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

Speeding Up Optimization-based Motion Planning through Deep Learning

Tenhumberg, Johannes and Darius, Burschka and 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

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


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.

Item URL in elib:https://elib.dlr.de/187915/
Document Type:Conference or Workshop Item (Speech)
Additional Information:Video: https://kzbin.info/www/speeding-up-optimization-based-motion-planning-through-deep-learning/hIOtoJV9ptCKoa8
Title:Speeding Up Optimization-based Motion Planning through Deep Learning
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Tenhumberg, JohannesUNSPECIFIEDhttps://orcid.org/0000-0002-5090-1259UNSPECIFIED
Darius, BurschkaUNSPECIFIEDhttps://orcid.org/0000-0002-9866-0343UNSPECIFIED
Bäuml, BertholdUNSPECIFIEDhttps://orcid.org/0000-0002-4545-4765UNSPECIFIED
Date:20 October 2022
Journal or Publication Title:2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
Keywords:Motion and Path Planning; Deep Learning Methods; Learning from Experience
Event Title:IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Event Location:Kyoto, Japan
Event Type:international Conference
Event Start Date:23 October 2022
Event End Date:27 October 2022
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 - Telerobotics
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Tenhumberg, Johannes
Deposited On:05 Dec 2022 12:13
Last Modified:24 Apr 2024 20:49

Repository Staff Only: item control page

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