UAV Control Method Combining Reptile Meta-Reinforcement Learning and Generative Adversarial Imitation Learning

Article


Jiang, Shui, Ge, Yanning, Yang, Xu, Yang, Wencheng and Cui, Hui. 2024. "UAV Control Method Combining Reptile Meta-Reinforcement Learning and Generative Adversarial Imitation Learning." Future Internet. 16 (3). https://doi.org/10.3390/fi16030105
Article Title

UAV Control Method Combining Reptile Meta-Reinforcement Learning and Generative Adversarial Imitation Learning

ERA Journal ID212586
Article CategoryArticle
AuthorsJiang, Shui, Ge, Yanning, Yang, Xu, Yang, Wencheng and Cui, Hui
Journal TitleFuture Internet
Journal Citation16 (3)
Number of Pages18
Year2024
PublisherMDPI AG
Place of PublicationSwitzerland
ISSN1999-5903
Digital Object Identifier (DOI)https://doi.org/10.3390/fi16030105
Web Address (URL)https://www.mdpi.com/1999-5903/16/3/105
Abstract

Reinforcement learning (RL) is pivotal in empowering Unmanned Aerial Vehicles (UAVs) to navigate and make decisions efficiently and intelligently within complex and dynamic surroundings. Despite its significance, RL is hampered by inherent limitations such as low sample efficiency, restricted generalization capabilities, and a heavy reliance on the intricacies of reward function design. These challenges often render single-method RL approaches inadequate, particularly in the context of UAV operations where high costs and safety risks in real-world applications cannot be overlooked. To address these issues, this paper introduces a novel RL framework that synergistically integrates meta-learning and imitation learning. By leveraging the Reptile algorithm from meta-learning and Generative Adversarial Imitation Learning (GAIL), coupled with state normalization techniques for processing state data, this framework significantly enhances the model’s adaptability. It achieves this by identifying and leveraging commonalities across various tasks, allowing for swift adaptation to new challenges without the need for complex reward function designs. To ascertain the efficacy of this integrated approach, we conducted simulation experiments within both two-dimensional environments. The empirical results clearly indicate that our GAIL-enhanced Reptile method surpasses conventional single-method RL algorithms in terms of training efficiency. This evidence underscores the potential of combining meta-learning and imitation learning to surmount the traditional barriers faced by reinforcement learning in UAV trajectory planning and decision-making processes.

Keywordsunmanned aerial vehicles (UAVs); meta-reinforcement learning; enerative adversarial imitation learning
Contains Sensitive ContentDoes not contain sensitive content
ANZSRC Field of Research 2020460304. Computer vision
Byline AffiliationsFujian Normal University, China
Minjiang University, China
School of Mathematics, Physics and Computing
Monash University
Permalink -

https://research.usq.edu.au/item/z5y70/uav-control-method-combining-reptile-meta-reinforcement-learning-and-generative-adversarial-imitation-learning

Download files


Published Version
futureinternet-16-00105.pdf
License: CC BY 4.0
File access level: Anyone

  • 2
    total views
  • 0
    total downloads
  • 0
    views this month
  • 0
    downloads this month

Export as

Related outputs

Evaluating Cryptocurrency Market Risk on the Blockchain: An Empirical Study Using the ARMA-GARCH-VaR Model
Huang, Yongrong, Wang, Huiqing, Chen, Zhide, Feng, Chen, Zhu, Kexin, Yang, Xu and Yang, Wencheng. 2024. "Evaluating Cryptocurrency Market Risk on the Blockchain: An Empirical Study Using the ARMA-GARCH-VaR Model." IEEE Open Journal of the Computer Society. 5, pp. 83-94. https://doi.org/10.1109/OJCS.2024.3370603
Feature extraction and learning approaches for cancellable biometrics: A survey
Yang, Wencheng, Wang, Song, Hu, Jiankun, Tao, Xiaohui and Li, Yan. 2024. "Feature extraction and learning approaches for cancellable biometrics: A survey." CAAI Transactions on Intelligence Technology. 9 (1), pp. 4-25. https://doi.org/10.1049/cit2.12283
An Adaptive Feature Fusion Network for Alzheimer’s Disease Prediction
Wei, Shicheng, Li, Yan and Yang, Wencheng. 2023. "An Adaptive Feature Fusion Network for Alzheimer’s Disease Prediction." 12th International Conference on Health Information Science (HIS 2023). Melbourne, Australia 23 - 24 Oct 2023 Germany. https://doi.org/10.1007/978-981-99-7108-4
A Review of Homomorphic Encryption for Privacy-Preserving Biometrics
Yang, Wencheng, Wang, Song, Cui, Hui, Tang, Zhaohui and Li, Yan. 2023. "A Review of Homomorphic Encryption for Privacy-Preserving Biometrics." Sensors. 23 (7). https://doi.org/10.3390/s23073566
Hybrid KD-NFT: A multi-layered NFT assisted robust Knowledge Distillation framework for Internet of Things
Wang, Nai, Chen, Junjun, Wu, Di, Yang, Wencheng, Xiang, Yong and Sajjanhar, Atul. 2023. "Hybrid KD-NFT: A multi-layered NFT assisted robust Knowledge Distillation framework for Internet of Things." Journal of Information Security and Applications. 75. https://doi.org/10.1016/j.jisa.2023.103483
A review of multi-factor authentication in the Internet of Healthcare Things
Suleski, Tance, Ahmed, Mohiuddin, Yang, Wencheng and Wang, Eugene. 2023. "A review of multi-factor authentication in the Internet of Healthcare Things." Digital Health. 9, pp. 1-20. https://doi.org/10.1177/20552076231177144
Token-Based Biometric Enhanced Key Derivation for Authentication Over Wireless Networks
Cui, Hui, Yang, Xuechao, Yang, Wencheng, Qin, Baodong and Yi, Xun. 2023. "Token-Based Biometric Enhanced Key Derivation for Authentication Over Wireless Networks." IEEE Transactions on Network Science and Engineering. 10 (4), pp. 2347-2357. https://doi.org/10.1109/TNSE.2023.3246439
A Secure Online Fingerprint Authentication System for Industrial IoT Devices over 5G Networks
Bedari, Aseel, Wang, Song and Yang, Wencheng. 2022. "A Secure Online Fingerprint Authentication System for Industrial IoT Devices over 5G Networks." Sensors. 22 (19), pp. 1-16. https://doi.org/10.3390/s22197609
Multimedia security and privacy protection in the internet of things: research developments and challenges
Yang, Wencheng, Wang, Song, Hu, Jiankun and Karie, Nickson M.. 2022. "Multimedia security and privacy protection in the internet of things: research developments and challenges." International Journal of Multimedia Intelligence and Security. 4 (1), pp. 20-46. https://doi.org/10.1504/ijmis.2022.121282
A linear convolution-based cancelable fingerprint biometric authentication system
Yang, Wencheng, Wang, Song, Kang, James Jin, Johnstone, Michael N. and Bedari, Aseel. 2022. "A linear convolution-based cancelable fingerprint biometric authentication system." Computers and Security. 114, pp. 1-14. https://doi.org/10.1016/j.cose.2021.102583
A Review on Security Issues and Solutions of the Internet of Drones
Yang, Wencheng, Wang, Song, Yin, Xuefei, Wang, Xu and Hu, Jiankun. 2022. "A Review on Security Issues and Solutions of the Internet of Drones." IEEE Open Journal of the Computer Society. 3, pp. 96-110. https://doi.org/10.1109/OJCS.2022.3183003
Network Forensics in the Era of Artificial Intelligence
Yang, Wencheng, Johnstone, Michael N., Wang, Song, Karie, Nickson M., Bin Sahri, Nor Masri and Kang, James Jin. 2022. "Network Forensics in the Era of Artificial Intelligence." Ahmed, Mohiuddin, Islam, Sheikh Rabiul, Anwar, Adnan, Moustafa, Nour and Pathan, Al-Sakib Khan (ed.) Explainable Artificial Intelligence for Cyber Security: Next Generation Artificial Intelligence. Cham, Switzerland. Springer. pp. 171-190
Leveraging Artificial Intelligence Capabilities for Real-Time Monitoring of Cybersecurity Threats
Karie, Nickson M., Bin Sahri, Nor Masri Bin, Yang, Wencheng and Johnstone, Michael N.. 2022. "Leveraging Artificial Intelligence Capabilities for Real-Time Monitoring of Cybersecurity Threats." Ahmed, Mohiuddin, Islam, Sheikh Rabiul, Anwar, Adnan, Moustafa, Nour and Pathan, Al-Sakib Khan (ed.) Explainable Artificial Intelligence for Cyber Security: Next Generation Artificial Intelligence. Cham, Switzerland. Springer. pp. 141-169