{"id":"https://openalex.org/W4301369229","doi":"https://doi.org/10.1109/lra.2022.3196789","title":"A Reinforcement Learning Method for Motion Control With Constraints on an HPN Arm","display_name":"A Reinforcement Learning Method for Motion Control With Constraints on an HPN Arm","publication_year":2022,"publication_date":"2022-08-05","ids":{"openalex":"https://openalex.org/W4301369229","doi":"https://doi.org/10.1109/lra.2022.3196789"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3196789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3196789","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/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":["School of Data Science, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2605-263X","affiliations":[{"raw_affiliation_string":"School of Data Science, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":false,"raw_author_name":"Peijin Li","raw_affiliation_strings":["School of Computer Science, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China (USTC), Hefei, China","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":["School of Computer Science, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China (USTC), Hefei, China","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":["School of Physics, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Physics, University of Science and Technology of China (USTC), Hefei, China","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":["School of Computer Science, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China (USTC), Hefei, China","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":["School of Computer Science, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8992-9286","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China (USTC), Hefei, China","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":["School of Computer Science, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1515-0402","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6431,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.60825854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"7","issue":"4","first_page":"12006","last_page":"12013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9921000003814697,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.978600025177002,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.8914165496826172},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.7419191598892212},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6495662331581116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6040319800376892},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5585085153579712},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5486595630645752},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5440787672996521},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5412731766700745},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.529678463935852},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5085293054580688},{"id":"https://openalex.org/keywords/soft-robotics","display_name":"Soft robotics","score":0.4947070777416229},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4742801785469055},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.4293445646762848},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.42739367485046387},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4122107923030853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4094698429107666},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4029538631439209},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23511695861816406}],"concepts":[{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.8914165496826172},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.7419191598892212},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6495662331581116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6040319800376892},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5585085153579712},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5486595630645752},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5440787672996521},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5412731766700745},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.529678463935852},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5085293054580688},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.4947070777416229},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4742801785469055},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.4293445646762848},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.42739367485046387},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4122107923030853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4094698429107666},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4029538631439209},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23511695861816406},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3196789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3196789","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G5464075715","display_name":null,"funder_award_id":"61573333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1515749184","https://openalex.org/W2037867075","https://openalex.org/W2318613964","https://openalex.org/W2621077460","https://openalex.org/W2739140755","https://openalex.org/W2739636222","https://openalex.org/W2745494968","https://openalex.org/W2774695914","https://openalex.org/W2775361682","https://openalex.org/W2782435507","https://openalex.org/W2901112449","https://openalex.org/W2922829168","https://openalex.org/W2967429195","https://openalex.org/W3011120880","https://openalex.org/W3035790680","https://openalex.org/W3041885040","https://openalex.org/W3125605919","https://openalex.org/W3200553559","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W1992503747","https://openalex.org/W2371519816","https://openalex.org/W2043154226","https://openalex.org/W2369529107","https://openalex.org/W2329043542","https://openalex.org/W2109948066","https://openalex.org/W1678858522","https://openalex.org/W3195090107","https://openalex.org/W38056103","https://openalex.org/W2312533462"],"abstract_inverted_index":{"Soft":[0],"robotic":[1],"arms":[2],"have":[3,46],"shown":[4],"great":[5],"potential":[6],"toward":[7],"applications":[8],"to":[9,17,39,77,95,161],"human":[10],"daily":[11],"lives,":[12],"which":[13,123,157],"is":[14,67,75,136,198],"mainly":[15],"due":[16],"their":[18],"infinite":[19],"passive":[20],"degrees":[21],"of":[22,36,58,63],"freedom":[23],"and":[24,107],"intrinsic":[25],"safety.":[26],"There":[27],"are":[28],"tasks":[29],"in":[30,154],"lives":[31],"that":[32,45,149,195],"require":[33],"the":[34,37,51,61,64,70,82,97,117,126,130,134,142,155,159,163,174,179,186,196,202,211,214],"motion":[35,83,101],"robot":[38],"meet":[40],"some":[41],"certain":[42],"pose":[43,131,175],"constraints":[44,104,132],"not":[47],"been":[48],"implemented":[49],"through":[50,81],"soft":[52,65,118,183],"arm,":[53,184],"like":[54],"delivering":[55],"a":[56,91,114,147],"glass":[57],"water.":[59],"Because":[60],"workspace":[62,212],"arm":[66,119,127,135,164,203],"affected":[68],"by":[69],"loads":[71,106],"or":[72,169,208],"interaction,":[73],"it":[74],"difficult":[76],"implement":[78,178],"this":[79,87],"task":[80],"planning":[84],"method.":[85],"In":[86],"letter,":[88],"we":[89,145],"propose":[90],"Q-learning":[92],"based":[93,120],"approach":[94,180,197],"address":[96],"problem,":[98],"directly":[99],"achieving":[100],"control":[102],"with":[103,141,165],"under":[105,213],"interaction":[108,170],"without":[109],"planning.":[110],"We":[111,177],"first":[112],"generate":[113],"controller":[115,160],"for":[116],"on":[121,181],"Q-learning,":[122],"can":[124],"operate":[125,162],"while":[128,171],"satisfying":[129,173],"when":[133,201],"neither":[137],"loaded":[138],"nor":[139],"interacted":[140],"environment.":[143],"Then,":[144],"introduce":[146],"process":[148],"adjusts":[150],"corresponding":[151],"Q":[152],"values":[153],"controller,":[156],"allows":[158],"an":[166,205],"unknown":[167],"load":[168],"still":[172],"constraints.":[176],"our":[182],"i.e.,":[185],"Honeycomb":[187],"Pneumatic":[188],"Network":[189],"(HPN)":[190],"Arm.":[191],"The":[192],"experiments":[193],"show":[194],"effective,":[199],"even":[200,209],"reached":[204],"untrained":[206],"situation":[207],"beyond":[210],"interaction.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
