z 2022-10-16 2022-10-26T11:07:53Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/145993 Sensors 22 (20): 7847 (2022) PUBLISHER_CC http://dx.doi.org/10.3390/s22207847 Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Multidisciplinary Digital Publishing Institute Multidisciplinary Digital Publishing Institute |
| spellingShingle | Siew, Peng Mun Linares, Richard Optimal Tasking of Ground-Based Sensors for Space Situational Awareness Using Deep Reinforcement Learning |
| title | Optimal Tasking of Ground-Based Sensors for Space Situational Awareness Using Deep Reinforcement Learning |
| title_full | Optimal Tasking of Ground-Based Sensors for Space Situational Awareness Using Deep Reinforcement Learning |
| title_fullStr | Optimal Tasking of Ground-Based Sensors for Space Situational Awareness Using Deep Reinforcement Learning |
| title_full_unstemmed | Optimal Tasking of Ground-Based Sensors for Space Situational Awareness Using Deep Reinforcement Learning |
| title_short | Optimal Tasking of Ground-Based Sensors for Space Situational Awareness Using Deep Reinforcement Learning |
| title_sort | optimal tasking of ground based sensors for space situational awareness using deep reinforcement learning |
| url | https://hdl.handle.net/1721.1/145993 |
| work_keys_str_mv | AT siewpengmun optimaltaskingofgroundbasedsensorsforspacesituationalawarenessusingdeepreinforcementlearning AT linaresrichard optimaltaskingofgroundbasedsensorsforspacesituationalawarenessusingdeepreinforcementlearning |