Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight Data
Recently, autonomous flight has emerged as a key technology in the aerospace and defense sectors; however, traditional code-based autonomous flight systems face limitations in complex environments. Although reinforcement learning offers an alternative, its practical application in real-world setting...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/4/264 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850183540192313344 |
|---|---|
| author | Uicheon Lee Seonah Lee Kyonghoon Kim |
| author_facet | Uicheon Lee Seonah Lee Kyonghoon Kim |
| author_sort | Uicheon Lee |
| collection | DOAJ |
| description | Recently, autonomous flight has emerged as a key technology in the aerospace and defense sectors; however, traditional code-based autonomous flight systems face limitations in complex environments. Although reinforcement learning offers an alternative, its practical application in real-world settings is hindered by the substantial data requirements. In this study, we develop a framework that integrates a Generative Adversarial Network (GAN) and Hindsight Experience Replay (HER) into model-based reinforcement learning to enhance data efficiency and accuracy. We compared the proposed framework against existing algorithms in actual quadcopter control. In the comparative experiment, we demonstrated an improvement of up to 70.59% in learning speed, clearly highlighting the impact of the environmental model. To the best of our knowledge, this study is the first where a GAN and HER are combined with model-based reinforcement learning, and it is expected to contribute significantly to the practical application of reinforcement learning in autonomous flight. |
| format | Article |
| id | doaj-art-4ac5fa35a4e042c39878c83106dc1e8e |
| institution | OA Journals |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-4ac5fa35a4e042c39878c83106dc1e8e2025-08-20T02:17:20ZengMDPI AGDrones2504-446X2025-03-019426410.3390/drones9040264Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight DataUicheon Lee0Seonah Lee1Kyonghoon Kim2Department of AI Convergence Engineering, Gyeongsang National University, Jinju 52828, Republic of KoreaDepartment of AI Convergence Engineering, Gyeongsang National University, Jinju 52828, Republic of KoreaSchool of Computer Science and Engineering, Kyungpook National University, Daegu 41566, Republic of KoreaRecently, autonomous flight has emerged as a key technology in the aerospace and defense sectors; however, traditional code-based autonomous flight systems face limitations in complex environments. Although reinforcement learning offers an alternative, its practical application in real-world settings is hindered by the substantial data requirements. In this study, we develop a framework that integrates a Generative Adversarial Network (GAN) and Hindsight Experience Replay (HER) into model-based reinforcement learning to enhance data efficiency and accuracy. We compared the proposed framework against existing algorithms in actual quadcopter control. In the comparative experiment, we demonstrated an improvement of up to 70.59% in learning speed, clearly highlighting the impact of the environmental model. To the best of our knowledge, this study is the first where a GAN and HER are combined with model-based reinforcement learning, and it is expected to contribute significantly to the practical application of reinforcement learning in autonomous flight.https://www.mdpi.com/2504-446X/9/4/264MBRL (model-based reinforcement learning)GANs (generative adversarial networks)HER (hindsight experience replay)autonomous flight |
| spellingShingle | Uicheon Lee Seonah Lee Kyonghoon Kim Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight Data Drones MBRL (model-based reinforcement learning) GANs (generative adversarial networks) HER (hindsight experience replay) autonomous flight |
| title | Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight Data |
| title_full | Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight Data |
| title_fullStr | Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight Data |
| title_full_unstemmed | Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight Data |
| title_short | Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight Data |
| title_sort | data efficient reinforcement learning framework for autonomous flight based on real world flight data |
| topic | MBRL (model-based reinforcement learning) GANs (generative adversarial networks) HER (hindsight experience replay) autonomous flight |
| url | https://www.mdpi.com/2504-446X/9/4/264 |
| work_keys_str_mv | AT uicheonlee dataefficientreinforcementlearningframeworkforautonomousflightbasedonrealworldflightdata AT seonahlee dataefficientreinforcementlearningframeworkforautonomousflightbasedonrealworldflightdata AT kyonghoonkim dataefficientreinforcementlearningframeworkforautonomousflightbasedonrealworldflightdata |