A Framework for Underwater Vehicle Localization based on Cross-view and Cross-domain Acoustic and Aerial Images

Abstract

Underwater robot localization is a challenging task due to the lack of a Global Positioning System (GPS). However, the capability to match georeferenced aerial images and acoustic underwater data can help on this task. Autonomous hybrid aerial and underwater vehicles also demand new localization methods capable of combining the perception from both environments. This paper proposes a cross-domain and cross-view localization framework based on color aerial images and underwater acoustic images. The method identify the correlation between the images from the different domains to improve the underwater localization. The method is designed to match images acquired in partially structured environments with shared features, such as harbors and marinas. The approach is validated on a real dataset acquired by an underwater vehicle in a marina. The results shows a improvement in the localization when compared to the dead reckoning of the vehicle.