Single-Grasp Object Classification and Feature Extraction with Simple Robot Hands and Tactile Sensors.
Identifieur interne : 003F51 ( Ncbi/Checkpoint ); précédent : 003F50; suivant : 003F52Single-Grasp Object Classification and Feature Extraction with Simple Robot Hands and Tactile Sensors.
Auteurs : Adam Spiers ; Minas Liarokapis ; Berk Calli ; Aaron DollarSource :
- IEEE transactions on haptics [ 2329-4051 ] ; 2016.
Abstract
Classical robotic approaches to tactile object identification often involve rigid mechanical grippers, dense sensor arrays and exploratory procedures (EPs). Though EPs are a natural method for humans to acquire object information, evidence also exists for meaningful tactile property inference from brief, non-exploratory motions (a 'haptic glance'). In this work we implement tactile object identification and feature extraction techniques on data acquired during a single, unplanned grasp with a simple, underactuated robot hand equipped with inexpensive barometric pressure sensors. Our methodology utilizes two cooperating schemes based on an advanced machine learning technique (random forests) and parametric methods that estimate object properties. The available data is limited to actuator positions (one per two link finger) and force sensors values (8 per finger). The schemes are able to work both independently and collaboratively, depending on the task scenario. When collaborating, the results of each method contribute to the other, improving the overall result in a synergistic fashion. Unlike prior work, the proposed approach does not require object exploration, re-grasping, grasp release or force modulation and works for arbitrary object start positions and orientations. Due to these factors the technique may be integrated into practical robotic grasping scenarios without adding time or manipulation overheads.
DOI: 10.1109/TOH.2016.2521378
PubMed: 26829804
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: 000118
- to stream PubMed, to step Curation: 000118
- to stream PubMed, to step Checkpoint: 000035
- to stream Ncbi, to step Merge: 003F51
- to stream Ncbi, to step Curation: 003F51
Links to Exploration step
pubmed:26829804Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Single-Grasp Object Classification and Feature Extraction with Simple Robot Hands and Tactile Sensors.</title>
<author><name sortKey="Spiers, Adam" sort="Spiers, Adam" uniqKey="Spiers A" first="Adam" last="Spiers">Adam Spiers</name>
</author>
<author><name sortKey="Liarokapis, Minas" sort="Liarokapis, Minas" uniqKey="Liarokapis M" first="Minas" last="Liarokapis">Minas Liarokapis</name>
</author>
<author><name sortKey="Calli, Berk" sort="Calli, Berk" uniqKey="Calli B" first="Berk" last="Calli">Berk Calli</name>
</author>
<author><name sortKey="Dollar, Aaron" sort="Dollar, Aaron" uniqKey="Dollar A" first="Aaron" last="Dollar">Aaron Dollar</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2016">2016</date>
<idno type="doi">10.1109/TOH.2016.2521378</idno>
<idno type="RBID">pubmed:26829804</idno>
<idno type="pmid">26829804</idno>
<idno type="wicri:Area/PubMed/Corpus">000118</idno>
<idno type="wicri:Area/PubMed/Curation">000118</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000035</idno>
<idno type="wicri:Area/Ncbi/Merge">003F51</idno>
<idno type="wicri:Area/Ncbi/Curation">003F51</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">003F51</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Single-Grasp Object Classification and Feature Extraction with Simple Robot Hands and Tactile Sensors.</title>
<author><name sortKey="Spiers, Adam" sort="Spiers, Adam" uniqKey="Spiers A" first="Adam" last="Spiers">Adam Spiers</name>
</author>
<author><name sortKey="Liarokapis, Minas" sort="Liarokapis, Minas" uniqKey="Liarokapis M" first="Minas" last="Liarokapis">Minas Liarokapis</name>
</author>
<author><name sortKey="Calli, Berk" sort="Calli, Berk" uniqKey="Calli B" first="Berk" last="Calli">Berk Calli</name>
</author>
<author><name sortKey="Dollar, Aaron" sort="Dollar, Aaron" uniqKey="Dollar A" first="Aaron" last="Dollar">Aaron Dollar</name>
</author>
</analytic>
<series><title level="j">IEEE transactions on haptics</title>
<idno type="eISSN">2329-4051</idno>
<imprint><date when="2016" type="published">2016</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Classical robotic approaches to tactile object identification often involve rigid mechanical grippers, dense sensor arrays and exploratory procedures (EPs). Though EPs are a natural method for humans to acquire object information, evidence also exists for meaningful tactile property inference from brief, non-exploratory motions (a 'haptic glance'). In this work we implement tactile object identification and feature extraction techniques on data acquired during a single, unplanned grasp with a simple, underactuated robot hand equipped with inexpensive barometric pressure sensors. Our methodology utilizes two cooperating schemes based on an advanced machine learning technique (random forests) and parametric methods that estimate object properties. The available data is limited to actuator positions (one per two link finger) and force sensors values (8 per finger). The schemes are able to work both independently and collaboratively, depending on the task scenario. When collaborating, the results of each method contribute to the other, improving the overall result in a synergistic fashion. Unlike prior work, the proposed approach does not require object exploration, re-grasping, grasp release or force modulation and works for arbitrary object start positions and orientations. Due to these factors the technique may be integrated into practical robotic grasping scenarios without adding time or manipulation overheads.</div>
</front>
</TEI>
<affiliations><list></list>
<tree><noCountry><name sortKey="Calli, Berk" sort="Calli, Berk" uniqKey="Calli B" first="Berk" last="Calli">Berk Calli</name>
<name sortKey="Dollar, Aaron" sort="Dollar, Aaron" uniqKey="Dollar A" first="Aaron" last="Dollar">Aaron Dollar</name>
<name sortKey="Liarokapis, Minas" sort="Liarokapis, Minas" uniqKey="Liarokapis M" first="Minas" last="Liarokapis">Minas Liarokapis</name>
<name sortKey="Spiers, Adam" sort="Spiers, Adam" uniqKey="Spiers A" first="Adam" last="Spiers">Adam Spiers</name>
</noCountry>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/HapticV1/Data/Ncbi/Checkpoint
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003F51 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Ncbi/Checkpoint/biblio.hfd -nk 003F51 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= HapticV1 |flux= Ncbi |étape= Checkpoint |type= RBID |clé= pubmed:26829804 |texte= Single-Grasp Object Classification and Feature Extraction with Simple Robot Hands and Tactile Sensors. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Ncbi/Checkpoint/RBID.i -Sk "pubmed:26829804" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Ncbi/Checkpoint/biblio.hfd \ | NlmPubMed2Wicri -a HapticV1
![]() | This area was generated with Dilib version V0.6.23. | ![]() |