Exploiting symmetries and extrusions for grasping household objects

Ana Huamán Quispe, Benoît Milville, Marco A. Gutiérrez, Can Erdogan, Mike Stilman, Henrik Christensen, Hani Ben Amor

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

11 Citations (Scopus)

Abstract

In this paper we present an approach for creating complete shape representations from a single depth image for robot grasping. We introduce algorithms for completing partial point clouds based on the analysis of symmetry and extrusion patterns in observed shapes. Identified patterns are used to generate a complete mesh of the object, which is, in turn, used for grasp planning. The approach allows robots to predict the shape of objects and include invisible regions into the grasp planning step. We show that the identification of shape patterns, such as extrusions, can be used for fast generation and optimization of grasps. Finally, we present experiments performed with our humanoid robot executing pick-up tasks based on single depth images and discuss the applications and shortcomings of our approach.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3702-3708
Number of pages7
Volume2015-June
EditionJune
DOIs
StatePublished - Jun 29 2015
Externally publishedYes
Event2015 IEEE International Conference on Robotics and Automation, ICRA 2015 - Seattle, United States
Duration: May 26 2015May 30 2015

Other

Other2015 IEEE International Conference on Robotics and Automation, ICRA 2015
CountryUnited States
CitySeattle
Period5/26/155/30/15

Fingerprint

Extrusion
Robots
Planning
Experiments

ASJC Scopus subject areas

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

Cite this

Quispe, A. H., Milville, B., Gutiérrez, M. A., Erdogan, C., Stilman, M., Christensen, H., & Ben Amor, H. (2015). Exploiting symmetries and extrusions for grasping household objects. In Proceedings - IEEE International Conference on Robotics and Automation (June ed., Vol. 2015-June, pp. 3702-3708). [7139713] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2015.7139713

Exploiting symmetries and extrusions for grasping household objects. / Quispe, Ana Huamán; Milville, Benoît; Gutiérrez, Marco A.; Erdogan, Can; Stilman, Mike; Christensen, Henrik; Ben Amor, Hani.

Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2015-June June. ed. Institute of Electrical and Electronics Engineers Inc., 2015. p. 3702-3708 7139713.

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

Quispe, AH, Milville, B, Gutiérrez, MA, Erdogan, C, Stilman, M, Christensen, H & Ben Amor, H 2015, Exploiting symmetries and extrusions for grasping household objects. in Proceedings - IEEE International Conference on Robotics and Automation. June edn, vol. 2015-June, 7139713, Institute of Electrical and Electronics Engineers Inc., pp. 3702-3708, 2015 IEEE International Conference on Robotics and Automation, ICRA 2015, Seattle, United States, 5/26/15. https://doi.org/10.1109/ICRA.2015.7139713
Quispe AH, Milville B, Gutiérrez MA, Erdogan C, Stilman M, Christensen H et al. Exploiting symmetries and extrusions for grasping household objects. In Proceedings - IEEE International Conference on Robotics and Automation. June ed. Vol. 2015-June. Institute of Electrical and Electronics Engineers Inc. 2015. p. 3702-3708. 7139713 https://doi.org/10.1109/ICRA.2015.7139713
Quispe, Ana Huamán ; Milville, Benoît ; Gutiérrez, Marco A. ; Erdogan, Can ; Stilman, Mike ; Christensen, Henrik ; Ben Amor, Hani. / Exploiting symmetries and extrusions for grasping household objects. Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2015-June June. ed. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 3702-3708
@inproceedings{180405f94343476590411f3476156747,
title = "Exploiting symmetries and extrusions for grasping household objects",
abstract = "In this paper we present an approach for creating complete shape representations from a single depth image for robot grasping. We introduce algorithms for completing partial point clouds based on the analysis of symmetry and extrusion patterns in observed shapes. Identified patterns are used to generate a complete mesh of the object, which is, in turn, used for grasp planning. The approach allows robots to predict the shape of objects and include invisible regions into the grasp planning step. We show that the identification of shape patterns, such as extrusions, can be used for fast generation and optimization of grasps. Finally, we present experiments performed with our humanoid robot executing pick-up tasks based on single depth images and discuss the applications and shortcomings of our approach.",
author = "Quispe, {Ana Huam{\'a}n} and Beno{\^i}t Milville and Guti{\'e}rrez, {Marco A.} and Can Erdogan and Mike Stilman and Henrik Christensen and {Ben Amor}, Hani",
year = "2015",
month = "6",
day = "29",
doi = "10.1109/ICRA.2015.7139713",
language = "English (US)",
volume = "2015-June",
pages = "3702--3708",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
edition = "June",

}

TY - GEN

T1 - Exploiting symmetries and extrusions for grasping household objects

AU - Quispe, Ana Huamán

AU - Milville, Benoît

AU - Gutiérrez, Marco A.

AU - Erdogan, Can

AU - Stilman, Mike

AU - Christensen, Henrik

AU - Ben Amor, Hani

PY - 2015/6/29

Y1 - 2015/6/29

N2 - In this paper we present an approach for creating complete shape representations from a single depth image for robot grasping. We introduce algorithms for completing partial point clouds based on the analysis of symmetry and extrusion patterns in observed shapes. Identified patterns are used to generate a complete mesh of the object, which is, in turn, used for grasp planning. The approach allows robots to predict the shape of objects and include invisible regions into the grasp planning step. We show that the identification of shape patterns, such as extrusions, can be used for fast generation and optimization of grasps. Finally, we present experiments performed with our humanoid robot executing pick-up tasks based on single depth images and discuss the applications and shortcomings of our approach.

AB - In this paper we present an approach for creating complete shape representations from a single depth image for robot grasping. We introduce algorithms for completing partial point clouds based on the analysis of symmetry and extrusion patterns in observed shapes. Identified patterns are used to generate a complete mesh of the object, which is, in turn, used for grasp planning. The approach allows robots to predict the shape of objects and include invisible regions into the grasp planning step. We show that the identification of shape patterns, such as extrusions, can be used for fast generation and optimization of grasps. Finally, we present experiments performed with our humanoid robot executing pick-up tasks based on single depth images and discuss the applications and shortcomings of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84938244979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938244979&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2015.7139713

DO - 10.1109/ICRA.2015.7139713

M3 - Conference contribution

AN - SCOPUS:84938244979

VL - 2015-June

SP - 3702

EP - 3708

BT - Proceedings - IEEE International Conference on Robotics and Automation

PB - Institute of Electrical and Electronics Engineers Inc.

ER -