Visual odometry for an omnidirectional-drive robot

Alberto Pretto, Emanuele Menegatti, Masaki Takahashi, Takafumi Suzuki, Enrico Pagello

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

1 Citation (Scopus)

Abstract

In this paper, we present a framework for 3D visual odometry applied to a hospital-use transfer robot equipped with an omni-drive system. The approach is based on features extracted out of and matched in monocular image sequences. We propose a new feature detection and tracking scheme robust to motion blur and well suitable in environment, as a hospital, where the local features are sparse and not much distinctive. Moreover, this approach match very well the omnidirectional drive robot for two reasons: the poorly reliable odometry of this drive system and the brisk jerks these robots experience when they cross an uneven floor. Experiments performed on a relatively long path in an indoor environment with repetitive patterns and sparse local features show the effectiveness of the proposed technique in reliably extracting and matching features and in the generation of a correct visual odometry. Results are obtained without the aid of any external sensors other than the robot's low-cost camera. We also presents a performance evaluation of the proposed features detection-descriptor scheme.

Original languageEnglish
Title of host publication2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009
DOIs
Publication statusPublished - 2009
Event2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009 - Sharjah, United Arab Emirates
Duration: 2009 Mar 232009 Mar 26

Other

Other2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009
CountryUnited Arab Emirates
CitySharjah
Period09/3/2309/3/26

Fingerprint

Robots
Cameras
Sensors
Costs
Experiments

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Pretto, A., Menegatti, E., Takahashi, M., Suzuki, T., & Pagello, E. (2009). Visual odometry for an omnidirectional-drive robot. In 2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009 [5164787] https://doi.org/10.1109/ISMA.2009.5164787

Visual odometry for an omnidirectional-drive robot. / Pretto, Alberto; Menegatti, Emanuele; Takahashi, Masaki; Suzuki, Takafumi; Pagello, Enrico.

2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009. 2009. 5164787.

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

Pretto, A, Menegatti, E, Takahashi, M, Suzuki, T & Pagello, E 2009, Visual odometry for an omnidirectional-drive robot. in 2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009., 5164787, 2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009, Sharjah, United Arab Emirates, 09/3/23. https://doi.org/10.1109/ISMA.2009.5164787
Pretto A, Menegatti E, Takahashi M, Suzuki T, Pagello E. Visual odometry for an omnidirectional-drive robot. In 2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009. 2009. 5164787 https://doi.org/10.1109/ISMA.2009.5164787
Pretto, Alberto ; Menegatti, Emanuele ; Takahashi, Masaki ; Suzuki, Takafumi ; Pagello, Enrico. / Visual odometry for an omnidirectional-drive robot. 2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009. 2009.
@inproceedings{60f635d7ab0d4a918dfe86ce85da7f4d,
title = "Visual odometry for an omnidirectional-drive robot",
abstract = "In this paper, we present a framework for 3D visual odometry applied to a hospital-use transfer robot equipped with an omni-drive system. The approach is based on features extracted out of and matched in monocular image sequences. We propose a new feature detection and tracking scheme robust to motion blur and well suitable in environment, as a hospital, where the local features are sparse and not much distinctive. Moreover, this approach match very well the omnidirectional drive robot for two reasons: the poorly reliable odometry of this drive system and the brisk jerks these robots experience when they cross an uneven floor. Experiments performed on a relatively long path in an indoor environment with repetitive patterns and sparse local features show the effectiveness of the proposed technique in reliably extracting and matching features and in the generation of a correct visual odometry. Results are obtained without the aid of any external sensors other than the robot's low-cost camera. We also presents a performance evaluation of the proposed features detection-descriptor scheme.",
author = "Alberto Pretto and Emanuele Menegatti and Masaki Takahashi and Takafumi Suzuki and Enrico Pagello",
year = "2009",
doi = "10.1109/ISMA.2009.5164787",
language = "English",
isbn = "9781424434817",
booktitle = "2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009",

}

TY - GEN

T1 - Visual odometry for an omnidirectional-drive robot

AU - Pretto, Alberto

AU - Menegatti, Emanuele

AU - Takahashi, Masaki

AU - Suzuki, Takafumi

AU - Pagello, Enrico

PY - 2009

Y1 - 2009

N2 - In this paper, we present a framework for 3D visual odometry applied to a hospital-use transfer robot equipped with an omni-drive system. The approach is based on features extracted out of and matched in monocular image sequences. We propose a new feature detection and tracking scheme robust to motion blur and well suitable in environment, as a hospital, where the local features are sparse and not much distinctive. Moreover, this approach match very well the omnidirectional drive robot for two reasons: the poorly reliable odometry of this drive system and the brisk jerks these robots experience when they cross an uneven floor. Experiments performed on a relatively long path in an indoor environment with repetitive patterns and sparse local features show the effectiveness of the proposed technique in reliably extracting and matching features and in the generation of a correct visual odometry. Results are obtained without the aid of any external sensors other than the robot's low-cost camera. We also presents a performance evaluation of the proposed features detection-descriptor scheme.

AB - In this paper, we present a framework for 3D visual odometry applied to a hospital-use transfer robot equipped with an omni-drive system. The approach is based on features extracted out of and matched in monocular image sequences. We propose a new feature detection and tracking scheme robust to motion blur and well suitable in environment, as a hospital, where the local features are sparse and not much distinctive. Moreover, this approach match very well the omnidirectional drive robot for two reasons: the poorly reliable odometry of this drive system and the brisk jerks these robots experience when they cross an uneven floor. Experiments performed on a relatively long path in an indoor environment with repetitive patterns and sparse local features show the effectiveness of the proposed technique in reliably extracting and matching features and in the generation of a correct visual odometry. Results are obtained without the aid of any external sensors other than the robot's low-cost camera. We also presents a performance evaluation of the proposed features detection-descriptor scheme.

UR - http://www.scopus.com/inward/record.url?scp=70449686323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449686323&partnerID=8YFLogxK

U2 - 10.1109/ISMA.2009.5164787

DO - 10.1109/ISMA.2009.5164787

M3 - Conference contribution

SN - 9781424434817

BT - 2009 6th International Symposium on Mechatronics and its Applications, ISMA 2009

ER -