Behavior acquisition method based on embodiment for vision-based agent
Identifieur interne : 007417 ( Main/Exploration ); précédent : 007416; suivant : 007418Behavior acquisition method based on embodiment for vision-based agent
Auteurs : Kazunori Terada [Japon] ; Takayuki Nakamura [Japon] ; Hideaki Takeda [Japon]Source :
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Intelligence artificielle, Philosophie.
English descriptors
- KwdEn :
Abstract
A method for behavior acquisition that considers embodiment by associating tactile information to visual input is described. An agent that acts in the physical world always suffers constraints derived from embodiment. On the other hand, embodiment plays a very important role in the formation of visual function. Philosophical and clinical medicine's findings assert that vision does not function without learning through experiences of haptic motion. In this paper we argue the relation among vision, embodiment, and behavior. We developed a method for behavior acquisition through associating vision and tactile sensor. We performed experiments of obstacle avoidance using a computer simulation and a real agent to test the validity of our method.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 001060
- to stream PascalFrancis, to step Curation: 000449
- to stream PascalFrancis, to step Checkpoint: 001029
- to stream Main, to step Merge: 007969
- to stream Main, to step Curation: 007417
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Behavior acquisition method based on embodiment for vision-based agent</title><author><name sortKey="Terada, Kazunori" sort="Terada, Kazunori" uniqKey="Terada K" first="Kazunori" last="Terada">Kazunori Terada</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Dept. of Information Science, Gifu University</s1><s2>1-1 Yanagido, Gifu, 501-1193</s2><s3>JPN</s3><sZ>1 aut.</sZ></inist:fA14><country>Japon</country><wicri:noRegion>1-1 Yanagido, Gifu, 501-1193</wicri:noRegion></affiliation></author><author><name sortKey="Nakamura, Takayuki" sort="Nakamura, Takayuki" uniqKey="Nakamura T" first="Takayuki" last="Nakamura">Takayuki Nakamura</name><affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Dept. of Computer & Communication Science</s1><s2>Sakaetani 930, Wakayama, 640-8510</s2><s3>JPN</s3><sZ>2 aut.</sZ></inist:fA14><country>Japon</country><wicri:noRegion>Dept. of Computer & Communication Science</wicri:noRegion></affiliation></author><author><name sortKey="Takeda, Hideaki" sort="Takeda, Hideaki" uniqKey="Takeda H" first="Hideaki" last="Takeda">Hideaki Takeda</name><affiliation wicri:level="1"><inist:fA14 i1="03"><s1>National Institute of Informatics, 2-1-2 Hitotsubashi</s1><s2>Chiyoda-ku, Tokyo, 101-8430</s2><s3>JPN</s3><sZ>3 aut.</sZ></inist:fA14><country>Japon</country><wicri:noRegion>Chiyoda-ku, Tokyo, 101-8430</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">04-0194503</idno><date when="2002">2002</date><idno type="stanalyst">PASCAL 04-0194503 INIST</idno><idno type="RBID">Pascal:04-0194503</idno><idno type="wicri:Area/PascalFrancis/Corpus">001060</idno><idno type="wicri:Area/PascalFrancis/Curation">000449</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">001029</idno><idno type="wicri:Area/Main/Merge">007969</idno><idno type="wicri:Area/Main/Curation">007417</idno><idno type="wicri:Area/Main/Exploration">007417</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Behavior acquisition method based on embodiment for vision-based agent</title><author><name sortKey="Terada, Kazunori" sort="Terada, Kazunori" uniqKey="Terada K" first="Kazunori" last="Terada">Kazunori Terada</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Dept. of Information Science, Gifu University</s1><s2>1-1 Yanagido, Gifu, 501-1193</s2><s3>JPN</s3><sZ>1 aut.</sZ></inist:fA14><country>Japon</country><wicri:noRegion>1-1 Yanagido, Gifu, 501-1193</wicri:noRegion></affiliation></author><author><name sortKey="Nakamura, Takayuki" sort="Nakamura, Takayuki" uniqKey="Nakamura T" first="Takayuki" last="Nakamura">Takayuki Nakamura</name><affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Dept. of Computer & Communication Science</s1><s2>Sakaetani 930, Wakayama, 640-8510</s2><s3>JPN</s3><sZ>2 aut.</sZ></inist:fA14><country>Japon</country><wicri:noRegion>Dept. of Computer & Communication Science</wicri:noRegion></affiliation></author><author><name sortKey="Takeda, Hideaki" sort="Takeda, Hideaki" uniqKey="Takeda H" first="Hideaki" last="Takeda">Hideaki Takeda</name><affiliation wicri:level="1"><inist:fA14 i1="03"><s1>National Institute of Informatics, 2-1-2 Hitotsubashi</s1><s2>Chiyoda-ku, Tokyo, 101-8430</s2><s3>JPN</s3><sZ>3 aut.</sZ></inist:fA14><country>Japon</country><wicri:noRegion>Chiyoda-ku, Tokyo, 101-8430</wicri:noRegion></affiliation></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Artificial intelligence</term><term>Collision avoidance</term><term>Hand</term><term>Medical application</term><term>Numerical simulation</term><term>Philosophy</term><term>System realization</term><term>Tactile sensitivity</term><term>Tactile sensor</term><term>Visual information</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Information visuelle</term><term>Application médicale</term><term>Intelligence artificielle</term><term>Réalisation système</term><term>Sensibilité tactile</term><term>Main</term><term>Philosophie</term><term>Capteur tactile</term><term>Prévention esquive collision</term><term>Simulation numérique</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Intelligence artificielle</term><term>Philosophie</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">A method for behavior acquisition that considers embodiment by associating tactile information to visual input is described. An agent that acts in the physical world always suffers constraints derived from embodiment. On the other hand, embodiment plays a very important role in the formation of visual function. Philosophical and clinical medicine's findings assert that vision does not function without learning through experiences of haptic motion. In this paper we argue the relation among vision, embodiment, and behavior. We developed a method for behavior acquisition through associating vision and tactile sensor. We performed experiments of obstacle avoidance using a computer simulation and a real agent to test the validity of our method.</div></front></TEI><affiliations><list><country><li>Japon</li></country></list><tree><country name="Japon"><noRegion><name sortKey="Terada, Kazunori" sort="Terada, Kazunori" uniqKey="Terada K" first="Kazunori" last="Terada">Kazunori Terada</name></noRegion><name sortKey="Nakamura, Takayuki" sort="Nakamura, Takayuki" uniqKey="Nakamura T" first="Takayuki" last="Nakamura">Takayuki Nakamura</name><name sortKey="Takeda, Hideaki" sort="Takeda, Hideaki" uniqKey="Takeda H" first="Hideaki" last="Takeda">Hideaki Takeda</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/HapticV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 007417 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 007417 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= HapticV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= Pascal:04-0194503
|texte= Behavior acquisition method based on embodiment for vision-based agent
}}
| This area was generated with Dilib version V0.6.23. |  |