面向真实6G无人机通信的高效多模态波束预测:基于图像-位置-合成融合
Efficient Multimodal Beam Prediction for Real-World 6G UAV Communications via Image-Position-Synthetic Fusion
AI总结:
该研究针对真实6G无人机通信的高效波束预测问题,提出图像-位置-合成融合的多模态框架,在DeepSense 6G数据集上实现了更高的波束预测准确率,验证了多模态特征的互补价值。
摘要:
基于相机的波束选择可减少高移动性毫米波无人机链路中 exhaustive 信道测量的需求,但视觉与位置衍生表征的互补价值及其在模态退化下的表现仍需进一步研究。本文利用真实无人机测量数据开发了一种用于当前波束预测的分阶段多模态框架。所提出的32波束分类器结合了经ImageNet预训练的EfficientNet-B3视觉编码器与两种确定性位置衍生表征:显式几何-运动学向量及由位置构建的非线性合成特征基。图像与合成表征先进行融合,再与几何表征进行后期融合。在DeepSense 6G场景23上的实验表明,图像-合成融合达到了86.92%的Top-1准确率、99.03%的Top-3准确率和99.56%的Top-5准确率,相比仅图像推理的Top-1性能提升了2.64个百分点,且优于仅合成推理的60.71% Top-1准确率。添加几何-运动学分支后,测得性能最高,达到87.14%的Top-1准确率、99.12%的Top-3准确率和99.60%的Top-5准确率。受控输入干预进一步证明了该框架在视觉退化下的互补行为,以及对严重合成输入损坏的强敏感性。位置衍生的非线性特征为视觉上下文提供了互补信息,可改善所评估真实无人机场景中的当前波束预测。
英文摘要:
Camera-based beam selection can reduce the need for exhaustive channel measurement in highly mobile millimeter-wave UAV links, but the complementary value of visual and position-derived representations and their behavior under modality degradation require further investigation. This paper develops a staged multimodal framework for current-beam prediction using real-world UAV measurements. The proposed 32-beam classifier combines an ImageNet-pretrained EfficientNet-B3 visual encoder with two deterministic position-derived representations: an explicit Geometric-Kinematic vector and a nonlinear synthetic feature basis constructed from position. The image and synthetic representations are fused first, followed by late fusion with the geometry representation. Experiments on DeepSense 6G Scenario 23 show that Image-Synthetic fusion achieves 86.92% Top-1, 99.03% Top-3, and 99.56% Top-5 accuracy, improving Top-1 performance by 2.64 percentage points over image-only inference and outperforming the 60.71% Top-1 accuracy of synthetic-only inference. Adding the Geometric-Kinematic branch yields the highest measured performance, reaching 87.14% Top-1, 99.12% Top-3, and 99.60% Top-5 accuracy. Controlled input interventions further demonstrate complementary behavior under visual degradation and strong sensitivity to severe synthetic-input corruption. Position-derived nonlinear features provide complementary information to visual context and improve current-beam prediction in the evaluated real-world UAV setting.
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。