EUVIMEDEUVIMED entdecken
Crossref

Dual-Driven Pattern-Coupled Sparse Bayesian Learning Unfolding Network for Decentralized Noncoherent DoA Estimation in UAV Swarm

Liujie Lv, Sheng Wu, Ailing Xiao, Zhe Ji, Haoge Jia, Linling Kuang

IEEE Internet of Things Journal · 15.08.2025 · 12 (16) · 33592-33604

DOI: 10.1109/jiot.2025.3577155 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 15.08.2025. Verfasst von Liujie Lv und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Start-up Fund for Newly Introduced Teacher, National Key Laboratory Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The collaboration among multiple uncrewed aerial vehicles (UAVs) can overcome the limitation of spatial sensing capabilities of individual UAVs has attracted extensive attention in the field of Direction-of-Arrival (DoA) estimation. Considering the constrained hardware resources in UAV swarm, maintaining coherence among all elements is extremely challenging. In this article, we consider a collaborative UAV swarm with partly calibrated subarrays and propose a dual-driven joint-sparse pattern-coupled sparse Bayesian learning unfolding network (DD-JPC-SBLNet) for noncoherent DoA estimation. Specifically, we first propose a novel joint-sparse pattern-coupled sparse Bayesian learning (JPC-SBL) algorithm, which introduces a pattern-coupled model and a distributed noise variance estimation module, to improve the noncoherent DoA estimation accuracy. Then, the JPC-SBL algorithm is unfolded into cascaded customized neural networks, each of which learns the optimal coupling parameter configuration based on the pattern-coupled model and learns the current optimal signal hyperparameter update rule with a data-driven customized neural network. By effectively combining the advantages of model-driven and data-driven, the proposed dual-driven unfolding network exhibits superior convergence performance and speed. Simulation results demonstrate that the proposed method not only outperforms existing methods in terms of estimation accuracy and angular resolution, but also reduces computational complexity by more than 50% compared with other SBL-based algorithms.

Förderung

  • National Natural Science Foundation of China
  • Start-up Fund for Newly Introduced Teacher
  • National Key Laboratory Foundation of China

Zitieren

APA

Lv, L., Wu, S., Xiao, A., Ji, Z., Jia, H., & Kuang, L. (2025). Dual-Driven Pattern-Coupled Sparse Bayesian Learning Unfolding Network for Decentralized Noncoherent DoA Estimation in UAV Swarm. IEEE Internet of Things Journal, 12(16), 33592-33604. https://doi.org/10.1109/jiot.2025.3577155

Vancouver

Lv L, Wu S, Xiao A, Ji Z, Jia H, Kuang L. Dual-Driven Pattern-Coupled Sparse Bayesian Learning Unfolding Network for Decentralized Noncoherent DoA Estimation in UAV Swarm. IEEE Internet of Things Journal. 2025;12(16):33592-33604. doi:10.1109/jiot.2025.3577155

BibTeX
@article{Lv2025,
  author = {Lv, Liujie and Wu, Sheng and Xiao, Ailing and Ji, Zhe and Jia, Haoge and Kuang, Linling},
  title = {Dual-Driven Pattern-Coupled Sparse Bayesian Learning Unfolding Network for Decentralized Noncoherent DoA Estimation in UAV Swarm},
  journal = {IEEE Internet of Things Journal},
  year = {2025},
  volume = {12},
  number = {16},
  pages = {33592--33604},
  doi = {10.1109/jiot.2025.3577155}
}
Kostenlos starten →