Fuzzy Reinforcement Learning-Based Secure Capture and Formation Control for Multiagent Pursuit-Evasion Game
IEEE Transactions on Fuzzy Systems · 2026-05 · 34 (5) · 1630-1643
DOI: 10.1109/tfuzz.2026.3667941 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Fuzzy Systems, 2026-05. Verfasst von Haitao Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Ministry of Science and Information and Communications Technology, National Research Foundation of Korea.
Abstract (Originalsprache)
This article studies the distributed optimal strategy problem in multiagent pursuit-evasion game for capture and formation control under false data injection attacks (FDIAs) and input saturation constraints. In the game, pursuers aim to approach evaders, while evaders attempt to keep a distance, and agents within the same team are required to preserve cohesion. To achieve control objectives under the FDIAs and input saturation constraints, a hierarchical control framework is developed, which includes a sliding-mode control (SMC) layer and an optimal control layer. Moreover, the SMC strategy is designed to mitigate the effects of FDIAs and input saturation. Then, since the sliding-mode dynamics involves coupling terms associated with formation displacement, a fuzzy reinforcement learning-based optimal control strategy is proposed to achieve capture and formation aims. Furthermore, based on the Lyapunov method, it is proven that all closed-loop signals are uniformly ultimately bounded. Finally, the effectiveness of the proposed method is validated by simulations conducted on distributed mobile robots.
Förderung
- National Natural Science Foundation of China
- Ministry of Science and Information and Communications Technology
- National Research Foundation of Korea
- SEU Innovation Capability Enhancement Plan for Doctoral Students
Zitieren
APA
Wang, H., Liu, Q., & Park, J. H. (2026). Fuzzy Reinforcement Learning-Based Secure Capture and Formation Control for Multiagent Pursuit-Evasion Game. IEEE Transactions on Fuzzy Systems, 34(5), 1630-1643. https://doi.org/10.1109/tfuzz.2026.3667941
Vancouver
Wang H, Liu Q, Park JH. Fuzzy Reinforcement Learning-Based Secure Capture and Formation Control for Multiagent Pursuit-Evasion Game. IEEE Transactions on Fuzzy Systems. 2026;34(5):1630-1643. doi:10.1109/tfuzz.2026.3667941
BibTeX
@article{Wang2026,
author = {Wang, Haitao and Liu, Qingshan and Park, Ju H.},
title = {Fuzzy Reinforcement Learning-Based Secure Capture and Formation Control for Multiagent Pursuit-Evasion Game},
journal = {IEEE Transactions on Fuzzy Systems},
year = {2026},
volume = {34},
number = {5},
pages = {1630--1643},
doi = {10.1109/tfuzz.2026.3667941}
}
EUVIMED