Robust optimization with applications to design of context specific robot solutions

Troels Bo Jørgensen, Adam Wolniakowski, Henrik Gordon Petersen, Kristian Debrabant, Norbert Krüger

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

This paper presents an investigation of five optimization algorithms for simulation-based optimization for robotic tasks, where robust solutions are required. We evaluate the optimization methods on three use cases. The use cases involve using a robot for handling meat, optimizing gripper design for aligning objects and optimizing gripper design for table picking in cluttered scenes. We use dynamic simulations to model the use cases, where the most important physical aspects are captured. We have a focus on the robustness with respect to crucial system uncertainties, which is important in an industrial setting. The choice of parameterization and objective scores is also discussed since this choice has some impact on the performance of the optimization algorithms. For all problems, we find feasible solutions ready for real world testing, and overall the optimization method RBFopt has the best performance in terms of finding robust solutions within the fewest amount of simulations.

Original languageEnglish
JournalRobotics and Computer-Integrated Manufacturing
Volume53
Pages (from-to)162–177
ISSN0736-5845
DOIs
Publication statusPublished - 2018

Fingerprint

Robots
Grippers
Meats
Parameterization
Robotics
Computer simulation
Testing

Keywords

  • Dynamic simulation
  • Robotic manipulation
  • Robust optimization

Cite this

@article{2dbb74825527499ea867eb255731ad07,
title = "Robust optimization with applications to design of context specific robot solutions",
abstract = "This paper presents an investigation of five optimization algorithms for simulation-based optimization for robotic tasks, where robust solutions are required. We evaluate the optimization methods on three use cases. The use cases involve using a robot for handling meat, optimizing gripper design for aligning objects and optimizing gripper design for table picking in cluttered scenes. We use dynamic simulations to model the use cases, where the most important physical aspects are captured. We have a focus on the robustness with respect to crucial system uncertainties, which is important in an industrial setting. The choice of parameterization and objective scores is also discussed since this choice has some impact on the performance of the optimization algorithms. For all problems, we find feasible solutions ready for real world testing, and overall the optimization method RBFopt has the best performance in terms of finding robust solutions within the fewest amount of simulations.",
keywords = "Dynamic simulation, Robotic manipulation, Robust optimization",
author = "J{\o}rgensen, {Troels Bo} and Adam Wolniakowski and Petersen, {Henrik Gordon} and Kristian Debrabant and Norbert Kr{\"u}ger",
year = "2018",
doi = "10.1016/j.rcim.2018.04.005",
language = "English",
volume = "53",
pages = "162–177",
journal = "Robotics and Computer-Integrated Manufacturing",
issn = "0736-5845",
publisher = "Pergamon Press",

}

Robust optimization with applications to design of context specific robot solutions. / Jørgensen, Troels Bo; Wolniakowski, Adam; Petersen, Henrik Gordon; Debrabant, Kristian; Krüger, Norbert.

In: Robotics and Computer-Integrated Manufacturing, Vol. 53, 2018, p. 162–177.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Robust optimization with applications to design of context specific robot solutions

AU - Jørgensen, Troels Bo

AU - Wolniakowski, Adam

AU - Petersen, Henrik Gordon

AU - Debrabant, Kristian

AU - Krüger, Norbert

PY - 2018

Y1 - 2018

N2 - This paper presents an investigation of five optimization algorithms for simulation-based optimization for robotic tasks, where robust solutions are required. We evaluate the optimization methods on three use cases. The use cases involve using a robot for handling meat, optimizing gripper design for aligning objects and optimizing gripper design for table picking in cluttered scenes. We use dynamic simulations to model the use cases, where the most important physical aspects are captured. We have a focus on the robustness with respect to crucial system uncertainties, which is important in an industrial setting. The choice of parameterization and objective scores is also discussed since this choice has some impact on the performance of the optimization algorithms. For all problems, we find feasible solutions ready for real world testing, and overall the optimization method RBFopt has the best performance in terms of finding robust solutions within the fewest amount of simulations.

AB - This paper presents an investigation of five optimization algorithms for simulation-based optimization for robotic tasks, where robust solutions are required. We evaluate the optimization methods on three use cases. The use cases involve using a robot for handling meat, optimizing gripper design for aligning objects and optimizing gripper design for table picking in cluttered scenes. We use dynamic simulations to model the use cases, where the most important physical aspects are captured. We have a focus on the robustness with respect to crucial system uncertainties, which is important in an industrial setting. The choice of parameterization and objective scores is also discussed since this choice has some impact on the performance of the optimization algorithms. For all problems, we find feasible solutions ready for real world testing, and overall the optimization method RBFopt has the best performance in terms of finding robust solutions within the fewest amount of simulations.

KW - Dynamic simulation

KW - Robotic manipulation

KW - Robust optimization

U2 - 10.1016/j.rcim.2018.04.005

DO - 10.1016/j.rcim.2018.04.005

M3 - Journal article

VL - 53

SP - 162

EP - 177

JO - Robotics and Computer-Integrated Manufacturing

JF - Robotics and Computer-Integrated Manufacturing

SN - 0736-5845

ER -