Online Stochastic Variational Gaussian Process Mapping for Large-Scale Bathymetric SLAM in Real Time

Rao-Blackwellized particle filter (RBPF) SLAM solutions with Gaussian Process (GP) maps can both maintain multiple hypotheses of a vehicle pose estimate and perform implicit data association for loop closure detection in continuous terrain representations. Both qualities are of particular interest f...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters 2023-06, Vol.8 (6), p.3150-3157
Main Authors: Torroba, Ignacio, Cella, Marco, Teran, Aldo, Rolleberg, Niklas, Folkesson, John
Format: Article
Language:English
Subjects:
Autonomous underwater vehicles
Gaussian process
Gaussian processes
Kernel
Marine robotics
Particle trajectories
Process mapping
Real time
Real-time systems
Simultaneous localization and mapping
SLAM
Time measurement
Training
Trajectory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rao-Blackwellized particle filter (RBPF) SLAM solutions with Gaussian Process (GP) maps can both maintain multiple hypotheses of a vehicle pose estimate and perform implicit data association for loop closure detection in continuous terrain representations. Both qualities are of particular interest for SLAM with autonomous underwater vehicles (AUVs) in the open sea, where distinguishable features are scarce. However, the applicability of GP regression to parallel, real-time mapping in an RBPF framework remains limited by the size of the area to survey and the computational cost of the GP training. To overcome these constraints, in this letter we propose the adaption of Stochastic Variational GP (SVGP) regression to online mapping in combination with a novel, efficient particle trajectory storing in the RBPF. We show how the resulting RBPF-SVGP framework can achieve real-time performance in an embedded platform on two AUV surveys containing millions of points. We further test the framework on a live mission on an AUV and we make the implementation publicly available.
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2023.3264750