A Neural-enhanced Factor Graph-based Algorithm for Robust Positioning in Obstructed LOS Situations

TL;DR

This paper introduces a neural-enhanced factor graph algorithm that combines physics-based and data-driven models for accurate and robust localization in environments with obstructed line-of-sight conditions, outperforming existing methods.

Contribution

It develops a novel hybrid probabilistic model and a factor graph-based algorithm that fuse physics-based and data-driven information for improved positioning in multipath environments.

Findings

Significantly outperforms state-of-the-art localization methods in obstructed LOS scenarios.

Achieves near-optimal accuracy close to the posterior Cramer-Rao lower bound.

Effective even with limited training data in local regions.

Abstract

This paper presents a neural-enhanced probabilistic model and corresponding factor graph-based sum-product algorithm for robust localization and tracking in multipath-prone environments. The introduced hybrid probabilistic model consists of physics-based and data-driven measurement models capturing the information contained in both, the line-of-sight (LOS) component as well as in multipath components (NLOS components). The physics-based and data-driven models are embedded in a joint Bayesian framework allowing to derive from first principles a factor graph-based algorithm that fuses the information of these models. The proposed algorithm uses radio signal measurements from multiple base stations to robustly estimate the mobile agent's position together with all model parameters. It provides high localization accuracy by exploiting the position-related information of the LOS component via the physics-based model and robustness by exploiting the geometric imprint of multipath components independent of the propagation channel via the data-driven model. In a challenging numerical experiment involving obstructed LOS situations to all anchors, we show that the proposed sequential algorithm significantly outperforms state-of-the-art methods and attains the posterior Cramer-Rao lower bound even with training data limited to local regions.