Event-Driven Transformer-Based Reinforcement Learning for Trajectory Design and Channel Assignment in Multi-AAV Assisted Communication
IEEE Transactions on Cognitive Communications and Networking · 2025-12 · 11 (6) · 4254-4266
DOI: 10.1109/tccn.2025.3549603 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2025-12. Verfasst von Zikai Feng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Scientific Research Fund Project of Hainan University, Natural Science Foundation of Hainan Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
In the assisted communication system with multiple autonomous aerial vehicle base stations (AAV BSs), it is a challenge to achieve optimized trajectory design and channel assignment in unknown environments. Multi-agent reinforcement learning has proved effective for the above policy optimization. However, most existing baseline methods suffer from the excessive communication overhead and information explosion, which results in poor performance. In this paper, a novel event-driven transformer multi-agent reinforcement learning (EDT-MARL) framework is proposed to solve the multi-AAV assisted communication problem. The event-driven listening policy optimization is designed to learn the best strategy of event-driven listening based on the current channel states, which reduces unnecessary information listening for AAV BSs effectively. The transformer mechanism is used to extract useful information and patterns from massive observational information, so that the critic network of AAV BSs can evaluate the state information more accurately. Simulation results indicate that the proposed approach attains improved convergence over the baselines. AAV BSs learn the optimal trajectory design and channel assignment strategies to achieve their maximum cumulative rewards. Additionally, considering the cooperation and competition between AAV BSs, the proposed method with monotonic convergence provides an estimated Nash equilibrium for the multi-AAV assisted communication Markov game.
Förderung
- Scientific Research Fund Project of Hainan University
- Natural Science Foundation of Hainan Province
- National Natural Science Foundation of China
Zitieren
APA
Feng, Z., Wu, D., Huang, M., & Yuen, C. (2025). Event-Driven Transformer-Based Reinforcement Learning for Trajectory Design and Channel Assignment in Multi-AAV Assisted Communication. IEEE Transactions on Cognitive Communications and Networking, 11(6), 4254-4266. https://doi.org/10.1109/tccn.2025.3549603
Vancouver
Feng Z, Wu D, Huang M, Yuen C. Event-Driven Transformer-Based Reinforcement Learning for Trajectory Design and Channel Assignment in Multi-AAV Assisted Communication. IEEE Transactions on Cognitive Communications and Networking. 2025;11(6):4254-4266. doi:10.1109/tccn.2025.3549603
BibTeX
@article{Feng2025,
author = {Feng, Zikai and Wu, Di and Huang, Mengxing and Yuen, Chau},
title = {Event-Driven Transformer-Based Reinforcement Learning for Trajectory Design and Channel Assignment in Multi-AAV Assisted Communication},
journal = {IEEE Transactions on Cognitive Communications and Networking},
year = {2025},
volume = {11},
number = {6},
pages = {4254--4266},
doi = {10.1109/tccn.2025.3549603}
}
EUVIMED