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

Visual Repetition Sampling for Robot Manipulation Planning

Puang, En Yen and Lehner, Peter and Marton, Zoltan-Csaba and Durner, Maximilian and Triebel, Rudolph and Albu-Schäffer, Alin Olimpiu (2019) Visual Repetition Sampling for Robot Manipulation Planning. In: IEEE International Conference on Robotics and Automation ICRA. ICRA 2019, 20-24 May, Montreal.

[img] PDF


One of the main challenges in sampling-based motion planners is to find an efficient sampling strategy. While methods such as Rapidly-exploring Random Tree (RRT) have shown to be more reliable in complex environments than optimization-based methods, they often require longer planning times, which reduces their usability for real-time applications. Recently, biased sampling methods have shown to remedy this issue. For example Gaussian Mixture Models (GMMs) have been used to sample more efficiently in feasible regions of the configuration space. Once the GMM is learned, however, this approach does not adapt its biases to individual planning scene during inference. Hence, we propose in this work a more efficient sampling strategy to further bias the GMM based on visual input upon query. We employ an autoencoder trained entirely in simulation to extract features from depth images and use the latent representation to adjust the weights of each Gaussian components in the GMM. We show empirically that this improves the sampling efficiency of an RRT motion planner in both real and simulated scenes.

Item URL in elib:https://elib.dlr.de/128182/
Document Type:Conference or Workshop Item (Poster)
Title:Visual Repetition Sampling for Robot Manipulation Planning
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Puang, En Yenen.puang (at) dlr.deUNSPECIFIED
Lehner, PeterPeter.Lehner (at) dlr.deUNSPECIFIED
Marton, Zoltan-CsabaZoltan.Marton (at) dlr.dehttps://orcid.org/0000-0002-3035-493X
Durner, MaximilianMaximilian.Durner (at) dlr.deUNSPECIFIED
Triebel, RudolphRudolph.Triebel (at) dlr.deUNSPECIFIED
Albu-Schäffer, Alin OlimpiuAlin.Albu-Schaeffer (at) dlr.deUNSPECIFIED
Journal or Publication Title:IEEE International Conference on Robotics and Automation ICRA
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
Keywords:Motion Planning, Deep Learning
Event Title:ICRA 2019
Event Location:Montreal
Event Type:international Conference
Event Dates:20-24 May
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Autonomous Learning Robots [SY]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Puang, En Yen
Deposited On:01 Jul 2019 10:46
Last Modified:31 Jul 2019 20:25

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.