Learning efficient haptic shape exploration with a rigid tactile sensor array
Fleer S, Moringen A, Klatzky RL, Ritter H (2020)
PLOS ONE 15(1): e0226880.
Zeitschriftenaufsatz
| Veröffentlicht | Englisch
Download
journal.pone.0226880.fleer.pdf
2.99 MB
Autor*in
Einrichtung
Abstract / Bemerkung
Haptic exploration is a key skill for both robots and humans to discriminate and handle unknown objects or to recognize familiar objects. Its active nature is evident in humans who from early on reliably acquire sophisticated sensory-motor capabilities for active exploratory touch and directed manual exploration that associates surfaces and object properties with their spatial locations. This is in stark contrast to robotics. In this field, the relative lack of good real-world interaction models—along with very restricted sensors and a scarcity of suitable training data to leverage machine learning methods—has so far rendered haptic exploration a largely underdeveloped skill. In robot vision however, deep learning approaches and an abundance of available training data have triggered huge advances. In the present work, we connect recent advances in recurrent models of visual attention with previous insights about the organisation of human haptic search behavior, exploratory procedures and haptic glances for a novel architecture that learns a generative model of haptic exploration in a simulated three-dimensional environment. This environment contains a set of rigid static objects representing a selection of one-dimensional local shape features embedded in a 3D space: an edge, a flat and a convex surface. The proposed algorithm simultaneously optimizes main perception-action loop components: feature extraction, integration of features over time, and the control strategy, while continuously acquiring data online. Inspired by the Recurrent Attention Model, we formalize the target task of haptic object identification in a reinforcement learning framework and reward the learner in the case of success only. We perform a multi-module neural network training, including a feature extractor and a recurrent neural network module aiding pose control for storing and combining sequential sensory data. The resulting haptic meta-controller for the rigid 16 × 16 tactile sensor array moving in a physics-driven simulation environment, called the Haptic Attention Model, performs a sequence of haptic glances, and outputs corresponding force measurements. The resulting method has been successfully tested with four different objects. It achieved results close to 100% while performing object contour exploration that has been optimized for its own sensor morphology.
Stichworte
Tactile sensation;
Robots;
Employment;
Touch;
Learning;
Machine learning algorithms;
Recurrent neural networks;
Machine learning
Erscheinungsjahr
2020
Zeitschriftentitel
PLOS ONE
Band
15
Ausgabe
1
Art.-Nr.
e0226880
Urheberrecht / Lizenzen
ISSN
1932-6203
eISSN
1932-6203
Finanzierungs-Informationen
Open-Access-Publikationskosten wurden durch die Deutsche Forschungsgemeinschaft und die Universität Bielefeld gefördert.
Page URI
https://pub.uni-bielefeld.de/record/2939850
Zitieren
Fleer S, Moringen A, Klatzky RL, Ritter H. Learning efficient haptic shape exploration with a rigid tactile sensor array. PLOS ONE. 2020;15(1): e0226880.
Fleer, S., Moringen, A., Klatzky, R. L., & Ritter, H. (2020). Learning efficient haptic shape exploration with a rigid tactile sensor array. PLOS ONE, 15(1), e0226880. doi:10.1371/journal.pone.0226880
Fleer, Sascha, Moringen, Alexandra, Klatzky, Roberta L., and Ritter, Helge. 2020. “Learning efficient haptic shape exploration with a rigid tactile sensor array”. PLOS ONE 15 (1): e0226880.
Fleer, S., Moringen, A., Klatzky, R. L., and Ritter, H. (2020). Learning efficient haptic shape exploration with a rigid tactile sensor array. PLOS ONE 15:e0226880.
Fleer, S., et al., 2020. Learning efficient haptic shape exploration with a rigid tactile sensor array. PLOS ONE, 15(1): e0226880.
S. Fleer, et al., “Learning efficient haptic shape exploration with a rigid tactile sensor array”, PLOS ONE, vol. 15, 2020, : e0226880.
Fleer, S., Moringen, A., Klatzky, R.L., Ritter, H.: Learning efficient haptic shape exploration with a rigid tactile sensor array. PLOS ONE. 15, : e0226880 (2020).
Fleer, Sascha, Moringen, Alexandra, Klatzky, Roberta L., and Ritter, Helge. “Learning efficient haptic shape exploration with a rigid tactile sensor array”. PLOS ONE 15.1 (2020): e0226880.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Name
journal.pone.0226880.fleer.pdf
2.99 MB
Access Level
Open Access
Zuletzt Hochgeladen
2020-01-13T09:46:03Z
MD5 Prüfsumme
defe05549427929172d62c2ba2244508
Daten bereitgestellt von European Bioinformatics Institute (EBI)
Zitationen in Europe PMC
Daten bereitgestellt von Europe PubMed Central.
References
Daten bereitgestellt von Europe PubMed Central.
Material in PUB:
In sonstiger Relation
Supplementary Material - Learning efficient haptic shape exploration with a rigid tactile sensor array
Fleer S, Moringen A, Klatzky RL, Ritter H (2019)
Bielefeld University.
Fleer S, Moringen A, Klatzky RL, Ritter H (2019)
Bielefeld University.
Export
Markieren/ Markierung löschen
Markierte Publikationen
Web of Science
Dieser Datensatz im Web of Science®Quellen
PMID: 31896135
PubMed | Europe PMC
arXiv: 1902.07501
Suchen in