Single cluster PHD SLAM: Application to autonomous underwater vehicles using stereo vision

Sharad Nagappa; Narcis Palomeras; Chee Sing Lee; Nuno Gracias; Daniel E Clark; Joaquim Salvi

doi:10.1109/OCEANS-Bergen.2013.6608107

Single cluster PHD SLAM: Application to autonomous underwater vehicles using stereo vision

Sharad Nagappa, Narcis Palomeras, Chee Sing Lee, Nuno Gracias, Daniel E Clark, Joaquim Salvi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Citations (Scopus)

Abstract

This paper considers the application of feature-based simultaneous localisation and mapping (SLAM) using a random finite sets (RFS) framework for an autonomous underwater vehicle. SLAM allows for reduction in localisation error by tracking features which provide a fixed external reference. The SLAM problem is addressed here using a single-cluster probability hypothesis density (PHD) filter. The filter uses a particle approximation for the vehicle position with a conditional Gaussian mixture PHD for the feature map. Map features are selected as unique point features generated from a stereo camera on-board the vehicle. We demonstrate the improvement in localisation applying the algorithm to a dataset obtained in an indoor test tank.

Original language	English
Title of host publication	MTS/IEEE OCEANS - Bergen
Subtitle of host publication	The Challenges of the Northern Dimension
Publisher	IEEE
ISBN (Print)	9781479900022
DOIs	https://doi.org/10.1109/OCEANS-Bergen.2013.6608107
Publication status	Published - 2013
Event	OCEANS 2013 - Bergen, Norway Duration: 10 Jun 2013 → 13 Jun 2013

Conference

Conference	OCEANS 2013
Country/Territory	Norway
City	Bergen
Period	10/06/13 → 13/06/13

ASJC Scopus subject areas

Ocean Engineering

Access to Document

10.1109/OCEANS-Bergen.2013.6608107

Cite this

@inproceedings{3c4813504a8d44b89ba67a1820be02a4,

title = "Single cluster PHD SLAM: Application to autonomous underwater vehicles using stereo vision",

abstract = "This paper considers the application of feature-based simultaneous localisation and mapping (SLAM) using a random finite sets (RFS) framework for an autonomous underwater vehicle. SLAM allows for reduction in localisation error by tracking features which provide a fixed external reference. The SLAM problem is addressed here using a single-cluster probability hypothesis density (PHD) filter. The filter uses a particle approximation for the vehicle position with a conditional Gaussian mixture PHD for the feature map. Map features are selected as unique point features generated from a stereo camera on-board the vehicle. We demonstrate the improvement in localisation applying the algorithm to a dataset obtained in an indoor test tank.",

author = "Sharad Nagappa and Narcis Palomeras and Lee, {Chee Sing} and Nuno Gracias and Clark, {Daniel E} and Joaquim Salvi",

year = "2013",

doi = "10.1109/OCEANS-Bergen.2013.6608107",

language = "English",

isbn = "9781479900022",

booktitle = "MTS/IEEE OCEANS - Bergen",

publisher = "IEEE",

address = "United States",

note = "OCEANS 2013 ; Conference date: 10-06-2013 Through 13-06-2013",

}

TY - GEN

T1 - Single cluster PHD SLAM

T2 - OCEANS 2013

AU - Nagappa, Sharad

AU - Palomeras, Narcis

AU - Lee, Chee Sing

AU - Gracias, Nuno

AU - Clark, Daniel E

AU - Salvi, Joaquim

PY - 2013

Y1 - 2013

N2 - This paper considers the application of feature-based simultaneous localisation and mapping (SLAM) using a random finite sets (RFS) framework for an autonomous underwater vehicle. SLAM allows for reduction in localisation error by tracking features which provide a fixed external reference. The SLAM problem is addressed here using a single-cluster probability hypothesis density (PHD) filter. The filter uses a particle approximation for the vehicle position with a conditional Gaussian mixture PHD for the feature map. Map features are selected as unique point features generated from a stereo camera on-board the vehicle. We demonstrate the improvement in localisation applying the algorithm to a dataset obtained in an indoor test tank.

AB - This paper considers the application of feature-based simultaneous localisation and mapping (SLAM) using a random finite sets (RFS) framework for an autonomous underwater vehicle. SLAM allows for reduction in localisation error by tracking features which provide a fixed external reference. The SLAM problem is addressed here using a single-cluster probability hypothesis density (PHD) filter. The filter uses a particle approximation for the vehicle position with a conditional Gaussian mixture PHD for the feature map. Map features are selected as unique point features generated from a stereo camera on-board the vehicle. We demonstrate the improvement in localisation applying the algorithm to a dataset obtained in an indoor test tank.

UR - http://www.scopus.com/inward/record.url?scp=84886575189&partnerID=8YFLogxK

U2 - 10.1109/OCEANS-Bergen.2013.6608107

DO - 10.1109/OCEANS-Bergen.2013.6608107

M3 - Conference contribution

AN - SCOPUS:84886575189

SN - 9781479900022

BT - MTS/IEEE OCEANS - Bergen

PB - IEEE

Y2 - 10 June 2013 through 13 June 2013

ER -

Single cluster PHD SLAM: Application to autonomous underwater vehicles using stereo vision

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this