{"id":"https://openalex.org/W3200553559","doi":"https://doi.org/10.1109/robio54168.2021.9739524","title":"A Q-learning Control Method for a Soft Robotic Arm Utilizing Training Data from a Rough Simulator","display_name":"A Q-learning Control Method for a Soft Robotic Arm Utilizing Training Data from a Rough Simulator","publication_year":2021,"publication_date":"2021-12-27","ids":{"openalex":"https://openalex.org/W3200553559","doi":"https://doi.org/10.1109/robio54168.2021.9739524","mag":"3200553559"},"language":"en","primary_location":{"id":"doi:10.1109/robio54168.2021.9739524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739524","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101446314","display_name":"Peijin Li","orcid":"https://orcid.org/0000-0001-6962-1399"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peijin Li","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089761031","display_name":"Gaotian Wang","orcid":"https://orcid.org/0009-0008-6189-3873"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaotian Wang","raw_affiliation_strings":["University of Science and Technology of China,School of Physical Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Physical Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712105","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0002-6769-0785"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Jiang","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042188753","display_name":"Yusong Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusong Jin","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046006647","display_name":"Yinghao Gan","orcid":"https://orcid.org/0000-0002-2605-263X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghao Gan","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084710341","display_name":"Xiaoping Chen","orcid":"https://orcid.org/0000-0001-8992-9286"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoping Chen","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061104105","display_name":"Jianmin Ji","orcid":"https://orcid.org/0000-0002-1515-0402"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Ji","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101446314"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.6907,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91363403,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"839","last_page":"845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9588000178337097,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11778","display_name":"Electrical and Bioimpedance Tomography","score":0.9570000171661377,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7278316617012024},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7176125049591064},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.600208044052124},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5516307950019836},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.5310896635055542},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.502617359161377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4988265037536621},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4737050235271454},{"id":"https://openalex.org/keywords/soft-robotics","display_name":"Soft robotics","score":0.44833192229270935},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42379823327064514},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41908830404281616},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.36737799644470215},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32690781354904175},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06310009956359863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278316617012024},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7176125049591064},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.600208044052124},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5516307950019836},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.5310896635055542},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.502617359161377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4988265037536621},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4737050235271454},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.44833192229270935},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42379823327064514},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41908830404281616},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.36737799644470215},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32690781354904175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06310009956359863},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio54168.2021.9739524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739524","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W199177729","https://openalex.org/W1499925623","https://openalex.org/W2032062395","https://openalex.org/W2053485789","https://openalex.org/W2056834288","https://openalex.org/W2101667962","https://openalex.org/W2337157527","https://openalex.org/W2508900105","https://openalex.org/W2592294539","https://openalex.org/W2621077460","https://openalex.org/W2739636222","https://openalex.org/W2775361682","https://openalex.org/W2967429195","https://openalex.org/W3035790680","https://openalex.org/W3125605919","https://openalex.org/W4249497594"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"It":[0],"is":[1],"challenging":[2],"to":[3,20,64],"control":[4],"a":[5,29,44,48,59],"soft":[6,50,77],"robot,":[7,51,78],"where":[8],"reinforcement":[9,25],"learning":[10,26],"methods":[11,27],"have":[12],"been":[13],"applied":[14,63],"with":[15],"promising":[16],"results.":[17],"However,":[18],"due":[19],"the":[21,66,69,73,89,98,101],"poor":[22],"sample":[23],"efficiency,":[24],"require":[28],"large":[30],"collection":[31],"of":[32,68,91,100],"training":[33,103],"data,":[34,104],"which":[35,53],"limits":[36],"their":[37],"applications.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"Q-learning":[45],"controller":[46],"for":[47],"physical":[49],"in":[52],"pre-trained":[54,92],"models":[55,93],"using":[56],"data":[57],"from":[58],"rough":[60],"simulator":[61],"are":[62],"improve":[65,108],"performance":[67],"controller.":[70],"We":[71],"implement":[72],"method":[74],"on":[75],"our":[76],"i.e.,":[79],"Honeycomb":[80],"Pneumatic":[81],"Network":[82],"(HPN)":[83],"arm.":[84],"The":[85],"experiments":[86],"show":[87],"that":[88],"usage":[90],"can":[94],"not":[95],"only":[96],"reduce":[97],"amount":[99],"real-world":[102],"but":[105],"also":[106],"greatly":[107],"its":[109],"accuracy":[110],"and":[111],"convergence":[112],"rate.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}