Avoiding Obstacles via Missile Real-Time Inference by Reinforcement Learning
In the contemporary battlefield where complexity has increased, the enhancement of the role and ability of missiles has become crucial. Thus, missile guidance systems are required to be further developed in a more intelligent and autonomous way to deal with complicated environments. In this paper, w...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4142 |
| _version_ | 1797505740084084736 |
|---|---|
| author | Daseon Hong Sungsu Park |
| author_facet | Daseon Hong Sungsu Park |
| author_sort | Daseon Hong |
| collection | DOAJ |
| description | In the contemporary battlefield where complexity has increased, the enhancement of the role and ability of missiles has become crucial. Thus, missile guidance systems are required to be further developed in a more intelligent and autonomous way to deal with complicated environments. In this paper, we propose novel missile guidance laws using reinforcement learning, which can autonomously avoid obstacles and terrains in complicated environments with limited prior information and even without the need of off-line trajectory or waypoint generation. The proposed guidance laws are focused on two mission scenarios: the first is with planar obstacles, which is used to cope with maritime operations, and the second is with complex terrain, which is used to cope with land operations. We present the detailed design processes for both scenarios, including a neural network architecture, reward function selection, and training method. Simulation results are provided to show the feasibility and effectiveness of the proposed guidance laws and some important aspects are discussed in terms of their advantages and limitations. |
| first_indexed | 2024-03-10T04:22:32Z |
| format | Article |
| id | doaj.art-0fb8f747aa6d49b0a98282c4197f8184 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:22:32Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0fb8f747aa6d49b0a98282c4197f81842023-11-23T07:44:50ZengMDPI AGApplied Sciences2076-34172022-04-01129414210.3390/app12094142Avoiding Obstacles via Missile Real-Time Inference by Reinforcement LearningDaseon Hong0Sungsu Park1Department of Aerospace Engineering, Sejong University, Seoul 05006, KoreaDepartment of Aerospace Engineering, Sejong University, Seoul 05006, KoreaIn the contemporary battlefield where complexity has increased, the enhancement of the role and ability of missiles has become crucial. Thus, missile guidance systems are required to be further developed in a more intelligent and autonomous way to deal with complicated environments. In this paper, we propose novel missile guidance laws using reinforcement learning, which can autonomously avoid obstacles and terrains in complicated environments with limited prior information and even without the need of off-line trajectory or waypoint generation. The proposed guidance laws are focused on two mission scenarios: the first is with planar obstacles, which is used to cope with maritime operations, and the second is with complex terrain, which is used to cope with land operations. We present the detailed design processes for both scenarios, including a neural network architecture, reward function selection, and training method. Simulation results are provided to show the feasibility and effectiveness of the proposed guidance laws and some important aspects are discussed in terms of their advantages and limitations.https://www.mdpi.com/2076-3417/12/9/4142missile guidanceobstacle avoidancereinforcement learningtwin delayed deep deterministic policy gradient |
| spellingShingle | Daseon Hong Sungsu Park Avoiding Obstacles via Missile Real-Time Inference by Reinforcement Learning Applied Sciences missile guidance obstacle avoidance reinforcement learning twin delayed deep deterministic policy gradient |
| title | Avoiding Obstacles via Missile Real-Time Inference by Reinforcement Learning |
| title_full | Avoiding Obstacles via Missile Real-Time Inference by Reinforcement Learning |
| title_fullStr | Avoiding Obstacles via Missile Real-Time Inference by Reinforcement Learning |
| title_full_unstemmed | Avoiding Obstacles via Missile Real-Time Inference by Reinforcement Learning |
| title_short | Avoiding Obstacles via Missile Real-Time Inference by Reinforcement Learning |
| title_sort | avoiding obstacles via missile real time inference by reinforcement learning |
| topic | missile guidance obstacle avoidance reinforcement learning twin delayed deep deterministic policy gradient |
| url | https://www.mdpi.com/2076-3417/12/9/4142 |
| work_keys_str_mv | AT daseonhong avoidingobstaclesviamissilerealtimeinferencebyreinforcementlearning AT sungsupark avoidingobstaclesviamissilerealtimeinferencebyreinforcementlearning |