{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217011","sets":["1164:2836:10841:10842"]},"path":["10842"],"owner":"44499","recid":"217011","title":["複数ポリシー切替による複雑な環境に適用可能な自律移動ロボットナビゲーション手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-03"},"_buckets":{"deposit":"8289c6d2-4b34-4c7e-b559-f75192281415"},"_deposit":{"id":"217011","pid":{"type":"depid","value":"217011","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"複数ポリシー切替による複雑な環境に適用可能な自律移動ロボットナビゲーション手法","author_link":["561352","561353"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"複数ポリシー切替による複雑な環境に適用可能な自律移動ロボットナビゲーション手法"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"IoT・ナビゲーション","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-03","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京女子大学大学院理学研究科"},{"subitem_text_value":"東京女子大学大学院理学研究科"}]},"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/217011/files/IPSJ-DPS22190027.pdf","label":"IPSJ-DPS22190027.pdf"},"date":[{"dateType":"Available","dateValue":"2024-03-03"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DPS22190027.pdf","filesize":[{"value":"1.0 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":"34"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"0599157b-70a9-4e80-9b2f-9ef4e5cb9a27","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":"天野, 加奈子"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"加藤, 由花"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10116224","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":"2188-8906","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，多様な動的環境に適用することを目的に，深層強化学習を用いた自律移動ロボットのナビゲーション手法が提案されている．しかし，学習される行動はシミュレーション環境に依存するため，現実世界に直接適用することは安全面および効率面で最適ではない場合がある．本稿では，人と空間を共有する自律移動ロボットが，人と障害物が混在する複雑な環境下において安全かつ効率的に目的地まで移動することを目的に，深層強化学習（DRL）手法を含む複数の行動決定方法を切り替えるナビゲーション手法を提案する．ここでは，新たにリセットポリシーを導入し，ロボット周辺の非占有領域の面積を用いて危険性の高い状況を判別することで，従来手法の課題である狭い環境での振動や衝突の回避を目指す．今回，深層強化学習手法単体を用いる場合と 3 種類の行動決定方法を切り替える場合においてナビゲーション実験を行い，環境中に静止障害物が存在するとき，切り替え手法の方が成功率が高いことを明らかにする．また，DRL・効率・安全の 3 つのポリシーの切り替え手法は，効率面で DRL ポリシー単体に劣ることや元々狭い環境では十分な成功率を得られないことを示す．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告マルチメディア通信と分散処理（DPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-03","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"27","bibliographicVolumeNumber":"2022-DPS-190"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217011,"updated":"2025-01-19T15:39:26.246731+00:00","links":{},"created":"2025-01-19T01:17:31.224981+00:00"}