Fully Bayesian Field Slam Using Gaussian Markov Random Fields

Huan N. Do, Mahdi Jadaliha, Mehmet Temel, Jongeun Choi

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper presents a fully Bayesian way to solve the simultaneous localization and spatial prediction problem using a Gaussian Markov random field (GMRF) model. The objective is to simultaneously localize robotic sensors and predict a spatial field of interest using sequentially collected noisy observations by robotic sensors. The set of observations consists of the observed noisy positions of robotic sensing vehicles and noisy measurements of a spatial field. To be flexible, the spatial field of interest is modeled by a GMRF with uncertain hyperparameters. We derive an approximate Bayesian solution to the problem of computing the predictive inferences of the GMRF and the localization, taking into account observations, uncertain hyperparameters, measurement noise, kinematics of robotic sensors, and uncertain localization. The effectiveness of the proposed algorithm is illustrated by simulation results as well as by experiment results. The experiment results successfully show the flexibility and adaptability of our fully Bayesian approach in a data-driven fashion.

Original languageEnglish
Pages (from-to)1175-1188
Number of pages14
JournalAsian Journal of Control
Volume18
Issue number4
DOIs
Publication statusPublished - 2016 Jul 1

Fingerprint

Robotics
Sensors
Kinematics
Experiments

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

Do, Huan N. ; Jadaliha, Mahdi ; Temel, Mehmet ; Choi, Jongeun. / Fully Bayesian Field Slam Using Gaussian Markov Random Fields. In: Asian Journal of Control. 2016 ; Vol. 18, No. 4. pp. 1175-1188.
@article{ce927efafc2743efae7db44480b0c386,
title = "Fully Bayesian Field Slam Using Gaussian Markov Random Fields",
abstract = "This paper presents a fully Bayesian way to solve the simultaneous localization and spatial prediction problem using a Gaussian Markov random field (GMRF) model. The objective is to simultaneously localize robotic sensors and predict a spatial field of interest using sequentially collected noisy observations by robotic sensors. The set of observations consists of the observed noisy positions of robotic sensing vehicles and noisy measurements of a spatial field. To be flexible, the spatial field of interest is modeled by a GMRF with uncertain hyperparameters. We derive an approximate Bayesian solution to the problem of computing the predictive inferences of the GMRF and the localization, taking into account observations, uncertain hyperparameters, measurement noise, kinematics of robotic sensors, and uncertain localization. The effectiveness of the proposed algorithm is illustrated by simulation results as well as by experiment results. The experiment results successfully show the flexibility and adaptability of our fully Bayesian approach in a data-driven fashion.",
author = "Do, {Huan N.} and Mahdi Jadaliha and Mehmet Temel and Jongeun Choi",
year = "2016",
month = "7",
day = "1",
doi = "10.1002/asjc.1237",
language = "English",
volume = "18",
pages = "1175--1188",
journal = "Asian Journal of Control",
issn = "1561-8625",
publisher = "National Taiwan University (IEEB)",
number = "4",

}

Fully Bayesian Field Slam Using Gaussian Markov Random Fields. / Do, Huan N.; Jadaliha, Mahdi; Temel, Mehmet; Choi, Jongeun.

In: Asian Journal of Control, Vol. 18, No. 4, 01.07.2016, p. 1175-1188.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fully Bayesian Field Slam Using Gaussian Markov Random Fields

AU - Do, Huan N.

AU - Jadaliha, Mahdi

AU - Temel, Mehmet

AU - Choi, Jongeun

PY - 2016/7/1

Y1 - 2016/7/1

N2 - This paper presents a fully Bayesian way to solve the simultaneous localization and spatial prediction problem using a Gaussian Markov random field (GMRF) model. The objective is to simultaneously localize robotic sensors and predict a spatial field of interest using sequentially collected noisy observations by robotic sensors. The set of observations consists of the observed noisy positions of robotic sensing vehicles and noisy measurements of a spatial field. To be flexible, the spatial field of interest is modeled by a GMRF with uncertain hyperparameters. We derive an approximate Bayesian solution to the problem of computing the predictive inferences of the GMRF and the localization, taking into account observations, uncertain hyperparameters, measurement noise, kinematics of robotic sensors, and uncertain localization. The effectiveness of the proposed algorithm is illustrated by simulation results as well as by experiment results. The experiment results successfully show the flexibility and adaptability of our fully Bayesian approach in a data-driven fashion.

AB - This paper presents a fully Bayesian way to solve the simultaneous localization and spatial prediction problem using a Gaussian Markov random field (GMRF) model. The objective is to simultaneously localize robotic sensors and predict a spatial field of interest using sequentially collected noisy observations by robotic sensors. The set of observations consists of the observed noisy positions of robotic sensing vehicles and noisy measurements of a spatial field. To be flexible, the spatial field of interest is modeled by a GMRF with uncertain hyperparameters. We derive an approximate Bayesian solution to the problem of computing the predictive inferences of the GMRF and the localization, taking into account observations, uncertain hyperparameters, measurement noise, kinematics of robotic sensors, and uncertain localization. The effectiveness of the proposed algorithm is illustrated by simulation results as well as by experiment results. The experiment results successfully show the flexibility and adaptability of our fully Bayesian approach in a data-driven fashion.

UR - http://www.scopus.com/inward/record.url?scp=84949032604&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949032604&partnerID=8YFLogxK

U2 - 10.1002/asjc.1237

DO - 10.1002/asjc.1237

M3 - Article

VL - 18

SP - 1175

EP - 1188

JO - Asian Journal of Control

JF - Asian Journal of Control

SN - 1561-8625

IS - 4

ER -