Publication detail

Methods for Simultaneous self Localization and Mapping for Depth Cameras

LIGOCKI, A.

Original Title

Methods for Simultaneous self Localization and Mapping for Depth Cameras

English Title

Methods for Simultaneous self Localization and Mapping for Depth Cameras

Type

conference paper

Language

en

Original Abstract

This work deals with the extension of the existing implementation of RGBD Visual SLAM with additional data source from wheel odometry of robot’s chassis, on which RGBD sensor is lo- cated. Each of these two position estimation methods has a different character measurement uncer- tainty. By combining these methods together we could be able to suppress the disadvantages of both approaches, and in the result we would be able to create more accurate model of the robot’s environ- ment, which was unknown at the beginning of the measurement. Also accuracy of position estimation in created model can be improved.

English abstract

This work deals with the extension of the existing implementation of RGBD Visual SLAM with additional data source from wheel odometry of robot’s chassis, on which RGBD sensor is lo- cated. Each of these two position estimation methods has a different character measurement uncer- tainty. By combining these methods together we could be able to suppress the disadvantages of both approaches, and in the result we would be able to create more accurate model of the robot’s environ- ment, which was unknown at the beginning of the measurement. Also accuracy of position estimation in created model can be improved.

Keywords

SLAM, Visual SLAM, Odometry, Kinect, 3D Mode, Position Estimation

Released

24.04.2017

Location

Brno

ISBN

978-80-214-5496-5

Book

Sborník EEICT 2017

Pages from

193

Pages to

195

Pages count

3

URL

Documents

BibTex


@inproceedings{BUT141431,
  author="Adam {Ligocki}",
  title="Methods for Simultaneous self Localization and Mapping for Depth Cameras",
  annote="This work deals with the extension of the existing implementation of RGBD Visual SLAM
with additional data source from wheel odometry of robot’s chassis, on which RGBD sensor is lo-
cated. Each of these two position estimation methods has a different character measurement uncer-
tainty. By combining these methods together we could be able to suppress the disadvantages of both
approaches, and in the result we would be able to create more accurate model of the robot’s environ-
ment, which was unknown at the beginning of the measurement. Also accuracy of position estimation
in created model can be improved.",
  booktitle="Sborník EEICT 2017",
  chapter="141431",
  howpublished="online",
  year="2017",
  month="april",
  pages="193--195",
  type="conference paper"
}