Adapting Parameterized Motions using Iterative Learning and Online Collision Detection

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Achieving both the flexibility and robustness required to advance the use of robotics in small and medium-sized productions is an essential but difficult task.
A fundamental problem is making the robot run blindly without additional sensors while still being robust to uncertainties and variations in the assembly processes.
In this paper, we address the use of parameterized motions suitable for blind execution and robust to uncertainties in the assembly process.
Collisions and incorrect assemblies are detected based on robot motor currents while motion parameters are updated based on Bayesian Optimization utilizing Gaussian Process learning.
This allows for motion parameters to be optimized using real world trials which incorporate all uncertainties inherent in the assembly process without requiring advanced robot and sensor setups.
The result is a simple and straightforward system which helps the user automatically find robust and uncertainty-tolerant motions.
We present experiments for an assembly case showing both detection and learning in the real world and how these combine to a robust robot system.
Original languageEnglish
Title of host publicationProceeding of the 2018 IEEE International Conference on Robotics and Automation
PublisherIEEE
Publication date13. Sep 2018
Pages7587-7594
ISBN (Print)978-1-5386-3082-2
ISBN (Electronic)978-1-5386-3081-5
DOIs
Publication statusPublished - 13. Sep 2018
Event2018 IEEE International Conference on Robotics and Automation - The Brisbane Convention & Exhibition Centre, Brisbane, Australia
Duration: 21. May 201825. May 2018
https://icra2018.org/

Conference

Conference2018 IEEE International Conference on Robotics and Automation
LocationThe Brisbane Convention & Exhibition Centre
CountryAustralia
CityBrisbane
Period21/05/201825/05/2018
Internet address

Cite this

Laursen, J. S., Sørensen, L. C., Schultz, U. P., Ellekilde, L-P., & Kraft, D. (2018). Adapting Parameterized Motions using Iterative Learning and Online Collision Detection. In Proceeding of the 2018 IEEE International Conference on Robotics and Automation (pp. 7587-7594). IEEE. https://doi.org/10.1109/ICRA.2018.8463208
Laursen, Johan Sund ; Sørensen, Lars Carøe ; Schultz, Ulrik Pagh ; Ellekilde, Lars-Peter ; Kraft, Dirk. / Adapting Parameterized Motions using Iterative Learning and Online Collision Detection. Proceeding of the 2018 IEEE International Conference on Robotics and Automation. IEEE, 2018. pp. 7587-7594
@inproceedings{9954c6e0c8d84b7b851889d104a03bcc,
title = "Adapting Parameterized Motions using Iterative Learning and Online Collision Detection",
abstract = "Achieving both the flexibility and robustness required to advance the use of robotics in small and medium-sized productions is an essential but difficult task. A fundamental problem is making the robot run blindly without additional sensors while still being robust to uncertainties and variations in the assembly processes.In this paper, we address the use of parameterized motions suitable for blind execution and robust to uncertainties in the assembly process. Collisions and incorrect assemblies are detected based on robot motor currents while motion parameters are updated based on Bayesian Optimization utilizing Gaussian Process learning. This allows for motion parameters to be optimized using real world trials which incorporate all uncertainties inherent in the assembly process without requiring advanced robot and sensor setups. The result is a simple and straightforward system which helps the user automatically find robust and uncertainty-tolerant motions. We present experiments for an assembly case showing both detection and learning in the real world and how these combine to a robust robot system.",
author = "Laursen, {Johan Sund} and S{\o}rensen, {Lars Car{\o}e} and Schultz, {Ulrik Pagh} and Lars-Peter Ellekilde and Dirk Kraft",
year = "2018",
month = "9",
day = "13",
doi = "10.1109/ICRA.2018.8463208",
language = "English",
isbn = "978-1-5386-3082-2",
pages = "7587--7594",
booktitle = "Proceeding of the 2018 IEEE International Conference on Robotics and Automation",
publisher = "IEEE",
address = "United States",

}

Laursen, JS, Sørensen, LC, Schultz, UP, Ellekilde, L-P & Kraft, D 2018, Adapting Parameterized Motions using Iterative Learning and Online Collision Detection. in Proceeding of the 2018 IEEE International Conference on Robotics and Automation. IEEE, pp. 7587-7594, 2018 IEEE International Conference on Robotics and Automation, Brisbane, Australia, 21/05/2018. https://doi.org/10.1109/ICRA.2018.8463208

Adapting Parameterized Motions using Iterative Learning and Online Collision Detection. / Laursen, Johan Sund; Sørensen, Lars Carøe; Schultz, Ulrik Pagh; Ellekilde, Lars-Peter; Kraft, Dirk.

Proceeding of the 2018 IEEE International Conference on Robotics and Automation. IEEE, 2018. p. 7587-7594.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Adapting Parameterized Motions using Iterative Learning and Online Collision Detection

AU - Laursen, Johan Sund

AU - Sørensen, Lars Carøe

AU - Schultz, Ulrik Pagh

AU - Ellekilde, Lars-Peter

AU - Kraft, Dirk

PY - 2018/9/13

Y1 - 2018/9/13

N2 - Achieving both the flexibility and robustness required to advance the use of robotics in small and medium-sized productions is an essential but difficult task. A fundamental problem is making the robot run blindly without additional sensors while still being robust to uncertainties and variations in the assembly processes.In this paper, we address the use of parameterized motions suitable for blind execution and robust to uncertainties in the assembly process. Collisions and incorrect assemblies are detected based on robot motor currents while motion parameters are updated based on Bayesian Optimization utilizing Gaussian Process learning. This allows for motion parameters to be optimized using real world trials which incorporate all uncertainties inherent in the assembly process without requiring advanced robot and sensor setups. The result is a simple and straightforward system which helps the user automatically find robust and uncertainty-tolerant motions. We present experiments for an assembly case showing both detection and learning in the real world and how these combine to a robust robot system.

AB - Achieving both the flexibility and robustness required to advance the use of robotics in small and medium-sized productions is an essential but difficult task. A fundamental problem is making the robot run blindly without additional sensors while still being robust to uncertainties and variations in the assembly processes.In this paper, we address the use of parameterized motions suitable for blind execution and robust to uncertainties in the assembly process. Collisions and incorrect assemblies are detected based on robot motor currents while motion parameters are updated based on Bayesian Optimization utilizing Gaussian Process learning. This allows for motion parameters to be optimized using real world trials which incorporate all uncertainties inherent in the assembly process without requiring advanced robot and sensor setups. The result is a simple and straightforward system which helps the user automatically find robust and uncertainty-tolerant motions. We present experiments for an assembly case showing both detection and learning in the real world and how these combine to a robust robot system.

U2 - 10.1109/ICRA.2018.8463208

DO - 10.1109/ICRA.2018.8463208

M3 - Article in proceedings

SN - 978-1-5386-3082-2

SP - 7587

EP - 7594

BT - Proceeding of the 2018 IEEE International Conference on Robotics and Automation

PB - IEEE

ER -

Laursen JS, Sørensen LC, Schultz UP, Ellekilde L-P, Kraft D. Adapting Parameterized Motions using Iterative Learning and Online Collision Detection. In Proceeding of the 2018 IEEE International Conference on Robotics and Automation. IEEE. 2018. p. 7587-7594 https://doi.org/10.1109/ICRA.2018.8463208