Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling

Javier Gimenez; Santiago Tosetti; Lucio Salinas; Ricardo Carelli

doi:10.23919/RPIC.2017.8214350

Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling

Javier Gimenez^*, Santiago Tosetti, Lucio Salinas, Ricardo Carelli

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

This work presents a non parametric probabilistic mapping based on kernel estimators which does not use grids. The proposed methodology characterizes the map with a cloud of points obtained from several observations of the environment. In order to maintain a bounded number of observations in memory, a recursive subsampling algorithm is proposed. The procedure is included in an SLAM, in order to localize the robot as well. An application example is the presented, where the proposed methodology is applied in an agricultural environment. Simulation and experimentation results are presented to validate the proposal.

Original language	English
Title of host publication	2017 17th Workshop on Information Processing and Control, RPIC 2017
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1-6
Number of pages	6
ISBN (Electronic)	9789875447547
DOIs	https://doi.org/10.23919/RPIC.2017.8214350
Publication status	Published - 20 Sept 2017
Event	17th Workshop on Information Processing and Control, RPIC 2017 - Mar del Plata, Argentina Duration: 20 Oct 2017 → 22 Oct 2017

Publication series

Name	2017 17th Workshop on Information Processing and Control, RPIC 2017
Volume	2017-January

Conference

Conference	17th Workshop on Information Processing and Control, RPIC 2017
Country/Territory	Argentina
City	Mar del Plata
Period	20/10/17 → 22/10/17

Bibliographical note

Publisher Copyright:
© 2017 Comisión Permanente RPIC.

Keywords

control systems
estimators
Mapping
robotics

Access to Document

10.23919/RPIC.2017.8214350

Handle.net

Persistent link

Cite this

Gimenez, J., Tosetti, S., Salinas, L., & Carelli, R. (2017). Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling. In 2017 17th Workshop on Information Processing and Control, RPIC 2017 (pp. 1-6). (2017 17th Workshop on Information Processing and Control, RPIC 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.23919/RPIC.2017.8214350

Gimenez, Javier ; Tosetti, Santiago ; Salinas, Lucio et al. / Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling. 2017 17th Workshop on Information Processing and Control, RPIC 2017. Institute of Electrical and Electronics Engineers (IEEE), 2017. pp. 1-6 (2017 17th Workshop on Information Processing and Control, RPIC 2017).

@inproceedings{0c0e8d890987489d84cad9f92ccdcf63,

title = "Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling",

abstract = "This work presents a non parametric probabilistic mapping based on kernel estimators which does not use grids. The proposed methodology characterizes the map with a cloud of points obtained from several observations of the environment. In order to maintain a bounded number of observations in memory, a recursive subsampling algorithm is proposed. The procedure is included in an SLAM, in order to localize the robot as well. An application example is the presented, where the proposed methodology is applied in an agricultural environment. Simulation and experimentation results are presented to validate the proposal.",

keywords = "control systems, estimators, Mapping, robotics",

author = "Javier Gimenez and Santiago Tosetti and Lucio Salinas and Ricardo Carelli",

note = "Publisher Copyright: {\textcopyright} 2017 Comisi{\'o}n Permanente RPIC.; 17th Workshop on Information Processing and Control, RPIC 2017 ; Conference date: 20-10-2017 Through 22-10-2017",

year = "2017",

month = sep,

day = "20",

doi = "10.23919/RPIC.2017.8214350",

language = "English",

series = "2017 17th Workshop on Information Processing and Control, RPIC 2017",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1--6",

booktitle = "2017 17th Workshop on Information Processing and Control, RPIC 2017",

address = "United States",

}

Gimenez, J, Tosetti, S, Salinas, L & Carelli, R 2017, Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling. in 2017 17th Workshop on Information Processing and Control, RPIC 2017. 2017 17th Workshop on Information Processing and Control, RPIC 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers (IEEE), pp. 1-6, 17th Workshop on Information Processing and Control, RPIC 2017, Mar del Plata, Argentina, 20/10/17. https://doi.org/10.23919/RPIC.2017.8214350

Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling. / Gimenez, Javier; Tosetti, Santiago; Salinas, Lucio et al.
2017 17th Workshop on Information Processing and Control, RPIC 2017. Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 1-6 (2017 17th Workshop on Information Processing and Control, RPIC 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling

AU - Gimenez, Javier

AU - Tosetti, Santiago

AU - Salinas, Lucio

AU - Carelli, Ricardo

PY - 2017/9/20

Y1 - 2017/9/20

N2 - This work presents a non parametric probabilistic mapping based on kernel estimators which does not use grids. The proposed methodology characterizes the map with a cloud of points obtained from several observations of the environment. In order to maintain a bounded number of observations in memory, a recursive subsampling algorithm is proposed. The procedure is included in an SLAM, in order to localize the robot as well. An application example is the presented, where the proposed methodology is applied in an agricultural environment. Simulation and experimentation results are presented to validate the proposal.

AB - This work presents a non parametric probabilistic mapping based on kernel estimators which does not use grids. The proposed methodology characterizes the map with a cloud of points obtained from several observations of the environment. In order to maintain a bounded number of observations in memory, a recursive subsampling algorithm is proposed. The procedure is included in an SLAM, in order to localize the robot as well. An application example is the presented, where the proposed methodology is applied in an agricultural environment. Simulation and experimentation results are presented to validate the proposal.

KW - control systems

KW - estimators

KW - Mapping

KW - robotics

UR - https://www.scopus.com/pages/publications/85046486432

U2 - 10.23919/RPIC.2017.8214350

DO - 10.23919/RPIC.2017.8214350

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:85046486432

T3 - 2017 17th Workshop on Information Processing and Control, RPIC 2017

SP - 1

EP - 6

BT - 2017 17th Workshop on Information Processing and Control, RPIC 2017

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 17th Workshop on Information Processing and Control, RPIC 2017

Y2 - 20 October 2017 through 22 October 2017

ER -

Gimenez J, Tosetti S, Salinas L, Carelli R. Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling. In 2017 17th Workshop on Information Processing and Control, RPIC 2017. Institute of Electrical and Electronics Engineers (IEEE). 2017. p. 1-6. (2017 17th Workshop on Information Processing and Control, RPIC 2017). doi: 10.23919/RPIC.2017.8214350

Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this