Incremental probabilistic geometry estimation for robot scene understanding

Louis Kenzo Cahier, Tetsuya Ogata, Hiroshi G. Okuno

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

2 Citations (Scopus)

Abstract

Our goal is to give mobile robots a rich representation of their environment as fast as possible. Current mapping methods such as SLAM are often sparse, and scene reconstruction methods using tilting laser scanners are relatively slow. In this paper, we outline a new method for iterative construction of a geometric mesh using streaming time-of-flight range data. Our results show that our algorithm can produce a stable representation after 6 frames, with higher accuracy than raw time-of-flight data.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages3625-3630
Number of pages6
DOIs
Publication statusPublished - 2012
Externally publishedYes

Fingerprint

Mobile robots
Robots
Geometry
Lasers

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Cahier, L. K., Ogata, T., & Okuno, H. G. (2012). Incremental probabilistic geometry estimation for robot scene understanding. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 3625-3630). [6225343] https://doi.org/10.1109/ICRA.2012.6225343

Incremental probabilistic geometry estimation for robot scene understanding. / Cahier, Louis Kenzo; Ogata, Tetsuya; Okuno, Hiroshi G.

Proceedings - IEEE International Conference on Robotics and Automation. 2012. p. 3625-3630 6225343.

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

Cahier, LK, Ogata, T & Okuno, HG 2012, Incremental probabilistic geometry estimation for robot scene understanding. in Proceedings - IEEE International Conference on Robotics and Automation., 6225343, pp. 3625-3630. https://doi.org/10.1109/ICRA.2012.6225343
Cahier LK, Ogata T, Okuno HG. Incremental probabilistic geometry estimation for robot scene understanding. In Proceedings - IEEE International Conference on Robotics and Automation. 2012. p. 3625-3630. 6225343 https://doi.org/10.1109/ICRA.2012.6225343
Cahier, Louis Kenzo ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Incremental probabilistic geometry estimation for robot scene understanding. Proceedings - IEEE International Conference on Robotics and Automation. 2012. pp. 3625-3630
@inproceedings{01fb725c928a4baeb73033d53ac14fc7,
title = "Incremental probabilistic geometry estimation for robot scene understanding",
abstract = "Our goal is to give mobile robots a rich representation of their environment as fast as possible. Current mapping methods such as SLAM are often sparse, and scene reconstruction methods using tilting laser scanners are relatively slow. In this paper, we outline a new method for iterative construction of a geometric mesh using streaming time-of-flight range data. Our results show that our algorithm can produce a stable representation after 6 frames, with higher accuracy than raw time-of-flight data.",
author = "Cahier, {Louis Kenzo} and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2012",
doi = "10.1109/ICRA.2012.6225343",
language = "English",
isbn = "9781467314039",
pages = "3625--3630",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - Incremental probabilistic geometry estimation for robot scene understanding

AU - Cahier, Louis Kenzo

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2012

Y1 - 2012

N2 - Our goal is to give mobile robots a rich representation of their environment as fast as possible. Current mapping methods such as SLAM are often sparse, and scene reconstruction methods using tilting laser scanners are relatively slow. In this paper, we outline a new method for iterative construction of a geometric mesh using streaming time-of-flight range data. Our results show that our algorithm can produce a stable representation after 6 frames, with higher accuracy than raw time-of-flight data.

AB - Our goal is to give mobile robots a rich representation of their environment as fast as possible. Current mapping methods such as SLAM are often sparse, and scene reconstruction methods using tilting laser scanners are relatively slow. In this paper, we outline a new method for iterative construction of a geometric mesh using streaming time-of-flight range data. Our results show that our algorithm can produce a stable representation after 6 frames, with higher accuracy than raw time-of-flight data.

UR - http://www.scopus.com/inward/record.url?scp=84864449345&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864449345&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2012.6225343

DO - 10.1109/ICRA.2012.6225343

M3 - Conference contribution

SN - 9781467314039

SP - 3625

EP - 3630

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -