arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.02563eess.SP
收藏

低空无线网络中的预测波束成形:一种交叉注意力方法

Predictive Beamforming in Low-Altitude Wireless Networks: A Cross-Attention Approach

Southern University of Science and Technology(南方科技大学);Beijing Institute of Technology(北京理工大学)

Xiaotong Zhao, Yuanhao Cui, Weijie Yuan, Ziye Jia, Heng Liu, Chengwen Xing

AI总结:

本文提出一种基于交叉注意力融合机制的多模态预测波束成形方法,通过联合利用视觉和结构化传感器数据,提升动态低空无线网络中波束预测的准确性和适应性。

摘要:

准确的波束预测对于维持可靠链路和高频谱效率在动态低空无线网络中至关重要。然而,现有方法往往无法捕捉异构传感模态之间的深层相关性,限制了其在复杂三维环境中的适应性。为了解决这些挑战,我们提出了一种基于交叉注意力融合机制的多模态预测波束成形方法,该方法联合利用视觉和结构化传感器数据。所提出的模型利用卷积神经网络(CNN)从视觉图像中学习多尺度空间特征层次,并利用Transformer编码器捕捉传感器数据中的跨维依赖性。然后引入一个交叉注意力融合模块,将两种模态之间的互补信息整合起来,生成统一且具有区分性的表示,以实现准确的波束预测。通过在真实世界数据集上进行的实验评估,我们的方法达到了79.7%的Top-1准确率和99.3%的Top-3准确率,超越了3D ResNet-Transformer基线方法在Top-1到Top-5指标上的4.4%-23.2%。这些结果验证了多模态交叉注意力融合在动态低空无线网络中智能波束选择中的有效性。

英文摘要:

Accurate beam prediction is essential for maintaining reliable links and high spectral efficiency in dynamic low-altitude wireless networks. However, existing approaches often fail to capture the deep correlations across heterogeneous sensing modalities, limiting their adaptability in complex three-dimensional environments. To overcome these challenges, we propose a multi-modal predictive beamforming method based on a cross-attention fusion mechanism that jointly leverages visual and structured sensor data. The proposed model utilizes a Convolutional Neural Network (CNN) to learn multi-scale spatial feature hierarchies from visual images and a Transformer encoder to capture cross-dimensional dependencies within sensor data. Then, a cross-attention fusion module is introduced to integrate complementary information between the two modalities, generating a unified and discriminative representation for accurate beam prediction. Through experimental evaluations conducted on a real-world dataset, our method reaches 79.7% Top-1 accuracy and 99.3% Top-3 accuracy, surpassing the 3D ResNet-Transformer baseline by 4.4%-23.2% across Top-1 to Top-5 metrics. These results verify that multi-modal cross-attention fusion is effective for intelligent beam selection in dynamic low-altitude wireless networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