Reinforcement Learning-Based Target State Estimation Under Communication Constraints
IEEE Sensors Journal · 01.05.2026 · 26 (9) · 14194-14206
DOI: 10.1109/jsen.2026.3676721 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.05.2026. Verfasst von Yiming Chen und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Key Research and Development Plan of China, China Postdoctoral Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
To address the cooperative target tracking problem in sensor-networked distributed state estimation with constrained communication resources, a method, reinforcement learning-based event-triggered cubature Kalman filter (RL-ETCKF), is proposed. First, the method derives closed-form solutions for optimal estimation and event-triggered gains under event-triggered conditions, forming the foundation of a distributed cooperative estimation algorithm that supports multinode information fusion. Second, by integrating reinforcement learning (RL) with an adaptive event-triggered mechanism, RL-ETCKF enables intelligent adjustment of communication frequency based on multidimensional state perception and dynamic thresholding, which effectively balances communication load and estimation accuracy. In the final step, the algorithm fuses local information across the network in a cooperative manner, maintaining robustness under limited bandwidth conditions. Extensive simulations based on typical maneuvering target scenarios demonstrate that the proposed RL-ETCKF method significantly reduces communication overhead while enhancing estimation accuracy and tracking performance compared to conventional distributed estimation approaches.
Förderung
- National Key Research and Development Plan of China
- China Postdoctoral Science Foundation
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
Zitieren
APA
Chen, Y., Zhang, Z., Guo, Z., Zhang, K., & Li, Q. (2026). Reinforcement Learning-Based Target State Estimation Under Communication Constraints. IEEE Sensors Journal, 26(9), 14194-14206. https://doi.org/10.1109/jsen.2026.3676721
Vancouver
Chen Y, Zhang Z, Guo Z, Zhang K, Li Q. Reinforcement Learning-Based Target State Estimation Under Communication Constraints. IEEE Sensors Journal. 2026;26(9):14194-14206. doi:10.1109/jsen.2026.3676721
BibTeX
@article{Chen2026,
author = {Chen, Yiming and Zhang, Zheng and Guo, Zheng and Zhang, Kanghao and Li, Qingdong},
title = {Reinforcement Learning-Based Target State Estimation Under Communication Constraints},
journal = {IEEE Sensors Journal},
year = {2026},
volume = {26},
number = {9},
pages = {14194--14206},
doi = {10.1109/jsen.2026.3676721}
}
EUVIMED