An Adaptive Robotic System for Doing Pick and Place Operations with Deformable Objects

Troels Bo Jørgensen*, Sebastian Hoppe Nesgaard Jensen, Henrik Aanæs, Niels Worsøe Hansen, Norbert Krüger

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

199 Downloads (Pure)

Abstract

This paper presents a robot system for performing pick and place operations with deformable objects. The system uses a structured light scanner to capture a point cloud of the object to be grasped. This point cloud is then analyzed to determine a pick and place action. Finally, the determined action is executed by the robot to solve the task. The robotic placement strategy contains several free parameters, which should be chosen in a context-specific manner. To determine these parameters we rely on simulation-based optimization of the individual use cases. The entire system is tested extensively in real world trials. First, the reliability of the grasp is evaluated for 7 different types of pork cuts. Then the validity of the simulation-based optimization of the placement strategy is evaluated for 2 of the most different pork cuts, to show the generality of the overall approach.

Original languageEnglish
JournalJournal of Intelligent and Robotic Systems: Theory and Applications
Volume94
Issue number1
Pages (from-to)81-100
ISSN0921-0296
DOIs
Publication statusPublished - 15 Apr 2019

Keywords

  • Deformable objects
  • Robotic manipulation
  • Simulation-based optimization
  • Structured light scanner
  • Vision-based meat analysis

Cite this

Jørgensen, Troels Bo ; Jensen, Sebastian Hoppe Nesgaard ; Aanæs, Henrik ; Hansen, Niels Worsøe ; Krüger, Norbert. / An Adaptive Robotic System for Doing Pick and Place Operations with Deformable Objects. In: Journal of Intelligent and Robotic Systems: Theory and Applications. 2019 ; Vol. 94, No. 1. pp. 81-100.
@article{37f3a17bcf074880a5948b27557d448f,
title = "An Adaptive Robotic System for Doing Pick and Place Operations with Deformable Objects",
abstract = "This paper presents a robot system for performing pick and place operations with deformable objects. The system uses a structured light scanner to capture a point cloud of the object to be grasped. This point cloud is then analyzed to determine a pick and place action. Finally, the determined action is executed by the robot to solve the task. The robotic placement strategy contains several free parameters, which should be chosen in a context-specific manner. To determine these parameters we rely on simulation-based optimization of the individual use cases. The entire system is tested extensively in real world trials. First, the reliability of the grasp is evaluated for 7 different types of pork cuts. Then the validity of the simulation-based optimization of the placement strategy is evaluated for 2 of the most different pork cuts, to show the generality of the overall approach.",
keywords = "Deformable objects, Robotic manipulation, Simulation-based optimization, Structured light scanner, Vision-based meat analysis",
author = "J{\o}rgensen, {Troels Bo} and Jensen, {Sebastian Hoppe Nesgaard} and Henrik Aan{\ae}s and Hansen, {Niels Wors{\o}e} and Norbert Kr{\"u}ger",
year = "2019",
month = "4",
day = "15",
doi = "10.1007/s10846-018-0958-6",
language = "English",
volume = "94",
pages = "81--100",
journal = "Journal of Intelligent and Robotic Systems",
issn = "0921-0296",
publisher = "Springer Netherlands",
number = "1",

}

An Adaptive Robotic System for Doing Pick and Place Operations with Deformable Objects. / Jørgensen, Troels Bo; Jensen, Sebastian Hoppe Nesgaard; Aanæs, Henrik; Hansen, Niels Worsøe; Krüger, Norbert.

In: Journal of Intelligent and Robotic Systems: Theory and Applications, Vol. 94, No. 1, 15.04.2019, p. 81-100.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - An Adaptive Robotic System for Doing Pick and Place Operations with Deformable Objects

AU - Jørgensen, Troels Bo

AU - Jensen, Sebastian Hoppe Nesgaard

AU - Aanæs, Henrik

AU - Hansen, Niels Worsøe

AU - Krüger, Norbert

PY - 2019/4/15

Y1 - 2019/4/15

N2 - This paper presents a robot system for performing pick and place operations with deformable objects. The system uses a structured light scanner to capture a point cloud of the object to be grasped. This point cloud is then analyzed to determine a pick and place action. Finally, the determined action is executed by the robot to solve the task. The robotic placement strategy contains several free parameters, which should be chosen in a context-specific manner. To determine these parameters we rely on simulation-based optimization of the individual use cases. The entire system is tested extensively in real world trials. First, the reliability of the grasp is evaluated for 7 different types of pork cuts. Then the validity of the simulation-based optimization of the placement strategy is evaluated for 2 of the most different pork cuts, to show the generality of the overall approach.

AB - This paper presents a robot system for performing pick and place operations with deformable objects. The system uses a structured light scanner to capture a point cloud of the object to be grasped. This point cloud is then analyzed to determine a pick and place action. Finally, the determined action is executed by the robot to solve the task. The robotic placement strategy contains several free parameters, which should be chosen in a context-specific manner. To determine these parameters we rely on simulation-based optimization of the individual use cases. The entire system is tested extensively in real world trials. First, the reliability of the grasp is evaluated for 7 different types of pork cuts. Then the validity of the simulation-based optimization of the placement strategy is evaluated for 2 of the most different pork cuts, to show the generality of the overall approach.

KW - Deformable objects

KW - Robotic manipulation

KW - Simulation-based optimization

KW - Structured light scanner

KW - Vision-based meat analysis

U2 - 10.1007/s10846-018-0958-6

DO - 10.1007/s10846-018-0958-6

M3 - Journal article

AN - SCOPUS:85058032112

VL - 94

SP - 81

EP - 100

JO - Journal of Intelligent and Robotic Systems

JF - Journal of Intelligent and Robotic Systems

SN - 0921-0296

IS - 1

ER -