CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion
share
Channel state information (CSI)-based fingerprinting via neural networks (NNs) is a promising approach to enable accurate indoor and outdoor positioning of user equipments (UEs), even under challenging propagation conditions. In this paper, we propose a CSI-based positioning pipeline for wireless LAN MIMO-OFDM systems operating indoors, which relies on NNs that extract a probability map indicating the likelihood of a UE being at a given grid point. We propose methods to fuse these probability maps at a centralized processor, which enables improved positioning accuracy if CSI is acquired at different access points (APs) and extracted from different transmit antennas. To improve positioning accuracy, we propose the design of CSI features that are robust to hardware and system impairments arising in real-world MIMO-OFDM transceivers. We provide experimental results with real-world indoor measurements under line-of-sight (LoS) and non-LoS propagation conditions, and for multi-antenna and multi-AP measurements. Our results demonstrate that probability fusion significantly improves positioning accuracy without requiring exact synchronization between APs and that centimeter-level median distance error is achievable.
READ FULL TEXT
