WEKO3
アイテム
{"_buckets": {"deposit": "eb6ffcff-9ecc-40e2-9089-5b3da7c953b8"}, "_deposit": {"created_by": 27, "id": "680", "owners": [27], "pid": {"revision_id": 0, "type": "depid", "value": "680"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00000680", "sets": ["78"]}, "author_link": ["3483", "3482", "3485", "3484", "3486"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2020-04-15", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "5", "bibliographicPageEnd": "1931", "bibliographicPageStart": "1918", "bibliographicVolumeNumber": "50", "bibliographic_titles": [{}, {"bibliographic_title": "IEEE Transactions on Systems, Man, and Cybernetics: Systems", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Hwang, Jungsik"}], "nameIdentifiers": [{"nameIdentifier": "3482", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Kim, Jinhyung"}], "nameIdentifiers": [{"nameIdentifier": "3483", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Ahmadi, Ahmadreza"}], "nameIdentifiers": [{"nameIdentifier": "3484", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Choi, Minkyu"}], "nameIdentifiers": [{"nameIdentifier": "3485", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Tani, Jun"}], "nameIdentifiers": [{"nameIdentifier": "3486", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "This paper aims to investigate how adequate cognitive functions for recognizing, predicting, and generating a variety of actions can be developed through iterative learning of action-caused dynamic perceptual patterns. Particularly, we examined the capabilities of mental simulation of one\u0027s own actions as well as the inference of others\u0027 intention because they play a crucial role, especially in social cognition. We propose a dynamic neural network model based on predictive coding which can generate and recognize dynamic visuo-proprioceptive patterns. The proposed model was examined by conducting a set of robotic simulation experiments in which a robot was trained to imitate visually perceived gesture patterns of human subjects in a simulation environment. The experimental results showed that the proposed model was able to develop a predictive model of imitative interaction through iterative learning of large-scale spatio-temporal patterns in visuo-proprioceptive input streams. Also, the experiment verified that the model was able to generate mental imagery of dynamic visuo-proprioceptive patterns without feeding the external inputs. Furthermore, the model was able to recognize the intention of others by minimizing prediction error in the observations of the others\u0027 action patterns in an online manner. These findings suggest that the error minimization principle in predictive coding could provide a primal account for the mirror neuron functions for generating actions as well as recognizing those generated by others in a social cognitive context.", "subitem_description_type": "Other"}]}, "item_10001_publisher_8": {"attribute_name": "Publisher", "attribute_value_mlt": [{"subitem_publisher": "IEEE"}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:doi/10.1109/TSMC.2018.2791984", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_17": {"attribute_name": "Related site", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://ieeexplore.ieee.org/document/8276651/", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works."}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "2168-2216", "subitem_source_identifier_type": "ISSN"}, {"subitem_source_identifier": "2168-2232", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_version_type_20": {"attribute_name": "Author\u0027s flag", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_ab4af688f83e57aa", "subitem_version_type": "AM"}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2022-04-15"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "HWANG_SMC_woHeader.pdf", "filesize": [{"value": "1.7 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1700000.0, "url": {"label": "HWANG_SMC_woHeader", "url": "https://oist.repo.nii.ac.jp/record/680/files/HWANG_SMC_woHeader.pdf"}, "version_id": "340f0a48-da61-479c-9709-a26c3a74ea07"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Dealing With Large-Scale Spatio-Temporal Patterns in Imitative Interaction Between a Robot and a Human by Using the Predictive Coding Framework", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Dealing With Large-Scale Spatio-Temporal Patterns in Imitative Interaction Between a Robot and a Human by Using the Predictive Coding Framework", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "27", "path": ["78"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/680", "pubdate": {"attribute_name": "公開日", "attribute_value": "2020-02-01"}, "publish_date": "2020-02-01", "publish_status": "0", "recid": "680", "relation": {}, "relation_version_is_last": true, "title": ["Dealing With Large-Scale Spatio-Temporal Patterns in Imitative Interaction Between a Robot and a Human by Using the Predictive Coding Framework"], "weko_shared_id": 27}
Dealing With Large-Scale Spatio-Temporal Patterns in Imitative Interaction Between a Robot and a Human by Using the Predictive Coding Framework
https://oist.repo.nii.ac.jp/records/680
https://oist.repo.nii.ac.jp/records/6806dc463fd-ef25-415e-a5f5-a70b598450b0
名前 / ファイル | ライセンス | アクション |
---|---|---|
HWANG_SMC_woHeader (1.7 MB)
|
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2020-02-01 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Dealing With Large-Scale Spatio-Temporal Patterns in Imitative Interaction Between a Robot and a Human by Using the Predictive Coding Framework | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | journal article | |||||
著者(英) |
Hwang, Jungsik
× Hwang, Jungsik× Kim, Jinhyung× Ahmadi, Ahmadreza× Choi, Minkyu× Tani, Jun |
|||||
書誌情報 |
en : IEEE Transactions on Systems, Man, and Cybernetics: Systems 巻 50, 号 5, p. 1918-1931, 発行日 2020-04-15 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | This paper aims to investigate how adequate cognitive functions for recognizing, predicting, and generating a variety of actions can be developed through iterative learning of action-caused dynamic perceptual patterns. Particularly, we examined the capabilities of mental simulation of one's own actions as well as the inference of others' intention because they play a crucial role, especially in social cognition. We propose a dynamic neural network model based on predictive coding which can generate and recognize dynamic visuo-proprioceptive patterns. The proposed model was examined by conducting a set of robotic simulation experiments in which a robot was trained to imitate visually perceived gesture patterns of human subjects in a simulation environment. The experimental results showed that the proposed model was able to develop a predictive model of imitative interaction through iterative learning of large-scale spatio-temporal patterns in visuo-proprioceptive input streams. Also, the experiment verified that the model was able to generate mental imagery of dynamic visuo-proprioceptive patterns without feeding the external inputs. Furthermore, the model was able to recognize the intention of others by minimizing prediction error in the observations of the others' action patterns in an online manner. These findings suggest that the error minimization principle in predictive coding could provide a primal account for the mirror neuron functions for generating actions as well as recognizing those generated by others in a social cognitive context. | |||||
出版者 | ||||||
出版者 | IEEE | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 2168-2216 | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 2168-2232 | |||||
DOI | ||||||
関連タイプ | isVersionOf | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.1109/TSMC.2018.2791984 | |||||
権利 | ||||||
権利情報 | © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://ieeexplore.ieee.org/document/8276651/ | |||||
著者版フラグ | ||||||
出版タイプ | AM | |||||
出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa |