{"id":"https://openalex.org/W4402215108","doi":"https://doi.org/10.1109/tase.2024.3451296","title":"Efficient Reinforcement Learning Method for Multi-Phase Robot Manipulation Skill Acquisition via Human Knowledge, Model-Based, and Model-Free Methods","display_name":"Efficient Reinforcement Learning Method for Multi-Phase Robot Manipulation Skill Acquisition via Human Knowledge, Model-Based, and Model-Free Methods","publication_year":2024,"publication_date":"2024-09-04","ids":{"openalex":"https://openalex.org/W4402215108","doi":"https://doi.org/10.1109/tase.2024.3451296"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2024.3451296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3451296","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","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/A5100381466","display_name":"Xing Liu","orcid":"https://orcid.org/0000-0002-5327-4908"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xing Liu","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-4908","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323067","display_name":"Zihao Liu","orcid":"https://orcid.org/0000-0001-5306-6626"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Liu","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016266277","display_name":"Gaozhao Wang","orcid":"https://orcid.org/0009-0003-4184-0903"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaozhao Wang","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0003-4184-0903","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083493899","display_name":"Zhengxiong Liu","orcid":"https://orcid.org/0000-0002-9427-4066"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxiong Liu","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-9427-4066","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091127758","display_name":"Panfeng Huang","orcid":"https://orcid.org/0000-0002-5132-9602"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panfeng Huang","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-5132-9602","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100381466"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":2.9802,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92246135,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"6643","last_page":"6652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7804999947547913,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7804999947547913,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.6922000050544739,"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/T10763","display_name":"Digital Transformation in Industry","score":0.6392999887466431,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6962822675704956},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6723197102546692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5801815390586853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5085872411727905},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.47359564900398254},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4730728566646576},{"id":"https://openalex.org/keywords/robot-kinematics","display_name":"Robot kinematics","score":0.4197445809841156},{"id":"https://openalex.org/keywords/dreyfus-model-of-skill-acquisition","display_name":"Dreyfus model of skill acquisition","score":0.41053518652915955},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.39948469400405884},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3712708652019501},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.27051448822021484}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6962822675704956},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6723197102546692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5801815390586853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085872411727905},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.47359564900398254},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4730728566646576},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.4197445809841156},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.41053518652915955},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.39948469400405884},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3712708652019501},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.27051448822021484},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2024.3451296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3451296","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5198280451","display_name":null,"funder_award_id":"62103334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7483363023","display_name":null,"funder_award_id":"92370123","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7676250215","display_name":null,"funder_award_id":"62273280","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":28,"referenced_works":["https://openalex.org/W1539716820","https://openalex.org/W1977655452","https://openalex.org/W2060914855","https://openalex.org/W2559835615","https://openalex.org/W2793264449","https://openalex.org/W2877093712","https://openalex.org/W2963411833","https://openalex.org/W2967717386","https://openalex.org/W2997896361","https://openalex.org/W3033119093","https://openalex.org/W3035497536","https://openalex.org/W3037429136","https://openalex.org/W3039116038","https://openalex.org/W3109467707","https://openalex.org/W3134939669","https://openalex.org/W3206820790","https://openalex.org/W4205513846","https://openalex.org/W4207069129","https://openalex.org/W4210939259","https://openalex.org/W4213053250","https://openalex.org/W4283788634","https://openalex.org/W4384519313","https://openalex.org/W4385430467","https://openalex.org/W6680657880","https://openalex.org/W6749061090","https://openalex.org/W6764125455","https://openalex.org/W6858881048","https://openalex.org/W6867621267"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W3119422923"],"abstract_inverted_index":{"A":[0],"novel":[1],"efficient":[2,224],"reinforcement":[3,238],"learning":[4,227,239,250],"paradigm":[5],"combining":[6],"human":[7,37,56,233],"knowledge,":[8,234],"model-based":[9,145,235],"and":[10,33,49,89,158,200,236],"model-free":[11,123,237],"methods":[12,240],"is":[13,39,58,101,135,147,178,202],"presented":[14,59,166],"for":[15,103,173,206,228],"optimal":[16],"robot":[17,23,47,68,72,176],"manipulation":[18,24,50,69,73,139,188,192,225,230],"control":[19],"during":[20,45,117],"complex":[21,187,229],"multi-phase":[22,67],"tasks,":[25],"e.g.,":[26],"the":[27,43,62,66,97,113,118,121,126,138,144,156,162,165,174,180,215,245,248],"peg-in-hole":[28],"tasks":[29,74,193,231],"with":[30,55,94,109,129,141],"tight":[31],"fit":[32],"nut-and-bolt":[34],"assembly.":[35],"Firstly,":[36],"demonstration":[38],"conducted":[40],"to":[41,60,169,252],"collect":[42],"data":[44],"successful":[46],"manipulation,":[48],"phase":[51,93,108,140],"estimation":[52],"method":[53,100,134,146,205],"integrating":[54],"knowledge":[57],"obtain":[61],"higher-level":[63],"planning":[64,99],"of":[65,82,115,150,164,186,210,217,247],"tasks.":[70],"Typical":[71],"can":[75,194],"usually":[76],"be":[77,195],"decomposed":[78,196],"into":[79,197],"three":[80],"types":[81],"phases,":[83],"namely":[84,125],"free":[85,95],"motion,":[86,96],"discontinuous":[87,110],"contact,":[88],"continuous":[90,142],"contact.":[91],"For":[92,107,137],"motion":[98],"utilized":[102,148],"generating":[104],"smooth":[105],"trajectory.":[106],"contact":[111],"in":[112],"axes":[114],"interest":[116],"pre-manipulation":[119],"process,":[120],"rule-based":[122],"method,":[124],"Policy":[127],"Gradients":[128],"Human-Guided":[130],"Parameter-based":[131],"Exploration":[132],"(PGHGPE)":[133],"utilized.":[136],"contacts,":[143],"because":[149],"its":[151],"higher":[152],"sample":[153],"efficiency.":[154,220],"Finally,":[155],"simulation":[157],"experimental":[159],"studies":[160],"verify":[161],"effectiveness":[163],"algorithm.":[167],"Note":[168],"Practitioners\u2014The":[170],"important":[171],"premise":[172],"future":[175],"assistants":[177],"that":[179],"robots":[181],"should":[182],"have":[183],"certain":[184],"ability":[185],"skill":[189,226,249],"learning.":[190],"Complex":[191],"multiple":[198],"stages,":[199],"HRL":[201,213],"a":[203,253],"suitable":[204],"solving":[207],"this":[208,222],"kind":[209],"problems.":[211],"However,":[212],"faces":[214],"challenge":[216],"low":[218],"computational":[219],"To":[221],"end,":[223],"via":[232],"are":[241],"presented,":[242],"which":[243],"improves":[244],"efficiency":[246],"process":[251],"practical":[254],"level.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}