{"created":"2025-01-19T01:22:10.681131+00:00","updated":"2025-01-19T13:49:20.725471+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00222211","sets":["1164:3865:10834:11027"]},"path":["11027"],"owner":"44499","recid":"222211","title":["強化学習を用いた運搬ロボットの通信品質保証に関する一検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-11-09"},"_buckets":{"deposit":"c91fb8fb-e97c-48f4-9952-9706d24309ec"},"_deposit":{"id":"222211","pid":{"type":"depid","value":"222211","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"強化学習を用いた運搬ロボットの通信品質保証に関する一検討","author_link":["582712","582714","582710","582713","582711","582716","582715"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"強化学習を用いた運搬ロボットの通信品質保証に関する一検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人流解析・通信","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-11-09","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"日本電信電話株式会社NTT未来ねっと研究所"},{"subitem_text_value":"日本電信電話株式会社NTT未来ねっと研究所"},{"subitem_text_value":"日本電信電話株式会社NTTアクセスサービスシステム研究所"},{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"大阪大学大学院情報科学研究科"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"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/222211/files/IPSJ-MBL22105022.pdf","label":"IPSJ-MBL22105022.pdf"},"date":[{"dateType":"Available","dateValue":"2024-11-09"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MBL22105022.pdf","filesize":[{"value":"740.7 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"35"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"c655aa8a-ce6f-4e9d-af17-836440ac1488","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"新宮, 裕章"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤橋, 卓也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"工藤, 理一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高橋, 馨子"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"村上, 友規"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"渡辺, 尚"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"猿渡, 俊介"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11851388","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8817","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"携帯電話網や無線 LAN の進化によっていつでもどこでも無線ネットワークに接続できる環境が整備されたことで，Automatic Guided Vehicle (AGV) による部品や荷物の自動搬送，無人走行車やドローンの遠隔操作などネットワークを介してロボットを制御する応用が広がっている．ネットワークを介してロボットを制御する場合，ネットワーク資源を共有している多数のロボットそれぞれに対して安定的な制御を確立するために必要な通信品質を維持することが求められる．本稿では，ロボットのタスクを考慮してネットワークの制御の最適化を実現する強化学習のフレームワーク「CoRein」を提案する．CoRein は，ロボットの操作とネットワークの設定を行動，ロボットとネットワークで取得できる情報を状態，ロボットに与えられたタスクの達成状況とネットワーク性能を加味した報酬関数を設定して，行動価値関数を Deep Neural Network (DNN) で強化学習する．計算機シミュレーションを用いて複数台のロボットが定められた経路を移動して荷物を運搬する環境で評価した結果，CoRein を用いることで各ロボットに対して十分な通信速度を保証するネットワーク設定が可能となり，各ロボットが与えられたタスクを効率よく達成できることを確認できた．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告モバイルコンピューティングとパーベイシブシステム（MBL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-11-09","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"22","bibliographicVolumeNumber":"2022-MBL-105"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":222211,"links":{}}