Investigating Active Pattern Recognition in an Imitative Game View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2001-06-12

AUTHORS

Sorin Moga , Philippe Gaussier , Mathias Quoy

ABSTRACT

In imitation learning processes, the ”student” robot must be able to perceive the environment and to detect one ”teacher”. In our approach of learning by imitation, we consider that the student tries to learn the teacher trajectory (temporal pattern). In this context, we propose a neural architecture for a mobile robot which detects its teacher using the optical flow information. The detected flow is used to initiate the imitative game. The main idea consists in using a pattern recognition system in order to allow the student to continue its imitative game even if the teacher is stopped. Since the movement detection and the pattern recognition systems work in parallel, they can provide different answers with different time constant. Neural fields equations are used to merge these information and to allow a stable dynamical behavior of the robot. Moreover, the stability of the decision making allows the robot to online learn to recognize the teacher from one image to the next. More... »

PAGES

516-523

References to SciGraph publications

  • 2000-08-18. Parallelization of Neural Networks Using PVM in RECENT ADVANCES IN PARALLEL VIRTUAL MACHINE AND MESSAGE PASSING INTERFACE
  • 1977-06. Dynamics of pattern formation in lateral-inhibition type neural fields in BIOLOGICAL CYBERNETICS
  • Book

    TITLE

    Bio-Inspired Applications of Connectionism

    ISBN

    978-3-540-42237-2
    978-3-540-45723-7

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/3-540-45723-2_62

    DOI

    http://dx.doi.org/10.1007/3-540-45723-2_62

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1041296809


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Information Processing and System Research Lab", 
              "id": "https://www.grid.ac/institutes/grid.463844.9", 
              "name": [
                "ETIS / CNRS 8051A, Groupe Neurocybernetique ENSEA, 6, avenue du Ponceau, F-95014, Cergy-Pontoise, cedex, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Moga", 
            "givenName": "Sorin", 
            "id": "sg:person.010406070305.09", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010406070305.09"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Information Processing and System Research Lab", 
              "id": "https://www.grid.ac/institutes/grid.463844.9", 
              "name": [
                "ETIS / CNRS 8051A, Groupe Neurocybernetique ENSEA, 6, avenue du Ponceau, F-95014, Cergy-Pontoise, cedex, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gaussier", 
            "givenName": "Philippe", 
            "id": "sg:person.01041272554.05", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01041272554.05"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Information Processing and System Research Lab", 
              "id": "https://www.grid.ac/institutes/grid.463844.9", 
              "name": [
                "ETIS / CNRS 8051A, Groupe Neurocybernetique ENSEA, 6, avenue du Ponceau, F-95014, Cergy-Pontoise, cedex, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Quoy", 
            "givenName": "Mathias", 
            "id": "sg:person.010556353111.37", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010556353111.37"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/0921-8890(95)00049-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1005616328"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1080/088395198117596", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009321480"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45255-9_40", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029132096", 
              "https://doi.org/10.1007/3-540-45255-9_40"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45255-9_40", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029132096", 
              "https://doi.org/10.1007/3-540-45255-9_40"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00337259", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045614723", 
              "https://doi.org/10.1007/bf00337259"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00337259", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045614723", 
              "https://doi.org/10.1007/bf00337259"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2001-06-12", 
        "datePublishedReg": "2001-06-12", 
        "description": "In imitation learning processes, the \u201dstudent\u201d robot must be able to perceive the environment and to detect one \u201dteacher\u201d. In our approach of learning by imitation, we consider that the student tries to learn the teacher trajectory (temporal pattern). In this context, we propose a neural architecture for a mobile robot which detects its teacher using the optical flow information. The detected flow is used to initiate the imitative game. The main idea consists in using a pattern recognition system in order to allow the student to continue its imitative game even if the teacher is stopped. Since the movement detection and the pattern recognition systems work in parallel, they can provide different answers with different time constant. Neural fields equations are used to merge these information and to allow a stable dynamical behavior of the robot. Moreover, the stability of the decision making allows the robot to online learn to recognize the teacher from one image to the next.", 
        "editor": [
          {
            "familyName": "Mira", 
            "givenName": "Jos\u00e9", 
            "type": "Person"
          }, 
          {
            "familyName": "Prieto", 
            "givenName": "Alberto", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/3-540-45723-2_62", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-540-42237-2", 
            "978-3-540-45723-7"
          ], 
          "name": "Bio-Inspired Applications of Connectionism", 
          "type": "Book"
        }, 
        "name": "Investigating Active Pattern Recognition in an Imitative Game", 
        "pagination": "516-523", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/3-540-45723-2_62"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "c4b9e2fbcc22200f3ad0c3e48eac407693f6fe188b6469edeb500a3384ef29e5"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1041296809"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/3-540-45723-2_62", 
          "https://app.dimensions.ai/details/publication/pub.1041296809"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T05:44", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000347_0000000347/records_89801_00000001.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F3-540-45723-2_62"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/3-540-45723-2_62'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-45723-2_62'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-45723-2_62'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-45723-2_62'


