Erik Leitinger

TL;DR: It is demonstrated that new millimeter-wave (mm-wave) technology, under investigation for 5G communications systems, will be able to provide centimeter (cm)-accuracy indoor localization in a robust manner, ideally suited for AL.

TL;DR: A unified framework is presented for the quantification of position-related information, using the concept of equivalent Fisher information, for multipath-assisted positioning, and results show the applicability of the framework for the characterization of the localization capabilities of a given environment.

Abstract: This paper provides an initial investigation on the application of convolutional neural networks (CNNs) for fingerprint-based positioning using measured massive MIMO channels. When represented in appropriate domains, massive MIMO channels have a sparse structure which can be efficiently learned by CNNs for positioning purposes. We evaluate the positioning accuracy of state-of-the-art CNNs with channel fingerprints generated from a channel model with a rich clustered structure: the COST 2100 channel model. We find that moderately deep CNNs can achieve fractional-wavelength positioning accuracies, provided that an enough representative data set is available for training.

TL;DR: A Bayesian model of the SLAM problem is developed and represents it by a factor graph, which enables the use of belief propagation for efficient marginalization of the joint posterior distribution and the resulting BP-based SLAM algorithm detects the VAs associated with the PAs and estimates jointly the time-varying position of the mobile agent.

TL;DR: This letter presents the improvement of a multipath-assisted tracking approach using information about the relevance of deterministic multipath components in an environment using information fed to a tracking filter as an observation noise model.