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 proceedingConference 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 languageEnglish
Title of host publication2017 17th Workshop on Information Processing and Control, RPIC 2017
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-6
Number of pages6
ISBN (Electronic)9789875447547
DOIs
Publication statusPublished - 20 Sept 2017
Event17th Workshop on Information Processing and Control, RPIC 2017 - Mar del Plata, Argentina
Duration: 20 Oct 201722 Oct 2017

Publication series

Name2017 17th Workshop on Information Processing and Control, RPIC 2017
Volume2017-January

Conference

Conference17th Workshop on Information Processing and Control, RPIC 2017
Country/TerritoryArgentina
CityMar del Plata
Period20/10/1722/10/17

Bibliographical note

Publisher Copyright:
© 2017 Comisión Permanente RPIC.

Keywords

  • control systems
  • estimators
  • Mapping
  • robotics

Fingerprint

Dive into the research topics of 'Probabilistic mapping in agricultural environments using kernel estimators with recursive subsampling'. Together they form a unique fingerprint.

Cite this