Phase-Only Positioning: Overcoming Integer Ambiguity Challenge through Deep Learning

TL;DR

This paper introduces deep learning methods for phase-only positioning in cell-free systems, effectively resolving the integer ambiguity problem and significantly reducing inference complexity for high-precision 6G positioning.

Contribution

The paper presents two novel deep learning approaches that overcome integer ambiguity in phase-only positioning, enhancing accuracy and efficiency in distributed antenna systems.

Findings

Achieves 2-3 orders of magnitude reduction in inference complexity.

Demonstrates improved positioning accuracy over baseline methods.

Validates effectiveness in simulated 6G system scenarios.

Abstract

This paper investigates uplink carrier phase positioning (CPP) in cell-free (CF) or distributed antenna system context, assuming a challenging case where only phase measurements are utilized as observations. In general, CPP can achieve sub-meter to centimeter-level accuracy but is challenged by the integer ambiguity problem. In this work, we propose two deep learning approaches for phase-only positioning, overcoming the integer ambiguity challenge. The first one directly uses phase measurements, while the second one first estimates integer ambiguities and then integrates them with phase measurements for improved accuracy. Our numerical results demonstrate that an inference complexity reduction of two to three orders of magnitude is achieved, compared to maximum likelihood baseline solution, depending on the approach and parameter configuration. This emphasizes the potential of the developed deep learning solutions for efficient and precise positioning in future CF 6G systems.