LOS Delay Estimation using Super Resolution Deep Neural Networks for Precise Positioning

Precise positioning in 5G that can enable a wide variety of new use cases. We investigate the problem of accurate line-of-sight (LOS) delay estimation of an observed wireless channel using deep neural networks (NN). These delay estimates are the primary building block for deriving accurate position estimates. Our work proposes a custom super-resolution NN that exploits the properties of the wireless channel to guide the NN design. We compare against traditional algorithms used for LOS detection and show that the proposed NN shows excellent performance in the presence of weak LOS signals and dense multipath; scenarios that are challenging for traditional signal processing algorithms.