Continuous visual world modeling for autonomous robot manipulation

Arda Inceoglu; Cagatay Koc; Besim Ongun Kanat; Mustafa Ersen; Sanem Sariel

doi:10.1109/TSMC.2017.2787482

Continuous visual world modeling for autonomous robot manipulation

Arda Inceoglu^*, Cagatay Koc, Besim Ongun Kanat, Mustafa Ersen, Sanem Sariel

^*Corresponding author for this work

Istanbul Technical University

Research output: Contribution to journal › Article › peer-review

13 Citations (Scopus)

Abstract

Service robots need to handle a variety of everyday manipulation tasks to accomplish household chores such as cooking and cleaning. Successful execution of these tasks is highly dependent on how reliable the robot perceives its environment through noisy sensing. We present a visual world modeling system for service robots to generate and maintain accurate models of their environments for continuous scenarios. This system is designed to provide a generic platform for both humanoid and ground manipulation robots using different types of vision sensors and algorithms. In our particular implementation, visual data processed by different perception algorithms are used for building and continuously updating a world model of the environment. We evaluate our system on a variety of object manipulation scenarios and show that the system produces consistent perception outcomes suitable for different manipulation tasks.

Original language	English
Article number	8270600
Pages (from-to)	192-205
Number of pages	14
Journal	IEEE Transactions on Systems, Man, and Cybernetics: Systems
Volume	49
Issue number	1
DOIs	https://doi.org/10.1109/TSMC.2017.2787482
Publication status	Published - Jan 2019

Bibliographical note

Publisher Copyright:
© 2013 IEEE.

Funding

Manuscript received July 7, 2017; revised September 27, 2017; accepted December 7, 2017. Date of publication January 26, 2018; date of current version December 14, 2018. This work was supported by the Scientific and Technological Research Council of Turkey (TUBITAK) under Grant 115E-368. This paper was recommended by Associate Editor A. Hussain. (Corresponding author: Arda Inceoglu.) The authors are with the Artificial Intelligence and Robotics Laboratory, Department of Computer Engineering, Istanbul Technical University, 34469 Istanbul, Turkey (e-mail: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]).

Funders	Funder number
TUBITAK	115E-368
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Keywords

3-D perception
service robots
symbolic scene representation
visual world modeling

Access to Document

10.1109/TSMC.2017.2787482

Cite this

@article{393d16e31efb47558d9a92336844dcef,

title = "Continuous visual world modeling for autonomous robot manipulation",

abstract = "Service robots need to handle a variety of everyday manipulation tasks to accomplish household chores such as cooking and cleaning. Successful execution of these tasks is highly dependent on how reliable the robot perceives its environment through noisy sensing. We present a visual world modeling system for service robots to generate and maintain accurate models of their environments for continuous scenarios. This system is designed to provide a generic platform for both humanoid and ground manipulation robots using different types of vision sensors and algorithms. In our particular implementation, visual data processed by different perception algorithms are used for building and continuously updating a world model of the environment. We evaluate our system on a variety of object manipulation scenarios and show that the system produces consistent perception outcomes suitable for different manipulation tasks.",

keywords = "3-D perception, service robots, symbolic scene representation, visual world modeling",

author = "Arda Inceoglu and Cagatay Koc and Kanat, {Besim Ongun} and Mustafa Ersen and Sanem Sariel",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2019",

month = jan,

doi = "10.1109/TSMC.2017.2787482",

language = "English",

volume = "49",

pages = "192--205",

journal = "IEEE Transactions on Systems, Man, and Cybernetics: Systems",

issn = "2168-2216",

publisher = "IEEE Advancing Technology for Humanity",

number = "1",

}

TY - JOUR

T1 - Continuous visual world modeling for autonomous robot manipulation

AU - Inceoglu, Arda

AU - Koc, Cagatay

AU - Kanat, Besim Ongun

AU - Ersen, Mustafa

AU - Sariel, Sanem

PY - 2019/1

Y1 - 2019/1

N2 - Service robots need to handle a variety of everyday manipulation tasks to accomplish household chores such as cooking and cleaning. Successful execution of these tasks is highly dependent on how reliable the robot perceives its environment through noisy sensing. We present a visual world modeling system for service robots to generate and maintain accurate models of their environments for continuous scenarios. This system is designed to provide a generic platform for both humanoid and ground manipulation robots using different types of vision sensors and algorithms. In our particular implementation, visual data processed by different perception algorithms are used for building and continuously updating a world model of the environment. We evaluate our system on a variety of object manipulation scenarios and show that the system produces consistent perception outcomes suitable for different manipulation tasks.

AB - Service robots need to handle a variety of everyday manipulation tasks to accomplish household chores such as cooking and cleaning. Successful execution of these tasks is highly dependent on how reliable the robot perceives its environment through noisy sensing. We present a visual world modeling system for service robots to generate and maintain accurate models of their environments for continuous scenarios. This system is designed to provide a generic platform for both humanoid and ground manipulation robots using different types of vision sensors and algorithms. In our particular implementation, visual data processed by different perception algorithms are used for building and continuously updating a world model of the environment. We evaluate our system on a variety of object manipulation scenarios and show that the system produces consistent perception outcomes suitable for different manipulation tasks.

KW - 3-D perception

KW - service robots

KW - symbolic scene representation

KW - visual world modeling

UR - http://www.scopus.com/inward/record.url?scp=85041298397&partnerID=8YFLogxK

U2 - 10.1109/TSMC.2017.2787482

DO - 10.1109/TSMC.2017.2787482

M3 - Article

AN - SCOPUS:85041298397

SN - 2168-2216

VL - 49

SP - 192

EP - 205

JO - IEEE Transactions on Systems, Man, and Cybernetics: Systems

JF - IEEE Transactions on Systems, Man, and Cybernetics: Systems

IS - 1

M1 - 8270600

ER -

Continuous visual world modeling for autonomous robot manipulation

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this