Vision-based robotic system for object agnostic placing operations

Nikolaos Rofalis; Lazaros Nalpantidis; Nils Axel Andersen; Volker Kriger

doi:10.5220/0005712404650473

Vision-based robotic system for object agnostic placing operations

Nikolaos Rofalis, Lazaros Nalpantidis, Nils Axel Andersen, Volker Kriger

Aalborg University

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Industrial robots are part of almost all modern factories. Even though, industrial robots nowadays manipulate objects of a huge variety in different environments, exact knowledge about both of them is generally assumed. The aim of this work is to investigate the ability of a robotic system to operate within an unknown environment manipulating unknown objects. The developed system detects objects, finds matching compartments in a placing box, and ultimately grasps and places the objects there. The developed system exploits 3D sensing and visual feature extraction. No prior knowledge is provided to the system, neither for the objects nor for the placing box. The experimental evaluation of the developed robotic system shows that a combination of seemingly simple modules and strategies can provide effective solution to the targeted problem.

Original language	English
Title of host publication	VISIGRAPP 2016. 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Publisher	SCITEPRESS Digital Library
Publication date	2016
Pages	467-75
ISBN (Print)	9789897581755
DOIs	https://doi.org/10.5220/0005712404650473
Publication status	Published - 2016
Event	11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) - Rome, Italy Duration: 27 Feb 2016 → 29 Feb 2016

Conference

Conference	11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP)
Country/Territory	Italy
City	Rome
Period	27/02/2016 → 29/02/2016

Keywords

Image recognition
Control in industrial production systems
Computer vision and image processing techniques
Robotics
Manufacturing facilities
image matching
industrial robots
production facilities
robot vision
modern factories
visual feature extraction
3D sensing
matching compartments
environment unknown object manipulation
object agnostic placing operations
vision-based robotic system

Access to Document

10.5220/0005712404650473

OpenUrl availability

Full text

Cite this

@inproceedings{4b70901fda754812b4f2072d7d1391e7,

title = "Vision-based robotic system for object agnostic placing operations",

abstract = "Industrial robots are part of almost all modern factories. Even though, industrial robots nowadays manipulate objects of a huge variety in different environments, exact knowledge about both of them is generally assumed. The aim of this work is to investigate the ability of a robotic system to operate within an unknown environment manipulating unknown objects. The developed system detects objects, finds matching compartments in a placing box, and ultimately grasps and places the objects there. The developed system exploits 3D sensing and visual feature extraction. No prior knowledge is provided to the system, neither for the objects nor for the placing box. The experimental evaluation of the developed robotic system shows that a combination of seemingly simple modules and strategies can provide effective solution to the targeted problem.",

keywords = "Image recognition, Control in industrial production systems, Computer vision and image processing techniques, Robotics, Manufacturing facilities, image matching, industrial robots, production facilities, robot vision, modern factories, visual feature extraction, 3D sensing, matching compartments, environment unknown object manipulation, object agnostic placing operations, vision-based robotic system",

author = "Nikolaos Rofalis and Lazaros Nalpantidis and Andersen, {Nils Axel} and Volker Kriger",

year = "2016",

doi = "10.5220/0005712404650473",

language = "English",

isbn = "9789897581755",

pages = "467--75",

booktitle = "VISIGRAPP 2016. 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

publisher = "SCITEPRESS Digital Library",

note = "11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) ; Conference date: 27-02-2016 Through 29-02-2016",

}

Rofalis, N, Nalpantidis, L, Andersen, NA & Kriger, V 2016, Vision-based robotic system for object agnostic placing operations. in VISIGRAPP 2016. 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. SCITEPRESS Digital Library, pp. 467-75, 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), Rome, Italy, 27/02/2016. https://doi.org/10.5220/0005712404650473

Vision-based robotic system for object agnostic placing operations. / Rofalis, Nikolaos; Nalpantidis, Lazaros; Andersen, Nils Axel et al.
VISIGRAPP 2016. 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. SCITEPRESS Digital Library, 2016. p. 467-75.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Vision-based robotic system for object agnostic placing operations

AU - Rofalis, Nikolaos

AU - Nalpantidis, Lazaros

AU - Andersen, Nils Axel

AU - Kriger, Volker

PY - 2016

Y1 - 2016

N2 - Industrial robots are part of almost all modern factories. Even though, industrial robots nowadays manipulate objects of a huge variety in different environments, exact knowledge about both of them is generally assumed. The aim of this work is to investigate the ability of a robotic system to operate within an unknown environment manipulating unknown objects. The developed system detects objects, finds matching compartments in a placing box, and ultimately grasps and places the objects there. The developed system exploits 3D sensing and visual feature extraction. No prior knowledge is provided to the system, neither for the objects nor for the placing box. The experimental evaluation of the developed robotic system shows that a combination of seemingly simple modules and strategies can provide effective solution to the targeted problem.

AB - Industrial robots are part of almost all modern factories. Even though, industrial robots nowadays manipulate objects of a huge variety in different environments, exact knowledge about both of them is generally assumed. The aim of this work is to investigate the ability of a robotic system to operate within an unknown environment manipulating unknown objects. The developed system detects objects, finds matching compartments in a placing box, and ultimately grasps and places the objects there. The developed system exploits 3D sensing and visual feature extraction. No prior knowledge is provided to the system, neither for the objects nor for the placing box. The experimental evaluation of the developed robotic system shows that a combination of seemingly simple modules and strategies can provide effective solution to the targeted problem.

KW - Image recognition

KW - Control in industrial production systems

KW - Computer vision and image processing techniques

KW - Robotics

KW - Manufacturing facilities

KW - image matching

KW - industrial robots

KW - production facilities

KW - robot vision

KW - modern factories

KW - visual feature extraction

KW - 3D sensing

KW - matching compartments

KW - environment unknown object manipulation

KW - object agnostic placing operations

KW - vision-based robotic system

U2 - 10.5220/0005712404650473

DO - 10.5220/0005712404650473

M3 - Article in proceedings

SN - 9789897581755

SP - 467

EP - 475

BT - VISIGRAPP 2016. 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

PB - SCITEPRESS Digital Library

T2 - 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP)

Y2 - 27 February 2016 through 29 February 2016

ER -

Vision-based robotic system for object agnostic placing operations

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this