Fully Bayesian simultaneous localization and spatial prediction using Gaussian Markov random fields (GMRFs)

Mahdi Jadaliha, Jongeun Choi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper investigates a fully Bayesian way to solve the simultaneous localization and spatial prediction (SLAP) 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 obtained noisy observations collected by robotic sensors. The set of observations consists of the observed uncertain poses 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.

Original languageEnglish
Title of host publication2013 American Control Conference, ACC 2013
Pages4592-4597
Number of pages6
Publication statusPublished - 2013 Sep 11
Event2013 1st American Control Conference, ACC 2013 - Washington, DC, United States
Duration: 2013 Jun 172013 Jun 19

Other

Other2013 1st American Control Conference, ACC 2013
CountryUnited States
CityWashington, DC
Period13/6/1713/6/19

Fingerprint

Robotics
Sensors
Kinematics

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Jadaliha, M., & Choi, J. (2013). Fully Bayesian simultaneous localization and spatial prediction using Gaussian Markov random fields (GMRFs). In 2013 American Control Conference, ACC 2013 (pp. 4592-4597). [6580547]
Jadaliha, Mahdi ; Choi, Jongeun. / Fully Bayesian simultaneous localization and spatial prediction using Gaussian Markov random fields (GMRFs). 2013 American Control Conference, ACC 2013. 2013. pp. 4592-4597
@inproceedings{2860712fe0444994bb9d68f236817c57,
title = "Fully Bayesian simultaneous localization and spatial prediction using Gaussian Markov random fields (GMRFs)",
abstract = "This paper investigates a fully Bayesian way to solve the simultaneous localization and spatial prediction (SLAP) 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 obtained noisy observations collected by robotic sensors. The set of observations consists of the observed uncertain poses 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.",
author = "Mahdi Jadaliha and Jongeun Choi",
year = "2013",
month = "9",
day = "11",
language = "English",
isbn = "9781479901777",
pages = "4592--4597",
booktitle = "2013 American Control Conference, ACC 2013",

}

Jadaliha, M & Choi, J 2013, Fully Bayesian simultaneous localization and spatial prediction using Gaussian Markov random fields (GMRFs). in 2013 American Control Conference, ACC 2013., 6580547, pp. 4592-4597, 2013 1st American Control Conference, ACC 2013, Washington, DC, United States, 13/6/17.

Fully Bayesian simultaneous localization and spatial prediction using Gaussian Markov random fields (GMRFs). / Jadaliha, Mahdi; Choi, Jongeun.

2013 American Control Conference, ACC 2013. 2013. p. 4592-4597 6580547.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Fully Bayesian simultaneous localization and spatial prediction using Gaussian Markov random fields (GMRFs)

AU - Jadaliha, Mahdi

AU - Choi, Jongeun

PY - 2013/9/11

Y1 - 2013/9/11

N2 - This paper investigates a fully Bayesian way to solve the simultaneous localization and spatial prediction (SLAP) 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 obtained noisy observations collected by robotic sensors. The set of observations consists of the observed uncertain poses 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.

AB - This paper investigates a fully Bayesian way to solve the simultaneous localization and spatial prediction (SLAP) 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 obtained noisy observations collected by robotic sensors. The set of observations consists of the observed uncertain poses 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.

UR - http://www.scopus.com/inward/record.url?scp=84883539772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883539772&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781479901777

SP - 4592

EP - 4597

BT - 2013 American Control Conference, ACC 2013

ER -

Jadaliha M, Choi J. Fully Bayesian simultaneous localization and spatial prediction using Gaussian Markov random fields (GMRFs). In 2013 American Control Conference, ACC 2013. 2013. p. 4592-4597. 6580547