EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Dynamic Time Division ISAC Beamforming for Vehicular Networks

Junseok Lim, Jaewoo So iD

Sensors · 30.04.2026 · 26 (9) · 2790

DOI: 10.3390/s26092790 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.04.2026. Verfasst von Junseok Lim und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering, Sogang University, Seoul 04107, Republic of Korea. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sogang University Research Grant of 2026.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Integrated sensing and communications (ISAC) is a promising key technology for vehicular networks, because it allows roadside units to support both data transmission and radar-like sensing over the same spectrum and hardware platform. In conventional time division ISAC systems, each frame is divided into sensing and communication phases with a fixed ratio, which determines the tradeoff between the sensing accuracy and the communication throughput. However, in high-mobility vehicular environments, a fixed sensing–communication split is often suboptimal due to time-varying channel and intervehicle interference variations. In this paper, we propose a dynamic sensing–communication time division and ISAC beamforming scheme that minimizes the Cramér–Rao lower bound while satisfying the minimum effective communication sum rate. We further develop a deep reinforcement learning framework based on proximal policy optimization to find the optimal time division ratio and beamforming vectors. Simulation results show that the proposed dynamic time division beamforming scheme significantly outperforms the conventional fixed time division beamforming schemes in terms of sensing accuracy and the communication sum rate.

Schlagwörter

Stichwörter der Autor:innen

Cramér–Rao lower bound (CRLB)ISAC beamformingdynamic time divisionintegrated sensing and communications (ISAC)proximal policy optimization (PPO)vehicular communications

Autor:innen und Institutionen

  • Department of Electronic Engineering, Sogang University, Seoul 04107, Republic of Korea.

ORCID-Profile: Jaewoo So

Förderung

  • Sogang University Research Grant of 2026

Zitieren

APA

Lim, J., & So, J. (2026). Deep Learning-Based Dynamic Time Division ISAC Beamforming for Vehicular Networks. Sensors, 26(9), 2790. https://doi.org/10.3390/s26092790

Vancouver

Lim J, So J. Deep Learning-Based Dynamic Time Division ISAC Beamforming for Vehicular Networks. Sensors. 2026;26(9):2790. doi:10.3390/s26092790

BibTeX
@article{Lim2026,
  author = {Lim, Junseok and So, Jaewoo},
  title = {Deep Learning-Based Dynamic Time Division ISAC Beamforming for Vehicular Networks},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2790},
  doi = {10.3390/s26092790}
}
Kostenlos starten →