     

    This table displays all metadata directly associated to this object as RDF triples.

    98 TRIPLES      23 PREDICATES      30 URIs      19 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/3-540-45723-2_62 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N29f5b957c53e4a328d5f58919fa2c527
    4 schema:citation sg:pub.10.1007/3-540-45255-9_40
    5 sg:pub.10.1007/bf00337259
    6 https://doi.org/10.1016/0921-8890(95)00049-6
    7 https://doi.org/10.1080/088395198117596
    8 schema:datePublished 2001-06-12
    9 schema:datePublishedReg 2001-06-12
    10 schema:description In imitation learning processes, the ”student” robot must be able to perceive the environment and to detect one ”teacher”. In our approach of learning by imitation, we consider that the student tries to learn the teacher trajectory (temporal pattern). In this context, we propose a neural architecture for a mobile robot which detects its teacher using the optical flow information. The detected flow is used to initiate the imitative game. The main idea consists in using a pattern recognition system in order to allow the student to continue its imitative game even if the teacher is stopped. Since the movement detection and the pattern recognition systems work in parallel, they can provide different answers with different time constant. Neural fields equations are used to merge these information and to allow a stable dynamical behavior of the robot. Moreover, the stability of the decision making allows the robot to online learn to recognize the teacher from one image to the next.
    11 schema:editor Nbf84d94dc40c460492b365abcce8e474
    12 schema:genre chapter
    13 schema:inLanguage en
    14 schema:isAccessibleForFree false
    15 schema:isPartOf N052588aeeda64e2c84aaafde3c826453
    16 schema:name Investigating Active Pattern Recognition in an Imitative Game
    17 schema:pagination 516-523
    18 schema:productId N386a6105822244a18b97dae926646bd7
    19 N46e53c6f3ad74027831e53324afd158e
    20 N7e86d42de18048b3b2274569364ace1d
    21 schema:publisher Nf577b238a6534963804aeb1f5d3f060e
    22 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041296809
    23 https://doi.org/10.1007/3-540-45723-2_62
    24 schema:sdDatePublished 2019-04-16T05:44
    25 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    26 schema:sdPublisher Na56aff11d1e44b2f90b064c15c32445f
    27 schema:url https://link.springer.com/10.1007%2F3-540-45723-2_62
    28 sgo:license sg:explorer/license/
    29 sgo:sdDataset chapters
    30 rdf:type schema:Chapter
    31 N052588aeeda64e2c84aaafde3c826453 schema:isbn 978-3-540-42237-2
    32 978-3-540-45723-7
    33 schema:name Bio-Inspired Applications of Connectionism
    34 rdf:type schema:Book
    35 N29f5b957c53e4a328d5f58919fa2c527 rdf:first sg:person.010406070305.09
    36 rdf:rest N48e9542e85e34f6e8330f087cfac5a4d
    37 N386a6105822244a18b97dae926646bd7 schema:name dimensions_id
    38 schema:value pub.1041296809
    39 rdf:type schema:PropertyValue
    40 N40aa35d73728421d9755061f9e6b786a rdf:first N487ffb59d5a04f30b771fd0296fa3437
    41 rdf:rest rdf:nil
    42 N46e53c6f3ad74027831e53324afd158e schema:name doi
    43 schema:value 10.1007/3-540-45723-2_62
