{"id":"https://openalex.org/W4408950019","doi":"https://doi.org/10.1108/ir-12-2024-0534","title":"Self-supervised reinforcement learning for multi-step object manipulation skills","display_name":"Self-supervised reinforcement learning for multi-step object manipulation skills","publication_year":2025,"publication_date":"2025-03-28","ids":{"openalex":"https://openalex.org/W4408950019","doi":"https://doi.org/10.1108/ir-12-2024-0534"},"language":"en","primary_location":{"id":"doi:10.1108/ir-12-2024-0534","is_oa":false,"landing_page_url":"https://doi.org/10.1108/ir-12-2024-0534","pdf_url":null,"source":{"id":"https://openalex.org/S166948985","display_name":"Industrial Robot the international journal of robotics research and application","issn_l":"0143-991X","issn":["0143-991X","1758-5791"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Industrial Robot: the international journal of robotics research and application","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":null,"display_name":"Jiaqi Wang","orcid":"https://orcid.org/0009-0006-5048-2572"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":["South China University of Technology , Guangzhou,"],"raw_orcid":"https://orcid.org/0009-0006-5048-2572","affiliations":[{"raw_affiliation_string":"South China University of Technology , Guangzhou,","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074657967","display_name":"Chuxin Chen","orcid":"https://orcid.org/0000-0002-0008-5302"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuxin Chen","raw_affiliation_strings":["South China University of Technology , Guangzhou,"],"raw_orcid":"https://orcid.org/0000-0002-0008-5302","affiliations":[{"raw_affiliation_string":"South China University of Technology , Guangzhou,","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101726800","display_name":"Jingwei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Liu","raw_affiliation_strings":["South China University of Technology , Guangzhou,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology , Guangzhou,","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026223895","display_name":"Guanglong Du","orcid":"https://orcid.org/0000-0001-9425-843X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglong Du","raw_affiliation_strings":["South China University of Technology Department of CS, , Guangzhou,"],"raw_orcid":"https://orcid.org/0000-0001-9425-843X","affiliations":[{"raw_affiliation_string":"South China University of Technology Department of CS, , Guangzhou,","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063594353","display_name":"Xiaojun Zhu","orcid":"https://orcid.org/0000-0002-9506-9005"},"institutions":[{"id":"https://openalex.org/I4210124917","display_name":"JAC Motors (China)","ror":"https://ror.org/02ztwrd91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210124917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Zhu","raw_affiliation_strings":["Jianghuai Advanced Technology Center , Hefei,"],"raw_orcid":"https://orcid.org/0000-0002-9506-9005","affiliations":[{"raw_affiliation_string":"Jianghuai Advanced Technology Center , Hefei,","institution_ids":["https://openalex.org/I4210124917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084935157","display_name":"Quanlong Guan","orcid":"https://orcid.org/0000-0001-6911-3853"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanlong Guan","raw_affiliation_strings":["Jinan University , Guangzhou,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jinan University , Guangzhou,","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063670603","display_name":"Xiaojian Qiu","orcid":"https://orcid.org/0000-0002-7761-3425"},"institutions":[{"id":"https://openalex.org/I4210110650","display_name":"Nanchang Normal University","ror":"https://ror.org/01sbpdt14","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojian Qiu","raw_affiliation_strings":["Institute for Military-Civilian Integration of Jiangxi Province , Nanchang,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Military-Civilian Integration of Jiangxi Province , Nanchang,","institution_ids":["https://openalex.org/I4210110650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0542931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"52","issue":"6","first_page":"853","last_page":"865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9918000102043152,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.945900022983551,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7213507890701294},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5134097337722778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5123218297958374},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46611908078193665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4572870135307312},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.37281981110572815},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13940384984016418}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7213507890701294},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5134097337722778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5123218297958374},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46611908078193665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4572870135307312},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37281981110572815},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13940384984016418}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/ir-12-2024-0534","is_oa":false,"landing_page_url":"https://doi.org/10.1108/ir-12-2024-0534","pdf_url":null,"source":{"id":"https://openalex.org/S166948985","display_name":"Industrial Robot the international journal of robotics research and application","issn_l":"0143-991X","issn":["0143-991X","1758-5791"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Industrial Robot: the international journal of robotics research and application","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2789539638","https://openalex.org/W3008535267","https://openalex.org/W3087094117","https://openalex.org/W3101103779","https://openalex.org/W3211352205","https://openalex.org/W4223443410","https://openalex.org/W4319301291","https://openalex.org/W4362561002","https://openalex.org/W4362672763","https://openalex.org/W4380150950","https://openalex.org/W4386967465"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Purpose":[0],"The":[1,42,120,146,162,264],"purpose":[2],"of":[3,11,34,58,65,187,251,256,267],"this":[4],"study":[5],"is":[6,19,44,123,148],"to":[7,25,30,45,67,70,125,150,157,189,197,274],"address":[8],"the":[9,17,32,91,93,100,179,195,209,254,268,280],"challenge":[10],"object":[12,101],"manipulation":[13,102,159,277],"in":[14,27,83,283],"scenarios":[15],"where":[16],"target":[18],"not":[20,227],"explicitly":[21],"defined,":[22],"requiring":[23],"robots":[24,69,166,201],"engage":[26],"efficient":[28,183],"planning":[29,77,295],"determine":[31],"sequence":[33],"actions":[35],"for":[36,133,154,261,271],"picking,":[37],"placing":[38,140],"and":[39,78,85,141,174,219,253,279,286],"positioning":[40],"objects.":[41],"aim":[43],"develop":[46,233],"a":[47,56,62,96,198,212,220,234,248],"multistep":[48,76,158,236],"skill":[49,237],"learning":[50,118,238,259],"method":[51,239],"that":[52,74,98,165,240],"integrates":[53,241],"perception":[54,242],"with":[55,80,111,216,224,243],"set":[57],"primitive":[59,135,245],"actions,":[60,246],"including":[61,247],"novel":[63,235],"action":[64,136,250],"orienting,":[66,252],"enable":[68],"perform":[71],"complex":[72,169,276],"tasks":[73],"require":[75],"interaction":[79],"various":[81,225],"objects":[82,218,226],"cluttered":[84],"unstructured":[86],"environments.":[87],"Design/methodology/approach":[88],"To":[89],"achieve":[90],"purpose,":[92],"authors":[94],"propose":[95],"pipeline":[97],"decomposes":[99],"task":[103],"into":[104],"three":[105,128],"independent":[106],"stages,":[107],"each":[108,134],"trained":[109],"end-to-end":[110,262],"raw":[112],"visual":[113],"inputs":[114],"using":[115,205],"off-policy":[116,257],"reinforcement":[117,258],"algorithms.":[119],"Q-learning":[121],"algorithm":[122],"used":[124],"simultaneously":[126],"train":[127],"fully":[129],"convolutional":[130],"neural":[131],"networks":[132],"\u2013":[137,143],"grasping,":[138],"pushing,":[139],"orienting":[142],"from":[144],"scratch.":[145],"framework":[147,269],"designed":[149],"be":[151],"modular,":[152],"allowing":[153],"easy":[155,272],"extension":[156,273],"tasks.":[160],"Findings":[161],"findings":[163],"demonstrate":[164,289],"can":[167],"learn":[168],"behaviors":[170],"through":[171],"both":[172,284],"simulated":[173,285],"real-world":[175,287],"experiments.":[176],"In":[177],"simulation,":[178],"robot":[180,204,210],"achieved":[181,211],"an":[182],"block-stacking":[184],"success":[185],"rate":[186,215,223],"up":[188],"98%":[190],"during":[191,229],"testing.":[192],"When":[193],"transferring":[194],"model":[196],"real":[199],"universal":[200],"UR3":[202],"(UR3)":[203],"effective":[206],"domain":[207],"randomization,":[208],"100%":[213],"completion":[214,222],"convex":[217],"92%":[221],"seen":[228],"training.":[230,263],"Originality/value":[231],"We":[232],"multiple":[244],"new":[249],"use":[255],"algorithms":[260],"modular":[265],"design":[266],"allows":[270],"more":[275],"tasks,":[278],"encouraging":[281],"results":[282],"experiments":[288],"significant":[290],"improvements":[291],"over":[292],"current":[293],"long-term":[294],"methods.":[296]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}