A Deep Q-Network-Based Collaborative Control Research for Smart Ammunition Formation
The smart ammunition formation (SAF) system model usually has the characteristics of complexity, time variation, and nonlinearity. With the consideration of random factors, such as sensor error and environmental disturbance, the system model cannot be modeled accurately. To deal with this problem, t...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | International Journal of Aerospace Engineering |
| Online Access: | http://dx.doi.org/10.1155/2022/2021693 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551209458728960 |
|---|---|
| author | Jian Shen Benkang Zhang Qingyu Zhu Pengyun Chen |
| author_facet | Jian Shen Benkang Zhang Qingyu Zhu Pengyun Chen |
| author_sort | Jian Shen |
| collection | DOAJ |
| description | The smart ammunition formation (SAF) system model usually has the characteristics of complexity, time variation, and nonlinearity. With the consideration of random factors, such as sensor error and environmental disturbance, the system model cannot be modeled accurately. To deal with this problem, this paper investigated an intelligent deep Q-network- (DQN-) based control algorithm for the SAF collaborative control, which deals with the high dynamics and uncertainty in the SAF flight environment. In the environment description of the SAF, we built a dynamic model to represent the system joint states, which referred to the smart ammunition’s velocity, the trajectory inclination angle, the ballistic deflection angle, and the relative position between different formation nodes. Next, we describe the SAF collaborative control process as a Markov decision process (MDP) with the application of the reinforcement learning (RL) technique. Then, the basic framework ε-imitation action-selecting strategy and the algorithm details were developed to address the SAF control problem based on the DQN scheme. Finally, the numerical simulation was carried out to verify the effectiveness and portability of the DQN-based algorithm. The average total reward curve showed a reasonable convergence, and the relative kinematic relationship among the formation nodes met the requirements of the controller design. It illustrated that the DQN-based algorithm obtained a novel performance in the SAF collaborative control. |
| format | Article |
| id | doaj-art-b2fc5c7386344b6db32956b5a0068f55 |
| institution | Kabale University |
| issn | 1687-5974 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Aerospace Engineering |
| spelling | doaj-art-b2fc5c7386344b6db32956b5a0068f552025-02-03T06:04:44ZengWileyInternational Journal of Aerospace Engineering1687-59742022-01-01202210.1155/2022/2021693A Deep Q-Network-Based Collaborative Control Research for Smart Ammunition FormationJian Shen0Benkang Zhang1Qingyu Zhu2Pengyun Chen3College of Mechatronics EngineeringCollege of Mechatronics EngineeringAVIC China Aero-Polytechnology EstablishmentCollege of Mechatronics EngineeringThe smart ammunition formation (SAF) system model usually has the characteristics of complexity, time variation, and nonlinearity. With the consideration of random factors, such as sensor error and environmental disturbance, the system model cannot be modeled accurately. To deal with this problem, this paper investigated an intelligent deep Q-network- (DQN-) based control algorithm for the SAF collaborative control, which deals with the high dynamics and uncertainty in the SAF flight environment. In the environment description of the SAF, we built a dynamic model to represent the system joint states, which referred to the smart ammunition’s velocity, the trajectory inclination angle, the ballistic deflection angle, and the relative position between different formation nodes. Next, we describe the SAF collaborative control process as a Markov decision process (MDP) with the application of the reinforcement learning (RL) technique. Then, the basic framework ε-imitation action-selecting strategy and the algorithm details were developed to address the SAF control problem based on the DQN scheme. Finally, the numerical simulation was carried out to verify the effectiveness and portability of the DQN-based algorithm. The average total reward curve showed a reasonable convergence, and the relative kinematic relationship among the formation nodes met the requirements of the controller design. It illustrated that the DQN-based algorithm obtained a novel performance in the SAF collaborative control.http://dx.doi.org/10.1155/2022/2021693 |
| spellingShingle | Jian Shen Benkang Zhang Qingyu Zhu Pengyun Chen A Deep Q-Network-Based Collaborative Control Research for Smart Ammunition Formation International Journal of Aerospace Engineering |
| title | A Deep Q-Network-Based Collaborative Control Research for Smart Ammunition Formation |
| title_full | A Deep Q-Network-Based Collaborative Control Research for Smart Ammunition Formation |
| title_fullStr | A Deep Q-Network-Based Collaborative Control Research for Smart Ammunition Formation |
| title_full_unstemmed | A Deep Q-Network-Based Collaborative Control Research for Smart Ammunition Formation |
| title_short | A Deep Q-Network-Based Collaborative Control Research for Smart Ammunition Formation |
| title_sort | deep q network based collaborative control research for smart ammunition formation |
| url | http://dx.doi.org/10.1155/2022/2021693 |
| work_keys_str_mv | AT jianshen adeepqnetworkbasedcollaborativecontrolresearchforsmartammunitionformation AT benkangzhang adeepqnetworkbasedcollaborativecontrolresearchforsmartammunitionformation AT qingyuzhu adeepqnetworkbasedcollaborativecontrolresearchforsmartammunitionformation AT pengyunchen adeepqnetworkbasedcollaborativecontrolresearchforsmartammunitionformation AT jianshen deepqnetworkbasedcollaborativecontrolresearchforsmartammunitionformation AT benkangzhang deepqnetworkbasedcollaborativecontrolresearchforsmartammunitionformation AT qingyuzhu deepqnetworkbasedcollaborativecontrolresearchforsmartammunitionformation AT pengyunchen deepqnetworkbasedcollaborativecontrolresearchforsmartammunitionformation |