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

Symbolic Task Compression in Structured Task Learning

Saveriano, Matteo and Seegerer, Michael and Caccavale, Riccardo and Finzi, Alberto and Lee, Dongheui (2019) Symbolic Task Compression in Structured Task Learning. In: Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019. IEEE International Conference on Robotic Computing (IRC), Italy. doi: 10.1109/IRC.2019.00033. ISBN 978-153869245-5.

[img] PDF
774kB

Abstract

Learning everyday tasks from human demonstrations requires unsupervised segmentation of seamless demonstrations, which may result in highly fragmented and widely spread symbolic representations. Since the time needed to plan the task depends on the amount of possible behaviors, it is preferable to keep the number of behaviors as low as possible. In this work, we present an approach to simplify the symbolic representation of a learned task which leads to a reduction of the number of possible behaviors. The simplification is achieved by merging sequential behaviors, i.e. behaviors which are logically sequential and act on the same object. Assuming that the task at hand is encoded in a rooted tree, the approach traverses the tree searching for sequential nodes (behaviors) to merge. Using simple rules to assign pre- and post-conditions to each node, our approach significantly reduces the number of nodes, while keeping unaltered the task flexibility and avoiding perceptual aliasing. Experiments on automatically generated and learned tasks show a significant reduction of the planning time.

Item URL in elib:https://elib.dlr.de/132906/
Document Type:Conference or Workshop Item (Lecture)
Title:Symbolic Task Compression in Structured Task Learning
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Saveriano, MatteoUNSPECIFIEDhttps://orcid.org/0000-0002-9784-3973UNSPECIFIED
Seegerer, MichaelTUMUNSPECIFIEDUNSPECIFIED
Caccavale, RiccardoUNINAUNSPECIFIEDUNSPECIFIED
Finzi, AlbertoUNINAUNSPECIFIEDUNSPECIFIED
Lee, DongheuiUNSPECIFIEDhttps://orcid.org/0000-0003-1897-7664UNSPECIFIED
Date:2019
Journal or Publication Title:Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI:10.1109/IRC.2019.00033
ISBN:978-153869245-5
Status:Published
Keywords:Symbolic Task Compression, Structured Task
Event Title:IEEE International Conference on Robotic Computing (IRC)
Event Location:Italy
Event Type:international Conference
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 - Terrestrial Assistance Robotics (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Lee, Prof. Dongheui
Deposited On:18 Dec 2019 12:31
Last Modified:21 Jul 2023 10:26

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.