DeepAoANet: Learning Angle of Arrival from Software Defined Radios with Deep Neural Networks

TL;DR

DeepAoANet leverages deep neural networks to accurately estimate the Angle of Arrival from SDR data, outperforming traditional methods especially in multipath indoor environments, and operates in real-time.

Contribution

This paper introduces a novel deep learning-based AoA estimation method using SDR data, demonstrating high accuracy and real-time capability in challenging environments.

Findings

Achieved mean absolute AoA errors less than 2 degrees.

Effectively estimated multiple AoAs in multipath scenarios.

Demonstrated real-time inference on various platforms.

Abstract

Direction finding and positioning systems based on RF signals are significantly impacted by multipath propagation, particularly in indoor environments. Existing algorithms (e.g MUSIC) perform poorly in resolving Angle of Arrival (AoA) in the presence of multipath or when operating in a weak signal regime. We note that digitally sampled RF frontends allow for the easy analysis of signals, and their delayed components. Low-cost Software-Defined Radio (SDR) modules enable Channel State Information (CSI) extraction across a wide spectrum, motivating the design of an enhanced Angle-of-Arrival (AoA) solution. We propose a Deep Learning approach to deriving AoA from a single snapshot of the SDR multichannel data. We compare and contrast deep-learning based angle classification and regression models, to estimate up to two AoAs accurately. We have implemented the inference engines on different platforms to extract AoAs in real-time, demonstrating the computational tractability of our approach. To demonstrate the utility of our approach we have collected IQ (In-phase and Quadrature components) samples from a four-element Universal Linear Array (ULA) in various Light-of-Sight (LOS) and Non-Line-of-Sight (NLOS) environments, and published the dataset. Our proposed method demonstrates excellent reliability in determining number of impinging signals and realized mean absolute AoA errors less than $2^{\circ}$.