Combinatorial Data Augmentation: A Key Enabler to Bridge Geometry- and Data-Driven WiFi Positioning

TL;DR

This paper introduces combinatorial data augmentation (CDA) to effectively integrate geometry-driven and data-driven WiFi positioning methods, improving accuracy and reliability through field experiments with WiFi RTTs and IMUs.

Contribution

The paper presents a novel CDA principle that enhances WiFi positioning by combining geometry- and data-driven approaches, validated through real-world experiments.

Findings

CDA filters unreliable preliminary estimate locations (PELs).

CDA improves Kalman filter fusion of WiFi RTT and IMU data.

Achieves an average positioning error of 1.51 meters.

Abstract

Due to the emergence of various wireless sensing technologies, numerous positioning algorithms have been introduced in the literature, categorized into \emph{geometry-driven positioning} (GP) and \emph{data-driven positioning} (DP). These approaches have respective limitations, e.g., a non-line-of-sight issue for GP and the lack of a labeled dataset for DP, which can be complemented by integrating both methods. To this end, this paper aims to introduce a novel principle called \emph{combinatorial data augmentation} (CDA), a catalyst for the two approaches' seamless integration. Specifically, GP-based datasets augmented from different combinations of positioning entities, called \emph{preliminary estimate locations} (PELs), can be used as DP's inputs. We confirm the CDA's effectiveness from field experiments based on WiFi \emph{round-trip times} (RTTs) and \emph{inertial measurement units} (IMUs) by designing several CDA-based positioning algorithms. First, we show that CDA offers various metrics quantifying each PEL's reliability, thereby filtering out unreliable PELs for WiFi RTT positioning. Second, CDA helps compute the measurement covariance matrix of a Kalman filter for fusing two position estimates derived by WiFi RTT and IMUs. Third, we use the above position estimate as the corresponding PEL's real-time label for fingerprint-based positioning as a representative DP algorithm. It provides accurate and reliable positioning results, says an average positioning error of $1.51$ (m) with a standard deviation of $0.88$~(m).