基于变分自编码器的人工智能无人仓库无线传播预测
摘要
随着数据密集型应用需求的不断增长以及新兴技术的快速普及，无线通信将迎来显著的变革。为充分发挥5G及其以上技术的潜力，信号处理技术、创新的网络架构和高效的频谱利用策略方面都需要取得显著进展。这些进展促进了新兴技术的无缝集成，推动了工业数字化转型和连接化。本文提出了一种新颖的基于变分自编码器（VAE）的框架——针对5G无线频段内的自动化工业4.0环境（如仓库和工厂车间）的无线基础设施智能仓库方案（Wireless Infrastructure for Smart Warehouses using VAE, WISVA），用于精准的室内无线电传播建模。研究深入探讨了训练数据张量的精细创建过程，这些张量捕捉了受多样化障碍物影响的复杂电磁（EM）波行为，并阐述了所提出VAE模型的体系结构和训练方法。通过在各种场景下的SINR热力图预测能力，包括去噪任务、验证数据集、对未见配置的外推以及以前未遇到的仓库布局，展示了该模型的鲁棒性和适应性。 presented compelling reconstruction error heatmaps, highlighting the superior accuracy of WISVA compared to traditional autoencoder models. The paper also analyzes the model's performance in handling complex smart warehouse environments, demonstrating its potential as a key enabler for optimizing wireless infrastructure in Industry 4.0.
引用
@article{arxiv.2506.22456,
title = {AI-Driven Radio Propagation Prediction in Automated Warehouses using Variational Autoencoders},
author = {Rahul Gulia and Amlan Ganguly and Andres Kwasinski and Michael E. Kuhl and Ehsan Rashedi and Clark Hochgraf},
journal= {arXiv preprint arXiv:2506.22456},
year = {2025}
}
备注
Found a fundamental error (data leakage) in cross-validation setup affecting both papers. This issue compromises the model training and results, making performance claims unreliable and potentially misleading. We request withdrawal of current versions (v1) to prevent the dissemination of incorrect scientific findings. Corrected versions will be submitted later