ReForm: A Robot Learning Sandbox for Deformable Linear Object Manipulation
Laezza, Rita ; Gieselmann, Robert ; Pokorny, Florian T. and Karayiannidis, Yiannis LU
(2021)
2021 IEEE International Conference on Robotics and Automation, ICRA 2021
p.4717-4723
- Abstract
- Recent advances in machine learning have triggered an enormous interest in using learning-based approaches for robot control and object manipulation. While the majority of existing algorithms are evaluated under the assumption that the involved bodies are rigid, a large number of practical applications contain deformable objects. In this work we focus on Deformable Linear Objects (DLOs) which can be used to model cables, tubes or wires. They are present in many applications such as manufacturing, agriculture and medicine. New methods in robotic manipulation research are often demonstrated in custom environments impeding reproducibility and comparisons of algorithms. We introduce ReForm, a simulation sandbox and a tool for benchmarking... (More)
- Recent advances in machine learning have triggered an enormous interest in using learning-based approaches for robot control and object manipulation. While the majority of existing algorithms are evaluated under the assumption that the involved bodies are rigid, a large number of practical applications contain deformable objects. In this work we focus on Deformable Linear Objects (DLOs) which can be used to model cables, tubes or wires. They are present in many applications such as manufacturing, agriculture and medicine. New methods in robotic manipulation research are often demonstrated in custom environments impeding reproducibility and comparisons of algorithms. We introduce ReForm, a simulation sandbox and a tool for benchmarking manipulation of DLOs. We offer six distinct environments representing important characteristics of deformable objects such as elasticity, plasticity or self-collisions and occlusions. A modular framework is used, enabling design parameters such as the end-effector degrees of freedom, reward function and type of observation. ReForm is a novel robot learning sandbox with which we intend to facilitate testing and reproducibility in manipulation research for DLOs. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/53f9e3af-e978-4f73-b940-85acfebf11ad
- author
- Laezza, Rita
; Gieselmann, Robert
; Pokorny, Florian T.
and Karayiannidis, Yiannis
LU
- publishing date
- 2021
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2021 IEEE International Conference on Robotics and Automation (ICRA)
- pages
- 7 pages
- conference name
- 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
- conference location
- Xi'an, China
- conference dates
- 2021-05-30 - 2021-06-05
- external identifiers
-
- scopus:85116802097
- DOI
- 10.1109/ICRA48506.2021.9561766
- language
- English
- LU publication?
- no
- id
- 53f9e3af-e978-4f73-b940-85acfebf11ad
- date added to LUP
- 2022-12-14 15:11:33
- date last changed
- 2024-01-30 00:53:55
@inproceedings{53f9e3af-e978-4f73-b940-85acfebf11ad,
abstract = {{Recent advances in machine learning have triggered an enormous interest in using learning-based approaches for robot control and object manipulation. While the majority of existing algorithms are evaluated under the assumption that the involved bodies are rigid, a large number of practical applications contain deformable objects. In this work we focus on Deformable Linear Objects (DLOs) which can be used to model cables, tubes or wires. They are present in many applications such as manufacturing, agriculture and medicine. New methods in robotic manipulation research are often demonstrated in custom environments impeding reproducibility and comparisons of algorithms. We introduce ReForm, a simulation sandbox and a tool for benchmarking manipulation of DLOs. We offer six distinct environments representing important characteristics of deformable objects such as elasticity, plasticity or self-collisions and occlusions. A modular framework is used, enabling design parameters such as the end-effector degrees of freedom, reward function and type of observation. ReForm is a novel robot learning sandbox with which we intend to facilitate testing and reproducibility in manipulation research for DLOs.}},
author = {{Laezza, Rita and Gieselmann, Robert and Pokorny, Florian T. and Karayiannidis, Yiannis}},
booktitle = {{2021 IEEE International Conference on Robotics and Automation (ICRA)}},
language = {{eng}},
pages = {{4717--4723}},
title = {{ReForm: A Robot Learning Sandbox for Deformable Linear Object Manipulation}},
url = {{http://dx.doi.org/10.1109/ICRA48506.2021.9561766}},
doi = {{10.1109/ICRA48506.2021.9561766}},
year = {{2021}},
}