Direct Localization in Underwater Acoustics via Convolutional Neural Networks: A Data-Driven Approach

TL;DR

This paper introduces the first data-driven convolutional neural network approach for direct underwater acoustic source localization, outperforming traditional methods and approaching oracle-level accuracy.

Contribution

It presents a novel CNN-based DLOC method with tailored architecture and training, advancing underwater localization without prior environmental knowledge.

Findings

Outperforms existing alternatives in localization accuracy

Asymptotically matches oracle optimal model-based solutions

Demonstrates robustness and efficiency in underwater scenarios

Abstract

Direct localization (DLOC) methods, which use the observed data to localize a source at an unknown position in a one-step procedure, generally outperform their indirect two-step counterparts (e.g., using time-difference of arrivals). However, underwater acoustic DLOC methods require prior knowledge of the environment, and are computationally costly, hence slow. We propose, what is to the best of our knowledge, the first data-driven DLOC method. Inspired by classical and contemporary optimal model-based DLOC solutions, and leveraging the capabilities of convolutional neural networks (CNNs), we devise a holistic CNN-based solution. Our method includes a specifically-tailored input structure, architecture, loss function, and a progressive training procedure, which are of independent interest in the broader context of machine learning. We demonstrate that our method outperforms attractive alternatives, and asymptotically matches the performance of an oracle optimal model-based solution.