{"created":"2025-01-19T01:14:37.483582+00:00","updated":"2025-01-19T17:01:39.116651+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00213777","sets":["1164:2592:10486:10744"]},"path":["10744"],"owner":"44499","recid":"213777","title":["線形時相論理仕様を満たす監視ロボットの最適経路の有界設計法に基づく強化学習"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-11-11"},"_buckets":{"deposit":"9050a4fa-1e7e-4108-a839-caa839d139a5"},"_deposit":{"id":"213777","pid":{"type":"depid","value":"213777","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"線形時相論理仕様を満たす監視ロボットの最適経路の有界設計法に基づく強化学習","author_link":["547376","547375","547373","547374"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"線形時相論理仕様を満たす監視ロボットの最適経路の有界設計法に基づく強化学習"},{"subitem_title":"Bounded Synthesis and Reinforcement Learning based Optimal Path Planning for Surveillance Robots with LTL Specifications","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2021-11-11","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"大阪大学大学院基礎工学研究科"},{"subitem_text_value":"大阪大学大学院基礎工学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering Science, Osaka University","subitem_text_language":"en"},{"subitem_text_value":" Graduate School of Engineering Science, Osaka University","subitem_text_language":"en"}]},"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/213777/files/IPSJ-AL21185016.pdf","label":"IPSJ-AL21185016.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-AL21185016.pdf","filesize":[{"value":"1.7 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"9"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"87c0d00e-32e9-4095-bc1a-2daf70127dcf","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大浦, 稜平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"潮, 俊光"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Ryohei, Oura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Toshimitsu, Ushio","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN1009593X","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":"2188-8566","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"線形時相論理（LTL）は定性的かつ複雑な仕様を表現できる論理体系であり，複雑な制御タスクの仕様記述において近年注目されている．筆者らは，有界設計法を用いることで，確率的離散事象システムに対して LTL 仕様を満たしつつ最大許容的な制御パターンを提示するスーパバイザの強化学習法を提案している．本報告では，提案法とベイズ推定を移動ロボットの監視問題に適用し，与えた LTL 仕様を最大確率で満たしつつ，経路コストに対するリスク指標を最小化する制御方策の設計法を提案する．また，計算機シミュレーションによって本提案法に基づき正しい方策が学習されることを示す．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Linear temporal logic (LTL) is suitable for describing a complex control specification. In our previous study, for stochastic discrete event systems, we developed a bounded synthesis and reinforcement learning-based method for synthesis of supervisors that achieve maximal satisfaction probability and maximal permissiveness in the winning region. In this report, we apply the proposed method with Bayesian inference to a surveillance problem described by an LTL specification, synthesizing an optimal path that minimizes a risk factor for the cost of the transitions under the maximization of the satisfaction probability. By computer simulation, we show the effectiveness of the proposed method on the surveillance problem.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告アルゴリズム（AL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-11-11","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"16","bibliographicVolumeNumber":"2021-AL-185"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":213777,"links":{}}