Data-driven Loop Closure Detection in Bathymetric Point Clouds for Underwater SLAM

09/18/2022
by   Jiarui Tan, et al.
0

Simultaneous localization and mapping (SLAM) frameworks for autonomous navigation rely on robust data association to identify loop closures for back-end trajectory optimization. In the case of autonomous underwater vehicles (AUVs) equipped with multibeam echosounders (MBES), data association is particularly challenging due to the scarcity of identifiable landmarks in the seabed, the large drift in dead-reckoning navigation estimates to which AUVs are prone and the low resolution characteristic of MBES data. Deep learning solutions to loop closure detection have shown excellent performance on data from more structured environments. However, their transfer to the seabed domain is not immediate and efforts to port them are hindered by the lack of bathymetric datasets. Thus, in this paper we propose a neural network architecture aimed to showcase the potential of adapting such techniques to correspondence matching in bathymetric data. We train our framework on real bathymetry from an AUV mission and evaluate its performance on the tasks of loop closure detection and coarse point cloud alignment. Finally, we show its potential against a more traditional method and release both its implementation and the dataset used.

READ FULL TEXT

page 3

page 6

research
02/27/2023

GeoLCR: Attention-based Geometric Loop Closure and Registration

We present a novel algorithm for learning-based loop-closure for SLAM (s...
research
12/04/2017

Proving the existence of loops in robot trajectories

This paper presents a reliable method to verify the existence of loops a...
research
11/22/2022

SemanticLoop: loop closure with 3D semantic graph matching

Loop closure can effectively correct the accumulated error in robot loca...
research
05/24/2023

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

Place recognition using SOund Navigation and Ranging (SONAR) images is a...
research
03/14/2022

Drift Reduced Navigation with Deep Explainable Features

Modern autonomous vehicles (AVs) often rely on vision, LIDAR, and even r...
research
09/11/2018

Simultaneous Localization and Layout Model Selection in Manhattan Worlds

In this paper, we will demonstrate how Manhattan structure can be exploi...
research
06/12/2019

Adaptive Navigation Scheme for Optimal Deep-Sea Localization Using Multimodal Perception Cues

Underwater robot interventions require a high level of safety and reliab...

Please sign up or login with your details

Forgot password? Click here to reset