Feature-Based Global Localization for Underwater Terrain Aided Navigation Using Bag of Words

This paper presents a novel feature-based global localization method for underwater terrain aided navigation (UTAN) using Bag of Words (BoW). Before the mission, the prior bathymetric map is segmented into submaps, and the handcrafted terrain gradient features are extracted from the submaps. Subsequently, a BoW is trained using these features, and the submaps are indexed accordingly. During the UTAN mission, place recognition is achieved by matching the index of the newly collected submap with the indexes of the submaps in the database, and the vehicle pose is determined using TEASER++ registration method. Experimental results using a sea trial dataset demonstrate that the proposed method can achieve a fast and robust global localization without requiring the prior initial vehicle pose information, offering robustness against substantial initial positioning and heading errors.