# A semantic-aided particle filter approach for AUV localization

## TL;DR

This paper introduces a semantic-aided particle filter for autonomous underwater vehicle localization, enhancing traditional geometric methods by integrating environmental semantic information for improved accuracy.

## Contribution

It extends the standard particle filter with semantic data, demonstrating advantages over purely geometric approaches in underwater localization.

## Key findings

- Semantic layer improves localization accuracy
- Enhanced robustness in complex environments
- Outperforms geometric-only methods

## Abstract

This paper presents a novel approach to AUV localization, based on a semantic-aided particle filter. Particle filters have been used successfully for robotics localization since many years. Most of the approaches are however based on geometric measurements and geometric information and simulations. In the past years more and more efforts from research goes towards cognitive robotics and the marine domain is not exception. Moving from signal to symbol becomes therefore paramount for more complex applications. This paper presents a contribution in the well-known area of underwater localization, incorporating semantic information. An extension to the standard particle filter approach is presented, based on semantic information of the environment. A comparison with the geometric approach shows the advantages of a semantic layer to successfully perform self-localization.