{"updated":"2025-01-23T03:29:03.662967+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00009257","sets":["581:582:583"]},"path":["583"],"owner":"1","recid":"9257","title":["強化学習を用いたモジュール型多脚ロボットにおける適応的移動法獲得"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-03-15"},"_buckets":{"deposit":"dcb3e4ed-f2a1-4a46-9a37-b15958a98c18"},"_deposit":{"id":"9257","pid":{"type":"depid","value":"9257","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"強化学習を用いたモジュール型多脚ロボットにおける適応的移動法獲得","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"強化学習を用いたモジュール型多脚ロボットにおける適応的移動法獲得"},{"subitem_title":"Acquisition of Adaptive Movement Strategy by Reinforcement Learning in Modular Multiple-leg Mobile Robot","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般論文","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2009-03-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"公立はこだて未来大学大学院"},{"subitem_text_value":"公立はこだて未来大学大学院"},{"subitem_text_value":"東芝ソリューション株式会社"},{"subitem_text_value":"公立はこだて未来大学"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Future University-Hakodate","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Future University-Hakodate","subitem_text_language":"en"},{"subitem_text_value":"Toshiba Solutions Corpolation","subitem_text_language":"en"},{"subitem_text_value":"Future University-Hakodate","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/9257/files/IPSJ-JNL5003025.pdf"},"date":[{"dateType":"Available","dateValue":"2011-03-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL5003025.pdf","filesize":[{"value":"2.1 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"5ede6af4-63a6-45d4-a68d-6159e89d3e63","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2009 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"新堀航大"},{"creatorName":"兵頭, 和幸"},{"creatorName":"砂山, 享祐"},{"creatorName":"三上, 貞芳"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kodai, Shimbori","creatorNameLang":"en"},{"creatorName":"Kazuyuki, Hyodo","creatorNameLang":"en"},{"creatorName":"Kyosuke, Sunayama","creatorNameLang":"en"},{"creatorName":"Sadayoshi, Mikami","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"探査作業のような未知環境の下でロボットを用いるような研究が進められているが，ロボットのパーツの破損によって移動不可となる可能性などについては，まだ研究の余地が残されている．本論文では，ロボットが破損した場合でも，回収が困難な場合には破損部以外の利用可能なアクチュエータを用いることで移動法を再獲得するようなシステムを想定し，想定外の状況にもある程度適応できるような移動法獲得を，強化学習を用いて実現する．提案する手法では，脚形状から車輪形状などの想定外の形状へのアクチュエータモジュールの換装もある程度可能なシステムを前提とする．このような前提では新たな移動手順を広く探査することになるが，ロボットの移動機能を迅速に回復するためには，なるべく有用な行動を速く探査し利用することに重点を置く必要がある．このため，本研究では強化学習手法に対して，時間的信頼性に基づいた「行動価値の成長」と呼ぶ再探索手法を導入する．3D物理シミュレータによる6脚移動ロボットの実験により，提案する方法が比較的高速に良い候補となる移動法を獲得できていることが示されている．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Currently, intensive studies are carried out to make robots that can work under an unknown environment. It is however not so much investigated for methods to realize recovery from situations where a part of a robot has been broken. This study is to propose a configuration of a mobile robot system that is able to achieve a new movement under the situation where some of its actuators are broken and replaced by alternative ones, which may not be the same configuration as the original ones. In particular, the proposed method is designed to be able to deal with replacement of a leg-type actuator to a wheel-type actuator, which may not be considered in design-time. The proposed method is based on a Reinforcement Learning and is modified so that it can achieve rapid conversion over a wide search space. To this end, a “growth of action-value” method is proposed, which enables effective exploration of an action space based on temporal reliability of each action-value. A series of 3D simulation-based experiments are conducted, where the proposed method shows rapid conversion to a good candidate of movement patterns.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1180","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"1170","bibliographicIssueDates":{"bibliographicIssueDate":"2009-03-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"50"}]},"relation_version_is_last":true,"item_2_alternative_title_2":{"attribute_name":"その他タイトル","attribute_value_mlt":[{"subitem_alternative_title":"知識処理"}]},"weko_creator_id":"1"},"created":"2025-01-18T22:44:31.459108+00:00","id":9257,"links":{}}