A Semantic-Aided Particle Filter Approach for AUV Localization

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 selflocalization.

AUV localisation: a review of passive and active techniques

“…Whenever the environment surrounding the vehicle can be represented by specific high-level concepts, semantic-aided localisation can be performed. As outlined by Maurelli and Krupiński, a semantic-aided localisation approach can have several advantages, among which computational efficiency Maurelli and Krupiński (2018). Semantic-aided localisation is still very much unexplored for the underwater domain, whilst it has become more popular in indoor robotics.…”