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

Material Classification through Knocking and Grasping by Learning of Structure-Borne Sound under Changing Acoustic Conditions

Neumann, Michael und Nottensteiner, Korbinian und Kossyk, Ingo und Marton, Zoltan-Csaba (2018) Material Classification through Knocking and Grasping by Learning of Structure-Borne Sound under Changing Acoustic Conditions. In: IEEE International Conference on Automation Science and Engineering. 14th IEEE International Conference on Automation Science and Engineering (CASE 2018), 2018-08-20 - 2018-08-24, Munich. doi: 10.1109/COASE.2018.8560527. ISBN 978-1-5386-3593-3. ISSN 2161-8089.

[img] PDF - Nur DLR-intern zugänglich
4MB

Offizielle URL: https://ieeexplore.ieee.org/document/8560527

Kurzfassung

Structure-borne sound is an interesting sensory modality for inferring contact information in robotics due to comparably cheaply available sensor hardware, the possibility to integrate it into existing systems with little effort, and due to the richness of information in the acquired signals. In this work we investigate whether its is feasible to fit a robotic system with piezo acoustics sensorics in order to infer on properties about objects in the workspace of the robot during contact events. In contrast to existing works regarding object and material identification by evaluating sound the challenge in our experimental setup is that the sensor is integrated in the structure of the robot, hence, the measured audio signal are not only governed by the acoustic properties of the objects we try to identify but are also strongly influenced by the changing resonance properties of the robot due to its kinematic configuration and the ego-noise during operation. Therefore, we investigate whether it is possible to learn a classifier that is invariant and robust to these configuration dependent changes in the acquired audio signals. We exemplarily show the feasibility of this approach for contact inference in a material classification experiment and compare the performance of a deep learning classifier to several baseline machine learning methods. We found that a representation learning approach using a deep neural network shows the highest invariance to the changing acoustics properties and outperforms the baseline methods in our experiments. The results encourage the further investigation of the uses of structure-borne sound in robotic applications.

elib-URL des Eintrags:https://elib.dlr.de/124135/
Dokumentart:Konferenzbeitrag (Vortrag)
Titel:Material Classification through Knocking and Grasping by Learning of Structure-Borne Sound under Changing Acoustic Conditions
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Neumann, MichaelNICHT SPEZIFIZIERTNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Nottensteiner, Korbiniankorbinian.nottensteiner (at) dlr.dehttps://orcid.org/0000-0002-6016-6235NICHT SPEZIFIZIERT
Kossyk, IngoIngo.Kossyk (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Marton, Zoltan-CsabaZoltan.Marton (at) dlr.dehttps://orcid.org/0000-0002-3035-493XNICHT SPEZIFIZIERT
Datum:2018
Erschienen in:IEEE International Conference on Automation Science and Engineering
Referierte Publikation:Ja
Open Access:Nein
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Nein
DOI:10.1109/COASE.2018.8560527
ISSN:2161-8089
ISBN:978-1-5386-3593-3
Status:veröffentlicht
Stichwörter:material classification; deep learning; structure-borne sound; knocking; grasping; perception; robotic systems; variational auto-encoder
Veranstaltungstitel:14th IEEE International Conference on Automation Science and Engineering (CASE 2018)
Veranstaltungsort:Munich
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:20 August 2018
Veranstaltungsende:24 August 2018
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Technik für Raumfahrtsysteme
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R SY - Technik für Raumfahrtsysteme
DLR - Teilgebiet (Projekt, Vorhaben):R - Vorhaben Intelligente Mobilität (alt)
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Robotik und Mechatronik (ab 2013)
Hinterlegt von: Nottensteiner, Korbinian
Hinterlegt am:03 Dez 2018 16:33
Letzte Änderung:24 Apr 2024 20:28

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.