LLM in V2I: A Data-Driven Predictive Beamforming Framework for Vehicle Tracking in Near-Field ISAC Systems
IEEE Journal on Selected Areas in Communications · 2026 · 44 · 2510-2527
DOI: 10.1109/jsac.2025.3643394 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Communications, 2026. Verfasst von Hongjia Huang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
In this paper, we investigate the problem of predictive beamforming design for tracking vehicles in an integrated sensing and communication (ISAC)-based near-field vehicle-to-infrastructure (V2I) system. The waveform design in near-field scenarios requires the joint consideration of both range and angle dimensions, posing new challenges to conventional beamforming and tracking strategies. To address this issue, we propose a predictive beamforming framework leveraging a large language model (LLM)-based neural network (LNN), which exploits historical channel state information (CSI) to facilitate accurate future beamforming decisions. Cramér–Rao bounds (CRBs) for angle and distance estimation, along with the achievable sum-rate, are applied as key metrics to evaluate the sensing and communication performance of the V2I system, respectively. Capitalizing on the derived performance metrics, we formulate the optimization problems aiming either to maximize the sum-rate subject to CRB constraints or to minimize the CRB while ensuring a required communication rate, thereby accommodating different design requirements. Moreover, to effectively capture the stochastic nature of vehicle driving behavior, the performance metrics are further expressed in expectation form over the distribution of possible driving states. Consequently, a data-driven optimization approach based on the LNN is adopted to handle the resulting intractable analytical expressions, and the underlying LNN is trained with task-specific loss functions. During the training process, low-rank adaptation (LoRA) is incorporated to fine-tune the pre-trained LLM, which significantly reduces the number of trainable parameters. Simulation results demonstrate that the proposed framework accurately predicts future vehicle kinematic parameters and effectively optimizes the power allocation across transmit links. As a result, it achieves superior and robust performance in both communication and sensing tasks, highlighting its potential as a vital solution for next-generation near-field V2I systems.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Guangdong Province
- Shenzhen Science and Technology Program
- ZTE Industry-University-Institute Cooperation Funds
- La Trobe University Start-Up Package
- La Trobe University Research Project–School of Computing, Engineering and Mathematical Sciences (SCMES) CaRE and Beyond Scheme
Zitieren
APA
Huang, H., Yuan, W., Liu, C., Liu, L., Liu, F., Xiang, W., & Ng, D. W. K. (2026). LLM in V2I: A Data-Driven Predictive Beamforming Framework for Vehicle Tracking in Near-Field ISAC Systems. IEEE Journal on Selected Areas in Communications, 44, 2510-2527. https://doi.org/10.1109/jsac.2025.3643394
Vancouver
Huang H, Yuan W, Liu C, Liu L, Liu F, Xiang W, et al. LLM in V2I: A Data-Driven Predictive Beamforming Framework for Vehicle Tracking in Near-Field ISAC Systems. IEEE Journal on Selected Areas in Communications. 2026;44:2510-2527. doi:10.1109/jsac.2025.3643394
BibTeX
@article{Huang2026,
author = {Huang, Hongjia and Yuan, Weijie and Liu, Chang and Liu, Liang and Liu, Fan and Xiang, Wei and Ng, Derrick Wing Kwan},
title = {LLM in V2I: A Data-Driven Predictive Beamforming Framework for Vehicle Tracking in Near-Field ISAC Systems},
journal = {IEEE Journal on Selected Areas in Communications},
year = {2026},
volume = {44},
pages = {2510--2527},
doi = {10.1109/jsac.2025.3643394}
}
EUVIMED