TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Object detection in robotic applications for real-time localization using semi-unknown objects

Tutkimustuotosvertaisarvioitu

Standard

Object detection in robotic applications for real-time localization using semi-unknown objects. / Astola, Pekka; Aref, Mohammad M.; Vihonen, Juho; Mattila, Jouni; Tabus, Ioan.

International Conference on Telecommunications and Signal Processing (TSP). IEEE, 2017. s. 682-687.

Tutkimustuotosvertaisarvioitu

Harvard

Astola, P, Aref, MM, Vihonen, J, Mattila, J & Tabus, I 2017, Object detection in robotic applications for real-time localization using semi-unknown objects. julkaisussa International Conference on Telecommunications and Signal Processing (TSP). IEEE, Sivut 682-687, 1/01/00. https://doi.org/10.1109/TSP.2017.8076074

APA

Astola, P., Aref, M. M., Vihonen, J., Mattila, J., & Tabus, I. (2017). Object detection in robotic applications for real-time localization using semi-unknown objects. teoksessa International Conference on Telecommunications and Signal Processing (TSP) (Sivut 682-687). IEEE. https://doi.org/10.1109/TSP.2017.8076074

Vancouver

Astola P, Aref MM, Vihonen J, Mattila J, Tabus I. Object detection in robotic applications for real-time localization using semi-unknown objects. julkaisussa International Conference on Telecommunications and Signal Processing (TSP). IEEE. 2017. s. 682-687 https://doi.org/10.1109/TSP.2017.8076074

Author

Astola, Pekka ; Aref, Mohammad M. ; Vihonen, Juho ; Mattila, Jouni ; Tabus, Ioan. / Object detection in robotic applications for real-time localization using semi-unknown objects. International Conference on Telecommunications and Signal Processing (TSP). IEEE, 2017. Sivut 682-687

Bibtex - Lataa

@inproceedings{9940c8dbd40442e99bc76252d9858a81,
title = "Object detection in robotic applications for real-time localization using semi-unknown objects",
abstract = "We investigate the pose estimation of a semi-unknown object for stereo-vision-based navigation of a mobile manipulator. A new computationally fast vision algorithm is developed to extract the object's pose at a high rate from the captured scenes. Moreover, we present a method to deal with range dependent noise characteristics of the stereo vision to fulfill requirements for mobile manipulation tasks. As shown, a smoothed, high-bandwidth feedback is obtained by using robust real-time estimation, where special care is taken to accommodate the aforementioned nonlinearities of the stereo vision. This way, the manipulator is capable of positioning itself in the close vicinity of an object by navigation of its nonholonomic mobile base. Importantly, we achieve nearly the same accuracy in mobile robot positioning compared to standard marker-based techniques at distances greater than those typically considered suitable for position-based, high-bandwidth motion control within the robotics community.",
keywords = "control nonlinearities, feature extraction, manipulators, mobile robots, motion control, object detection, path planning, pose estimation, position control, robot vision, robust control, stereo image processing, high-bandwidth feedback, high-bandwidth motion control, mobile manipulation tasks, mobile manipulator, mobile robot positioning, nonholonomic mobile base, nonlinearities, object pose extraction, range dependent noise characteristics, real-time localization, robotic applications, robust real-time estimation, semiunknown object, stereo-vision-based navigation, Cameras, Mobile communication, Object detection, Pose estimation, Real-time systems, Service robots, autonomous robot, computer vision, real time, stereo vision",
author = "Pekka Astola and Aref, {Mohammad M.} and Juho Vihonen and Jouni Mattila and Ioan Tabus",
year = "2017",
month = "7",
day = "1",
doi = "10.1109/TSP.2017.8076074",
language = "English",
isbn = "978-1-5090-3982-1",
pages = "682--687",
booktitle = "International Conference on Telecommunications and Signal Processing (TSP)",
publisher = "IEEE",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Object detection in robotic applications for real-time localization using semi-unknown objects

AU - Astola, Pekka

AU - Aref, Mohammad M.

AU - Vihonen, Juho

AU - Mattila, Jouni

AU - Tabus, Ioan

PY - 2017/7/1

Y1 - 2017/7/1

N2 - We investigate the pose estimation of a semi-unknown object for stereo-vision-based navigation of a mobile manipulator. A new computationally fast vision algorithm is developed to extract the object's pose at a high rate from the captured scenes. Moreover, we present a method to deal with range dependent noise characteristics of the stereo vision to fulfill requirements for mobile manipulation tasks. As shown, a smoothed, high-bandwidth feedback is obtained by using robust real-time estimation, where special care is taken to accommodate the aforementioned nonlinearities of the stereo vision. This way, the manipulator is capable of positioning itself in the close vicinity of an object by navigation of its nonholonomic mobile base. Importantly, we achieve nearly the same accuracy in mobile robot positioning compared to standard marker-based techniques at distances greater than those typically considered suitable for position-based, high-bandwidth motion control within the robotics community.

AB - We investigate the pose estimation of a semi-unknown object for stereo-vision-based navigation of a mobile manipulator. A new computationally fast vision algorithm is developed to extract the object's pose at a high rate from the captured scenes. Moreover, we present a method to deal with range dependent noise characteristics of the stereo vision to fulfill requirements for mobile manipulation tasks. As shown, a smoothed, high-bandwidth feedback is obtained by using robust real-time estimation, where special care is taken to accommodate the aforementioned nonlinearities of the stereo vision. This way, the manipulator is capable of positioning itself in the close vicinity of an object by navigation of its nonholonomic mobile base. Importantly, we achieve nearly the same accuracy in mobile robot positioning compared to standard marker-based techniques at distances greater than those typically considered suitable for position-based, high-bandwidth motion control within the robotics community.

KW - control nonlinearities

KW - feature extraction

KW - manipulators

KW - mobile robots

KW - motion control

KW - object detection

KW - path planning

KW - pose estimation

KW - position control

KW - robot vision

KW - robust control

KW - stereo image processing

KW - high-bandwidth feedback

KW - high-bandwidth motion control

KW - mobile manipulation tasks

KW - mobile manipulator

KW - mobile robot positioning

KW - nonholonomic mobile base

KW - nonlinearities

KW - object pose extraction

KW - range dependent noise characteristics

KW - real-time localization

KW - robotic applications

KW - robust real-time estimation

KW - semiunknown object

KW - stereo-vision-based navigation

KW - Cameras

KW - Mobile communication

KW - Object detection

KW - Pose estimation

KW - Real-time systems

KW - Service robots

KW - autonomous robot

KW - computer vision

KW - real time

KW - stereo vision

U2 - 10.1109/TSP.2017.8076074

DO - 10.1109/TSP.2017.8076074

M3 - Conference contribution

SN - 978-1-5090-3982-1

SP - 682

EP - 687

BT - International Conference on Telecommunications and Signal Processing (TSP)

PB - IEEE

ER -