elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Kinematic transfer learning of sampling distributions for manipulator motion planning

Lehner, Peter and Roa Garzon, Máximo Alejandro and Albu-Schäffer, Alin Olimpiu (2022) Kinematic transfer learning of sampling distributions for manipulator motion planning. In: 39th IEEE International Conference on Robotics and Automation, ICRA 2022. IEEE. 2022 IEEE International Conference on Robotics and Automation, 23-27 May 2022, Philadelphia, USA. doi: 10.1109/ICRA46639.2022.9811915. ISBN 978-172819681-7. ISSN 1050-4729.

[img] PDF
2MB

Official URL: https://ieeexplore.ieee.org/document/9811915

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.

Item URL in elib:https://elib.dlr.de/186868/
Document Type:Conference or Workshop Item (Speech, Poster)
Title:Kinematic transfer learning of sampling distributions for manipulator motion planning
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Lehner, PeterUNSPECIFIEDhttps://orcid.org/0000-0002-3755-1186UNSPECIFIED
Roa Garzon, Máximo AlejandroUNSPECIFIEDhttps://orcid.org/0000-0003-1708-4223UNSPECIFIED
Albu-Schäffer, Alin OlimpiuUNSPECIFIEDhttps://orcid.org/0000-0001-5343-9074142115902
Date:May 2022
Journal or Publication Title:39th IEEE International Conference on Robotics and Automation, ICRA 2022
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI:10.1109/ICRA46639.2022.9811915
Publisher:IEEE
ISSN:1050-4729
ISBN:978-172819681-7
Status:Published
Keywords:robotics motion-planning transfer-learning
Event Title:2022 IEEE International Conference on Robotics and Automation
Event Location:Philadelphia, USA
Event Type:international Conference
Event Dates:23-27 May 2022
Organizer:IEEE Robotics and Automation Society
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - Terrestrial Assistance Robotics
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Lehner, Peter
Deposited On:13 Jul 2022 12:27
Last Modified:27 Oct 2023 15:29

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.