Neural RF SLAM for unsupervised positioning and mapping with channel state information

IEEE International Conference on Communications (ICC)(2022)

引用 3|浏览18
暂无评分
摘要
We present a neural network architecture for jointly learning user locations and environment mapping up to isometry, in an unsupervised way, from channel state information (CSI) values with no location information. The model is based on an encoder-decoder architecture. The encoder network maps CSI values to the user location. The decoder network models the physics of propagation by parametrizing the environment using virtual anchors. It aims at reconstructing, from the encoder output and virtual anchor location, the set of time of flights (ToFs) that are extracted from CSI using super-resolution methods. The neural network task is set prediction and is accordingly trained end-to-end. The proposed model learns an interpretable latent, i.e., user location, by just enforcing a physics-based decoder. It is shown that the proposed model achieves sub-meter accuracy on synthetic ray tracing based datasets with single anchor SISO setup while recovering the environment map up to 4cm median error in a 2D environment and 15cm in a 3D environment
更多
查看译文
关键词
environment map,neural RF SLAM,unsupervised positioning,channel state information,neural network architecture,user location,environment mapping,location information,encoder-decoder architecture,encoder network maps CSI,decoder network models,virtual anchors,encoder output,virtual anchor location,neural network task,physics-based decoder,single anchor SISO setup,median error
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要