Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning

Peter Lehner; Maximo A. Roa; Alin Albu-Schaffer

doi:10.1109/ICRA46639.2022.9811915

Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning

Peter Lehner, Maximo A. Roa, Alin Albu-Schaffer

Deutsches Zentrum für Luft- und Raumfahrt (DLR)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Recent research has shown that guiding sampling-based planners with sampling distributions, learned from previous experiences via density estimation, can significantly decrease computation times for motion planning. We propose an algorithm that can estimate the density from the experiences of a robot with different kinematic structure, on the same task. The method allows to generalize collected data from one source manipulator to similarly designed target manipulators, significantly reducing the computation time for new queries for the target manipulator. We evaluate the algorithm in two experiments, including a constrained manipulation task with five different collaborative robots, and show that transferring information can significantly decrease planning time.

Original language	English
Title of host publication	2022 IEEE International Conference on Robotics and Automation, ICRA 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7211-7217
Number of pages	7
ISBN (Electronic)	9781728196817
DOIs	https://doi.org/10.1109/ICRA46639.2022.9811915
State	Published - 2022
Externally published	Yes
Event	39th IEEE International Conference on Robotics and Automation, ICRA 2022 - Philadelphia, United States Duration: 23 May 2022 → 27 May 2022

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)	1050-4729

Conference

Conference	39th IEEE International Conference on Robotics and Automation, ICRA 2022
Country/Territory	United States
City	Philadelphia
Period	23/05/22 → 27/05/22

Access to Document

10.1109/ICRA46639.2022.9811915

Cite this

Lehner, P., Roa, M. A., & Albu-Schaffer, A. (2022). Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning. In 2022 IEEE International Conference on Robotics and Automation, ICRA 2022 (pp. 7211-7217). (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA46639.2022.9811915

@inproceedings{a053c141014e4cd6801d1390471e41b6,

title = "Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning",

abstract = "Recent research has shown that guiding sampling-based planners with sampling distributions, learned from previous experiences via density estimation, can significantly decrease computation times for motion planning. We propose an algorithm that can estimate the density from the experiences of a robot with different kinematic structure, on the same task. The method allows to generalize collected data from one source manipulator to similarly designed target manipulators, significantly reducing the computation time for new queries for the target manipulator. We evaluate the algorithm in two experiments, including a constrained manipulation task with five different collaborative robots, and show that transferring information can significantly decrease planning time.",

author = "Peter Lehner and Roa, {Maximo A.} and Alin Albu-Schaffer",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 39th IEEE International Conference on Robotics and Automation, ICRA 2022 ; Conference date: 23-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.1109/ICRA46639.2022.9811915",

language = "English",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "7211--7217",

booktitle = "2022 IEEE International Conference on Robotics and Automation, ICRA 2022",

}

Lehner, P, Roa, MA & Albu-Schaffer, A 2022, Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning. in 2022 IEEE International Conference on Robotics and Automation, ICRA 2022. Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 7211-7217, 39th IEEE International Conference on Robotics and Automation, ICRA 2022, Philadelphia, United States, 23/05/22. https://doi.org/10.1109/ICRA46639.2022.9811915

Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning. / Lehner, Peter; Roa, Maximo A.; Albu-Schaffer, Alin.
2022 IEEE International Conference on Robotics and Automation, ICRA 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 7211-7217 (Proceedings - IEEE International Conference on Robotics and Automation).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning

AU - Lehner, Peter

AU - Roa, Maximo A.

AU - Albu-Schaffer, Alin

PY - 2022

Y1 - 2022

N2 - Recent research has shown that guiding sampling-based planners with sampling distributions, learned from previous experiences via density estimation, can significantly decrease computation times for motion planning. We propose an algorithm that can estimate the density from the experiences of a robot with different kinematic structure, on the same task. The method allows to generalize collected data from one source manipulator to similarly designed target manipulators, significantly reducing the computation time for new queries for the target manipulator. We evaluate the algorithm in two experiments, including a constrained manipulation task with five different collaborative robots, and show that transferring information can significantly decrease planning time.

AB - Recent research has shown that guiding sampling-based planners with sampling distributions, learned from previous experiences via density estimation, can significantly decrease computation times for motion planning. We propose an algorithm that can estimate the density from the experiences of a robot with different kinematic structure, on the same task. The method allows to generalize collected data from one source manipulator to similarly designed target manipulators, significantly reducing the computation time for new queries for the target manipulator. We evaluate the algorithm in two experiments, including a constrained manipulation task with five different collaborative robots, and show that transferring information can significantly decrease planning time.

UR - http://www.scopus.com/inward/record.url?scp=85136319879&partnerID=8YFLogxK

U2 - 10.1109/ICRA46639.2022.9811915

DO - 10.1109/ICRA46639.2022.9811915

M3 - Conference contribution

AN - SCOPUS:85136319879

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 7211

EP - 7217

BT - 2022 IEEE International Conference on Robotics and Automation, ICRA 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 39th IEEE International Conference on Robotics and Automation, ICRA 2022

Y2 - 23 May 2022 through 27 May 2022

ER -

Lehner P, Roa MA, Albu-Schaffer A. Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning. In 2022 IEEE International Conference on Robotics and Automation, ICRA 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 7211-7217. (Proceedings - IEEE International Conference on Robotics and Automation). doi: 10.1109/ICRA46639.2022.9811915

Kinematic Transfer Learning of Sampling Distributions for Manipulator Motion Planning

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this