Multi-UAV Redeployment Optimization Based on Multi-Agent Deep Reinforcement Learning Oriented to Swarm Performance Restoration
Distributed artificial intelligence is increasingly being applied to multiple unmanned aerial vehicles (multi-UAVs). This poses challenges to the distributed reconfiguration (DR) required for the optimal redeployment of multi-UAVs in the event of vehicle destruction. This paper presents a multi-agen...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/23/9484 |
| _version_ | 1827592031997788160 |
|---|---|
| author | Qilong Wu Zitao Geng Yi Ren Qiang Feng Jilong Zhong |
| author_facet | Qilong Wu Zitao Geng Yi Ren Qiang Feng Jilong Zhong |
| author_sort | Qilong Wu |
| collection | DOAJ |
| description | Distributed artificial intelligence is increasingly being applied to multiple unmanned aerial vehicles (multi-UAVs). This poses challenges to the distributed reconfiguration (DR) required for the optimal redeployment of multi-UAVs in the event of vehicle destruction. This paper presents a multi-agent deep reinforcement learning-based DR strategy (DRS) that optimizes the multi-UAV group redeployment in terms of swarm performance. To generate a two-layer DRS between multiple groups and a single group, a multi-agent deep reinforcement learning framework is developed in which a QMIX network determines the swarm redeployment, and each deep Q-network determines the single-group redeployment. The proposed method is simulated using Python and a case study demonstrates its effectiveness as a high-quality DRS for large-scale scenarios. |
| first_indexed | 2024-03-09T01:42:58Z |
| format | Article |
| id | doaj.art-59302e2de172498d999e6e3605ea22c0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T01:42:58Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-59302e2de172498d999e6e3605ea22c02023-12-08T15:26:10ZengMDPI AGSensors1424-82202023-11-012323948410.3390/s23239484Multi-UAV Redeployment Optimization Based on Multi-Agent Deep Reinforcement Learning Oriented to Swarm Performance RestorationQilong Wu0Zitao Geng1Yi Ren2Qiang Feng3Jilong Zhong4School of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaDefense Innovation Institute, Academy of Military Science, Beijing 100071, ChinaDistributed artificial intelligence is increasingly being applied to multiple unmanned aerial vehicles (multi-UAVs). This poses challenges to the distributed reconfiguration (DR) required for the optimal redeployment of multi-UAVs in the event of vehicle destruction. This paper presents a multi-agent deep reinforcement learning-based DR strategy (DRS) that optimizes the multi-UAV group redeployment in terms of swarm performance. To generate a two-layer DRS between multiple groups and a single group, a multi-agent deep reinforcement learning framework is developed in which a QMIX network determines the swarm redeployment, and each deep Q-network determines the single-group redeployment. The proposed method is simulated using Python and a case study demonstrates its effectiveness as a high-quality DRS for large-scale scenarios.https://www.mdpi.com/1424-8220/23/23/9484distributed reconfiguration strategymulti-agent deep reinforcement learningunmanned aerial vehicle (UAV)UAV swarm redeployment |
| spellingShingle | Qilong Wu Zitao Geng Yi Ren Qiang Feng Jilong Zhong Multi-UAV Redeployment Optimization Based on Multi-Agent Deep Reinforcement Learning Oriented to Swarm Performance Restoration Sensors distributed reconfiguration strategy multi-agent deep reinforcement learning unmanned aerial vehicle (UAV) UAV swarm redeployment |
| title | Multi-UAV Redeployment Optimization Based on Multi-Agent Deep Reinforcement Learning Oriented to Swarm Performance Restoration |
| title_full | Multi-UAV Redeployment Optimization Based on Multi-Agent Deep Reinforcement Learning Oriented to Swarm Performance Restoration |
| title_fullStr | Multi-UAV Redeployment Optimization Based on Multi-Agent Deep Reinforcement Learning Oriented to Swarm Performance Restoration |
| title_full_unstemmed | Multi-UAV Redeployment Optimization Based on Multi-Agent Deep Reinforcement Learning Oriented to Swarm Performance Restoration |
| title_short | Multi-UAV Redeployment Optimization Based on Multi-Agent Deep Reinforcement Learning Oriented to Swarm Performance Restoration |
| title_sort | multi uav redeployment optimization based on multi agent deep reinforcement learning oriented to swarm performance restoration |
| topic | distributed reconfiguration strategy multi-agent deep reinforcement learning unmanned aerial vehicle (UAV) UAV swarm redeployment |
| url | https://www.mdpi.com/1424-8220/23/23/9484 |
| work_keys_str_mv | AT qilongwu multiuavredeploymentoptimizationbasedonmultiagentdeepreinforcementlearningorientedtoswarmperformancerestoration AT zitaogeng multiuavredeploymentoptimizationbasedonmultiagentdeepreinforcementlearningorientedtoswarmperformancerestoration AT yiren multiuavredeploymentoptimizationbasedonmultiagentdeepreinforcementlearningorientedtoswarmperformancerestoration AT qiangfeng multiuavredeploymentoptimizationbasedonmultiagentdeepreinforcementlearningorientedtoswarmperformancerestoration AT jilongzhong multiuavredeploymentoptimizationbasedonmultiagentdeepreinforcementlearningorientedtoswarmperformancerestoration |