elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Speeding Up Optimization-based Motion Planning through Deep Learning

Tenhumberg, Johannes und Darius, Burschka und Bäuml, Berthold (2022) Speeding Up Optimization-based Motion Planning through Deep Learning. In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022-10-23 - 2022-10-27, Kyoto, Japan. doi: 10.1109/IROS47612.2022.9981717. ISBN 978-166547927-1. ISSN 2153-0858.

[img] PDF
5MB

Offizielle URL: https://ieeexplore.ieee.org/document/9981717

Kurzfassung

Planning collision-free motions for robots with many degrees of freedom is challenging in environments with complex obstacle geometries. Recent work introduced the idea of speeding up the planning by encoding prior experience of successful motion plans in a neural network. However, this 'neural motion planning' did not scale to complex robots in unseen 3D environments as needed for real-world applications. Here, we introduce 'basis point set', well-known in computer vision, to neural motion planning as a modern compact environment encoding enabling efficient supervised training networks that generalize well over diverse 3D worlds. Combined with a new elaborate training scheme, we reach a planning success rate of 100 %. We use the network to predict an educated initial guess for an optimization-based planner (OMP), which quickly converges to a feasible solution, massively outperforming random multi-starts when tested on previously unseen environments. For the DLR humanoid Agile Justin with 19 DoF and in challenging obstacle environments, optimal paths can be generated in 200 ms using only a single CPU core. We also show a first successful real-world experiment based on a high-resolution world model from an integrated 3D sensor.

elib-URL des Eintrags:https://elib.dlr.de/187915/
Dokumentart:Konferenzbeitrag (Vortrag)
Zusätzliche Informationen:Video: https://kzbin.info/www/speeding-up-optimization-based-motion-planning-through-deep-learning/hIOtoJV9ptCKoa8
Titel:Speeding Up Optimization-based Motion Planning through Deep Learning
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Tenhumberg, JohannesJohannes.Tenhumberg (at) dlr.dehttps://orcid.org/0000-0002-5090-1259NICHT SPEZIFIZIERT
Darius, Burschkaburschka (at) cs.tum.eduhttps://orcid.org/0000-0002-9866-0343NICHT SPEZIFIZIERT
Bäuml, BertholdBerthold.Baeuml (at) dlr.dehttps://orcid.org/0000-0002-4545-4765NICHT SPEZIFIZIERT
Datum:20 Oktober 2022
Erschienen in:2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Ja
DOI:10.1109/IROS47612.2022.9981717
ISSN:2153-0858
ISBN:978-166547927-1
Status:veröffentlicht
Stichwörter:Motion and Path Planning; Deep Learning Methods; Learning from Experience
Veranstaltungstitel:IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Veranstaltungsort:Kyoto, Japan
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:23 Oktober 2022
Veranstaltungsende:27 Oktober 2022
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Robotik
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R RO - Robotik
DLR - Teilgebiet (Projekt, Vorhaben):R - Telerobotik
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Robotik und Mechatronik (ab 2013)
Hinterlegt von: Tenhumberg, Johannes
Hinterlegt am:05 Dez 2022 12:13
Letzte Änderung:24 Apr 2024 20:49

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.