{"created":"2023-06-20T13:22:52.666979+00:00","id":3588,"links":{},"metadata":{"_buckets":{"deposit":"1fee7963-df26-4859-85ac-5330fd1d147e"},"_deposit":{"created_by":21,"id":"3588","owners":[21],"pid":{"revision_id":0,"type":"depid","value":"3588"},"status":"published"},"_oai":{"id":"oai:ir.soken.ac.jp:00003588","sets":["2:429:19"]},"author_link":["1457","1459","1458"],"item_1_creator_2":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"奥野, 敬丞"}],"nameIdentifiers":[{}]}]},"item_1_creator_3":{"attribute_name":"フリガナ","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"オクノ, ケイスケ"}],"nameIdentifiers":[{}]}]},"item_1_date_granted_11":{"attribute_name":"学位授与年月日","attribute_value_mlt":[{"subitem_dategranted":"2012-09-28"}]},"item_1_degree_grantor_5":{"attribute_name":"学位授与機関","attribute_value_mlt":[{"subitem_degreegrantor":[{"subitem_degreegrantor_name":"総合研究大学院大学"}]}]},"item_1_degree_name_6":{"attribute_name":"学位名","attribute_value_mlt":[{"subitem_degreename":"博士（情報学）"}]},"item_1_description_12":{"attribute_name":"要旨","attribute_value_mlt":[{"subitem_description":"This paper describes a stochastic framework for intelligent humanoid\r\nrobots, which can cooperate and interact with humans through integra-\r\ntion of symbolic expressions and sensorimotor patterns. The research is\r\ndivided into 4 steps. Contributions of the each research step are: 1) an\r\nestimation method of sensorimotor patterns of others without having pre-\r\ndefined user speciffic model in advance through interaction between self\r\nand other, 2) a method to dynamically modify displaying motion pat-\r\nterns and to bind the motions with symbol expressions according to per-\r\nformance of human-learners, in order for conveying slight differences in\r\nmotions, where robotic system coaches humans motions, 3) analysis and\r\nmodeling of human-coaches' use of motions and symbolic expressions how\r\nthey change them dynamically according to learners performances, and\r\n4) demonstration of the feasibility of the robotic motion coaching system,\r\nwhich integrated the methods proposed in step 1) and 2), and the models\r\ngained in step 3), through experiments of actual sport coaching tasks for\r\nbeginners resulted in improvements in motion learning.\r\nIn the Chapter 1, The main stream of robotics researches are introduced\r\nas improvement in individual physical ability. Then, importance of in-\r\ntelligence of binding symbol expressions and unobservable sensorimotor\r\npatterns, and intelligence to estimate the sensorimotor patterns from ob-\r\nservable motions are discussed from interaction point of view.\r\nIn the Chapter 2, related works are introduced in various fields such\r\nas Robotics, Conversation Analysis, Human-Agent Interaction, Skill and\r\nSports Science, and Anticipation of Intention of Others from neuroscience\r\nand cognitive psychology point of view. Then, the chapter addresses chal-\r\nlenges from the perspective of required functions for the research. After\r\nthe discussion of the approach for the resolution method, the Proto-symbol\r\nSpace method is introduced as a basic tool for the proposed methods.\r\nThe Chapter 3 describes an estimation method of sensorimotor patterns\r\nof others from motion observation.\r\nAn approach is to bridge sensorimotor experience, or the Proto-symbol\r\nSpaces, between the self and the other. The sensorimotor experience for\r\neach are represented by the Proto-symbol Spaces for each in the research.\r\nThis approach would result in estimation error due to physical condition\r\ndiffierence between the self and the other. To clear this problem, a method\r\nis proposed in order for adaptive acquisition of Proto-symbol Space of\r\nother by sharing motion patterns and using open questions asking the\r\nothers' sensing status described by symbols. Simulation demonstrates\r\nthat it is possible to estimate sensorimotor patterns of others with 10-\r\n20% errors, even when estimation target motions are not in database.\r\nIn the second half of the chapter, I discusses about a method to estimate\r\nothers' symbol conversion strategy from sensor patterns. The method uses\r\nclosed questions asking comparative evaluation of sets of shared motions.\r\nThe simulation demonstrates that the method can estimate the symbol\r\nconversion strategy properly by sharing prepared sets of motions and using\r\nthe closed questions.