Cargando…

Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection

Robotic manipulators have to constantly deal with the complex task of detecting whether a grasp is stable or, in contrast, whether the grasped object is slipping. Recognising the type of slippage—translational, rotational—and its direction is more challenging than detecting only stability, but is si...

Descripción completa

Detalles Bibliográficos
Autores principales: Zapata-Impata, Brayan S., Gil, Pablo, Torres, Fernando
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6387284/
https://www.ncbi.nlm.nih.gov/pubmed/30691197
http://dx.doi.org/10.3390/s19030523
_version_ 1783397546249420800
author Zapata-Impata, Brayan S.
Gil, Pablo
Torres, Fernando
author_facet Zapata-Impata, Brayan S.
Gil, Pablo
Torres, Fernando
author_sort Zapata-Impata, Brayan S.
collection PubMed
description Robotic manipulators have to constantly deal with the complex task of detecting whether a grasp is stable or, in contrast, whether the grasped object is slipping. Recognising the type of slippage—translational, rotational—and its direction is more challenging than detecting only stability, but is simultaneously of greater use as regards correcting the aforementioned grasping issues. In this work, we propose a learning methodology for detecting the direction of a slip (seven categories) using spatio-temporal tactile features learnt from one tactile sensor. Tactile readings are, therefore, pre-processed and fed to a ConvLSTM that learns to detect these directions with just 50 ms of data. We have extensively evaluated the performance of the system and have achieved relatively high results at the detection of the direction of slip on unseen objects with familiar properties (82.56% accuracy).
format Online
Article
Text
id pubmed-6387284
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-63872842019-02-26 Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection Zapata-Impata, Brayan S. Gil, Pablo Torres, Fernando Sensors (Basel) Article Robotic manipulators have to constantly deal with the complex task of detecting whether a grasp is stable or, in contrast, whether the grasped object is slipping. Recognising the type of slippage—translational, rotational—and its direction is more challenging than detecting only stability, but is simultaneously of greater use as regards correcting the aforementioned grasping issues. In this work, we propose a learning methodology for detecting the direction of a slip (seven categories) using spatio-temporal tactile features learnt from one tactile sensor. Tactile readings are, therefore, pre-processed and fed to a ConvLSTM that learns to detect these directions with just 50 ms of data. We have extensively evaluated the performance of the system and have achieved relatively high results at the detection of the direction of slip on unseen objects with familiar properties (82.56% accuracy). MDPI 2019-01-27 /pmc/articles/PMC6387284/ /pubmed/30691197 http://dx.doi.org/10.3390/s19030523 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zapata-Impata, Brayan S.
Gil, Pablo
Torres, Fernando
Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection
title Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection
title_full Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection
title_fullStr Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection
title_full_unstemmed Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection
title_short Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection
title_sort learning spatio temporal tactile features with a convlstm for the direction of slip detection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6387284/
https://www.ncbi.nlm.nih.gov/pubmed/30691197
http://dx.doi.org/10.3390/s19030523
work_keys_str_mv AT zapataimpatabrayans learningspatiotemporaltactilefeatureswithaconvlstmforthedirectionofslipdetection
AT gilpablo learningspatiotemporaltactilefeatureswithaconvlstmforthedirectionofslipdetection
AT torresfernando learningspatiotemporaltactilefeatureswithaconvlstmforthedirectionofslipdetection