Probabilistic estimation of unmarked roads using radar

Juan I. Nieto, Andres Hernandez-Gutierrez, Eduardo Nebot

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper presents a probabilistic framework for unmarked roads estimation using radar sensors. The algorithm models the sensor likelihood function as a Gaussian mixture model. This sensor likelihood is used in a Bayesian approach to estimate the road edges probability distribution. A particle filter is used as the fusion mechanism to obtain posterior estimates of the road's parameters. The main applications of the approach presented are autonomous navigation and driver assistance. The use of radar permits the system to work even under difficult environmental conditions. Experimental results with data acquired in a mine environment are presented. By using a GPS mounted on the test vehicle, the algorithm outcome is registered with a satellite image of the experimental place. The registration allows to perform a qualitative analysis of the algorithm results. The results show the effectiveness of the algorithm presented.

Original languageEnglish
Pages (from-to)35-41
Number of pages7
JournalJournal of Physical Agents
Volume4
Issue number2
DOIs
Publication statusPublished - 1 Jan 2010

Fingerprint

Radar
Sensors
Probability distributions
Global positioning system
Navigation
Fusion reactions
Satellites

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering

Cite this

Nieto, Juan I. ; Hernandez-Gutierrez, Andres ; Nebot, Eduardo. / Probabilistic estimation of unmarked roads using radar. In: Journal of Physical Agents. 2010 ; Vol. 4, No. 2. pp. 35-41.
@article{4730363240c44513bacd1497daf5f6f8,
title = "Probabilistic estimation of unmarked roads using radar",
abstract = "This paper presents a probabilistic framework for unmarked roads estimation using radar sensors. The algorithm models the sensor likelihood function as a Gaussian mixture model. This sensor likelihood is used in a Bayesian approach to estimate the road edges probability distribution. A particle filter is used as the fusion mechanism to obtain posterior estimates of the road's parameters. The main applications of the approach presented are autonomous navigation and driver assistance. The use of radar permits the system to work even under difficult environmental conditions. Experimental results with data acquired in a mine environment are presented. By using a GPS mounted on the test vehicle, the algorithm outcome is registered with a satellite image of the experimental place. The registration allows to perform a qualitative analysis of the algorithm results. The results show the effectiveness of the algorithm presented.",
author = "Nieto, {Juan I.} and Andres Hernandez-Gutierrez and Eduardo Nebot",
year = "2010",
month = "1",
day = "1",
doi = "10.14198/JoPha.2010.4.2.05",
language = "English",
volume = "4",
pages = "35--41",
journal = "Journal of Physical Agents",
issn = "1888-0258",
publisher = "University of Alicante",
number = "2",

}

Probabilistic estimation of unmarked roads using radar. / Nieto, Juan I.; Hernandez-Gutierrez, Andres; Nebot, Eduardo.

In: Journal of Physical Agents, Vol. 4, No. 2, 01.01.2010, p. 35-41.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Probabilistic estimation of unmarked roads using radar

AU - Nieto, Juan I.

AU - Hernandez-Gutierrez, Andres

AU - Nebot, Eduardo

PY - 2010/1/1

Y1 - 2010/1/1

N2 - This paper presents a probabilistic framework for unmarked roads estimation using radar sensors. The algorithm models the sensor likelihood function as a Gaussian mixture model. This sensor likelihood is used in a Bayesian approach to estimate the road edges probability distribution. A particle filter is used as the fusion mechanism to obtain posterior estimates of the road's parameters. The main applications of the approach presented are autonomous navigation and driver assistance. The use of radar permits the system to work even under difficult environmental conditions. Experimental results with data acquired in a mine environment are presented. By using a GPS mounted on the test vehicle, the algorithm outcome is registered with a satellite image of the experimental place. The registration allows to perform a qualitative analysis of the algorithm results. The results show the effectiveness of the algorithm presented.

AB - This paper presents a probabilistic framework for unmarked roads estimation using radar sensors. The algorithm models the sensor likelihood function as a Gaussian mixture model. This sensor likelihood is used in a Bayesian approach to estimate the road edges probability distribution. A particle filter is used as the fusion mechanism to obtain posterior estimates of the road's parameters. The main applications of the approach presented are autonomous navigation and driver assistance. The use of radar permits the system to work even under difficult environmental conditions. Experimental results with data acquired in a mine environment are presented. By using a GPS mounted on the test vehicle, the algorithm outcome is registered with a satellite image of the experimental place. The registration allows to perform a qualitative analysis of the algorithm results. The results show the effectiveness of the algorithm presented.

UR - http://www.scopus.com/inward/record.url?scp=77956215130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956215130&partnerID=8YFLogxK

U2 - 10.14198/JoPha.2010.4.2.05

DO - 10.14198/JoPha.2010.4.2.05

M3 - Article

VL - 4

SP - 35

EP - 41

JO - Journal of Physical Agents

JF - Journal of Physical Agents

SN - 1888-0258

IS - 2

ER -