Robust Imaging Sonar-based Place Recognition and Localization in Underwater Environments

TL;DR

This paper introduces a robust, training-free imaging SONAR-based place recognition method for underwater SLAM, utilizing geometric encoding, hierarchical search, and adaptive techniques to improve robustness and efficiency across diverse underwater environments.

Contribution

It presents a novel, training-free approach that encodes geometric information from raw SONAR data and employs hierarchical search and adaptive methods for robust underwater place recognition.

Findings

Improved robustness in underwater place recognition across multiple datasets

Effective handling of rotation and translation variations in SONAR images

Enhanced speed and accuracy in SONAR frame retrieval

Abstract

Place recognition using SOund Navigation and Ranging (SONAR) images is an important task for simultaneous localization and mapping(SLAM) in underwater environments. This paper proposes a robust and efficient imaging SONAR based place recognition, SONAR context, and loop closure method. Unlike previous methods, our approach encodes geometric information based on the characteristics of raw SONAR measurements without prior knowledge or training. We also design a hierarchical searching procedure for fast retrieval of candidate SONAR frames and apply adaptive shifting and padding to achieve robust matching on rotation and translation changes. In addition, we can derive the initial pose through adaptive shifting and apply it to the iterative closest point (ICP) based loop closure factor. We evaluate the performance of SONAR context in the various underwater sequences such as simulated open water, real water tank, and real underwater environments. The proposed approach shows the robustness and improvements of place recognition on various datasets and evaluation metrics. Supplementary materials are available at https://github.com/sparolab/sonar_context.git.