\r\nThe Chapter 4 describes a proposing method for dynamic modification\r\nof motion demonstration and for binding the motions with symbol ex-\r\npressions according to performance of human-learners. This method can\r\nconvey slight diffierences between learning target motions demonstrated by\r\na coach and motions performed by learners. Feasibility of the method is\r\ndemonstrated through experiments of actual sport coaching tasks for be-\r\nginners by using a robotic coaching system. The robotic system coaches\r\nhuman-learners tennis forehand swing, by using emphatic motions and\r\nadverbial expressions generated from the proposing method. The experi-\r\nments resulted in improvements in motion learning. However, it was not\r\npossible to confirm whether either emphatic motions and/or adverbial\r\nexpressions is a contribution factor or not.\r\nIn the Chapter 5, I discuss about experiments for modeling how human-\r\ncoaches use emphatic motions and adverbial expressions. In the experi-\r\nments, human-coaches were asked to coach a robot-learner tennis forehand\r\nswing, by using the emphatic motions and adverbial expressions. Analysis\r\nof the results leads to models; two Adverbial Expression Use Models and\r\ntwo Emphatic Motion Use Models.\r\nIn the Chapter 6, I attempt to integrate the methods proposed in Chapter\r\n3 and 4, and the models obtained in Chapter 5. At first, I discuss about\r\nintegration of the robotic motion coaching system from Chapter 4 and\r\nthe models gained from Chapter 5. I then discuss a possible integration\r\nof the method to estimate sensorimotor patterns from the Chapter 3, the\r\nrobotic motion coaching system from Chapter 4, and the models gained\r\nfrom Chapter 5.\r\nI demonstrated the feasibility of the robotic motion coaching system inte-\r\ngrated with one of the EMU-Model and one of the AEU-Model, by experi-\r\nments of a tennis forehand swing coaching task for beginners. I confirmed\r\nthat the EMU-Model and the AEU-Model contribute to improvement in\r\nmotion learning. It is demonstrated that value output by the EMU-Model\r\nis a contribution factor by a statistic analysis. I also found there is an\r\nimprovement in motion learning when using the AEU-Models. However,\r\neven though I found positive contribution of the adverbial expressions for\r\nthe improvement in motion learning, it is not able to decide whether the\r\nadverbial expressions chosen by using the AEU-Model is a contribution\r\nfactor or not.\r\nThe thesis is then concluded in the Chapter 7.","subitem_description_type":"Other"}]},"item_1_description_7":{"attribute_name":"学位記番号","attribute_value_mlt":[{"subitem_description":"総研大甲第1555号","subitem_description_type":"Other"}]},"item_1_select_14":{"attribute_name":"所蔵","attribute_value_mlt":[{"subitem_select_item":"有"}]},"item_1_select_8":{"attribute_name":"研究科","attribute_value_mlt":[{"subitem_select_item":"複合科学研究科"}]},"item_1_select_9":{"attribute_name":"専攻","attribute_value_mlt":[{"subitem_select_item":"17 情報学専攻"}]},"item_1_text_10":{"attribute_name":"学位授与年度","attribute_value_mlt":[{"subitem_text_value":"2012"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"OKUNO, Keisuke","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2016-02-17"}],"displaytype":"simple","filename":"甲1555_要旨.pdf","filesize":[{"value":"341.6 kB"}],"format":"application/pdf","licensetype":"license_11","mimetype":"application/pdf","url":{"label":"要旨・審査要旨","url":"https://ir.soken.ac.jp/record/3588/files/甲1555_要旨.pdf"},"version_id":"1b8729a1-fe9a-4078-838b-ee3dc78153b0"},{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2016-02-17"}],"displaytype":"simple","filename":"甲1555_本文.pdf","filesize":[{"value":"5.2 MB"}],"format":"application/pdf","licensetype":"license_11","mimetype":"application/pdf","url":{"label":"本文","url":"https://ir.soken.ac.jp/record/3588/files/甲1555_本文.pdf"},"version_id":"92b0d36a-e79c-46d2-a567-411a59161d29"}]},"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":"thesis","resourceuri":"http://purl.org/coar/resource_type/c_46ec"}]},"item_title":"Cooperation and Interaction between Human and Humanoid Robots through Integration of Symbolic Expressions and Sensorimotor Patterns","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Cooperation and Interaction between Human and Humanoid Robots through Integration of Symbolic Expressions and Sensorimotor Patterns"},{"subitem_title":"Cooperation and Interaction between Human and Humanoid Robots through Integration of Symbolic Expressions and Sensorimotor Patterns","subitem_title_language":"en"}]},"item_type_id":"1","owner":"21","path":["19"],"pubdate":{"attribute_name":"公開日","attribute_value":"2013-06-12"},"publish_date":"2013-06-12","publish_status":"0","recid":"3588","relation_version_is_last":true,"title":["Cooperation and Interaction between Human and Humanoid Robots through Integration of Symbolic Expressions and Sensorimotor Patterns"],"weko_creator_id":"21","weko_shared_id":-1},"updated":"2023-06-20T15:28:40.419030+00:00"}