MARL-Based Multi-Satellite Intelligent Task Planning Method
In this article, we propose a solution to multi-satellite intelligent task planning using the multi-agent reinforcement learning (MARL) method. Fristly, we have developed a multi-satellite task planning model based on the Markov game framework. Furthermore, we have computationally designed a satelli...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10332252/ |
| _version_ | 1797361535059755008 |
|---|---|
| author | Guohui Zhang Xinhong Li Gangxuan Hu Yanyan Li Xun Wang Zhibin Zhang |
| author_facet | Guohui Zhang Xinhong Li Gangxuan Hu Yanyan Li Xun Wang Zhibin Zhang |
| author_sort | Guohui Zhang |
| collection | DOAJ |
| description | In this article, we propose a solution to multi-satellite intelligent task planning using the multi-agent reinforcement learning (MARL) method. Fristly, we have developed a multi-satellite task planning model based on the Markov game framework. Furthermore, we have computationally designed a satellite state transition function to address the task planning problem and successfully solved it using the multi-agent proximal policy optimization (MAPPO) algorithm. Our experimental results demonstrate that the MARL method exhibits remarkable convergence speed and performance, delivering significant rewards in multi-scale task planning scenarios. Consequently, it proves to be a highly suitable approach for multi-satellite intelligent task planning. |
| first_indexed | 2024-03-08T15:55:03Z |
| format | Article |
| id | doaj.art-dadb8ee6de354f30a03de581754606de |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T15:55:03Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-dadb8ee6de354f30a03de581754606de2024-01-09T00:02:27ZengIEEEIEEE Access2169-35362023-01-011113551713552810.1109/ACCESS.2023.333735810332252MARL-Based Multi-Satellite Intelligent Task Planning MethodGuohui Zhang0https://orcid.org/0000-0002-3782-6696Xinhong Li1Gangxuan Hu2Yanyan Li3Xun Wang4Zhibin Zhang5https://orcid.org/0000-0002-8112-7227Department of Aerospace Science and Technology, Space Engineering University, Beijing, ChinaDepartment of Aerospace Science and Technology, Space Engineering University, Beijing, ChinaDepartment of Aerospace Science and Technology, Space Engineering University, Beijing, ChinaDepartment of Aerospace Science and Technology, Space Engineering University, Beijing, ChinaDepartment of Aerospace Science and Technology, Space Engineering University, Beijing, ChinaDepartment of Aerospace Science and Technology, Space Engineering University, Beijing, ChinaIn this article, we propose a solution to multi-satellite intelligent task planning using the multi-agent reinforcement learning (MARL) method. Fristly, we have developed a multi-satellite task planning model based on the Markov game framework. Furthermore, we have computationally designed a satellite state transition function to address the task planning problem and successfully solved it using the multi-agent proximal policy optimization (MAPPO) algorithm. Our experimental results demonstrate that the MARL method exhibits remarkable convergence speed and performance, delivering significant rewards in multi-scale task planning scenarios. Consequently, it proves to be a highly suitable approach for multi-satellite intelligent task planning.https://ieeexplore.ieee.org/document/10332252/MARLmulti-satellite intelligent task planningMarkov gameMAPPO |
| spellingShingle | Guohui Zhang Xinhong Li Gangxuan Hu Yanyan Li Xun Wang Zhibin Zhang MARL-Based Multi-Satellite Intelligent Task Planning Method IEEE Access MARL multi-satellite intelligent task planning Markov game MAPPO |
| title | MARL-Based Multi-Satellite Intelligent Task Planning Method |
| title_full | MARL-Based Multi-Satellite Intelligent Task Planning Method |
| title_fullStr | MARL-Based Multi-Satellite Intelligent Task Planning Method |
| title_full_unstemmed | MARL-Based Multi-Satellite Intelligent Task Planning Method |
| title_short | MARL-Based Multi-Satellite Intelligent Task Planning Method |
| title_sort | marl based multi satellite intelligent task planning method |
| topic | MARL multi-satellite intelligent task planning Markov game MAPPO |
| url | https://ieeexplore.ieee.org/document/10332252/ |
| work_keys_str_mv | AT guohuizhang marlbasedmultisatelliteintelligenttaskplanningmethod AT xinhongli marlbasedmultisatelliteintelligenttaskplanningmethod AT gangxuanhu marlbasedmultisatelliteintelligenttaskplanningmethod AT yanyanli marlbasedmultisatelliteintelligenttaskplanningmethod AT xunwang marlbasedmultisatelliteintelligenttaskplanningmethod AT zhibinzhang marlbasedmultisatelliteintelligenttaskplanningmethod |