    44 rdf:type schema:PropertyValue
    45 N487ffb59d5a04f30b771fd0296fa3437 schema:familyName Prieto
    46 schema:givenName Alberto
    47 rdf:type schema:Person
    48 N48e9542e85e34f6e8330f087cfac5a4d rdf:first sg:person.01041272554.05
    49 rdf:rest N8c0557c70bec4fceb0bca0f2e22935e0
    50 N7e86d42de18048b3b2274569364ace1d schema:name readcube_id
    51 schema:value c4b9e2fbcc22200f3ad0c3e48eac407693f6fe188b6469edeb500a3384ef29e5
    52 rdf:type schema:PropertyValue
    53 N89c23ad07df647dbb5a6ccb13ca23cb4 schema:familyName Mira
    54 schema:givenName José
    55 rdf:type schema:Person
    56 N8c0557c70bec4fceb0bca0f2e22935e0 rdf:first sg:person.010556353111.37
    57 rdf:rest rdf:nil
    58 Na56aff11d1e44b2f90b064c15c32445f schema:name Springer Nature - SN SciGraph project
    59 rdf:type schema:Organization
    60 Nbf84d94dc40c460492b365abcce8e474 rdf:first N89c23ad07df647dbb5a6ccb13ca23cb4
    61 rdf:rest N40aa35d73728421d9755061f9e6b786a
    62 Nf577b238a6534963804aeb1f5d3f060e schema:location Berlin, Heidelberg
    63 schema:name Springer Berlin Heidelberg
    64 rdf:type schema:Organisation
    65 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    66 schema:name Information and Computing Sciences
    67 rdf:type schema:DefinedTerm
    68 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    69 schema:name Artificial Intelligence and Image Processing
    70 rdf:type schema:DefinedTerm
    71 sg:person.010406070305.09 schema:affiliation https://www.grid.ac/institutes/grid.463844.9
    72 schema:familyName Moga
    73 schema:givenName Sorin
    74 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010406070305.09
    75 rdf:type schema:Person
    76 sg:person.01041272554.05 schema:affiliation https://www.grid.ac/institutes/grid.463844.9
    77 schema:familyName Gaussier
    78 schema:givenName Philippe
    79 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01041272554.05
    80 rdf:type schema:Person
    81 sg:person.010556353111.37 schema:affiliation https://www.grid.ac/institutes/grid.463844.9
    82 schema:familyName Quoy
    83 schema:givenName Mathias
    84 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010556353111.37
    85 rdf:type schema:Person
    86 sg:pub.10.1007/3-540-45255-9_40 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029132096
    87 https://doi.org/10.1007/3-540-45255-9_40
    88 rdf:type schema:CreativeWork
    89 sg:pub.10.1007/bf00337259 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045614723
    90 https://doi.org/10.1007/bf00337259
    91 rdf:type schema:CreativeWork
    92 https://doi.org/10.1016/0921-8890(95)00049-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005616328
    93 rdf:type schema:CreativeWork
    94 https://doi.org/10.1080/088395198117596 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009321480
    95 rdf:type schema:CreativeWork
    96 https://www.grid.ac/institutes/grid.463844.9 schema:alternateName Information Processing and System Research Lab
    97 schema:name ETIS / CNRS 8051A, Groupe Neurocybernetique ENSEA, 6, avenue du Ponceau, F-95014, Cergy-Pontoise, cedex, France
    98 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...