{"id":"https://openalex.org/W4399526652","doi":"https://doi.org/10.1109/lra.2024.3412630","title":"Multi-Stage Reinforcement Learning for Non-Prehensile Manipulation","display_name":"Multi-Stage Reinforcement Learning for Non-Prehensile Manipulation","publication_year":2024,"publication_date":"2024-06-11","ids":{"openalex":"https://openalex.org/W4399526652","doi":"https://doi.org/10.1109/lra.2024.3412630"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3412630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3412630","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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/A5043850288","display_name":"Dexin Wang","orcid":"https://orcid.org/0000-0002-7956-6423"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dexin Wang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-7956-6423","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065058741","display_name":"Chunsheng Liu","orcid":"https://orcid.org/0000-0001-5516-2486"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunsheng Liu","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-5516-2486","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070332088","display_name":"Faliang Chang","orcid":"https://orcid.org/0000-0003-1276-2267"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Faliang Chang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-1276-2267","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022175950","display_name":"Hengqiang Huan","orcid":"https://orcid.org/0009-0007-6712-7451"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengqiang Huan","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0007-6712-7451","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100914541","display_name":"Kun Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Cheng","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0006-4272-5490","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":3.6933,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93434724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"7","first_page":"6712","last_page":"6719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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":0.9998000264167786,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9976999759674072,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/prehensile-tail","display_name":"Prehensile tail","score":0.986255407333374},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.522372305393219},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4700521230697632},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.46053197979927063},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.4530309736728668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3043248951435089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.294830858707428},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1352682113647461},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12309873104095459},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.11041641235351562}],"concepts":[{"id":"https://openalex.org/C136380597","wikidata":"https://www.wikidata.org/wiki/Q10508905","display_name":"Prehensile tail","level":2,"score":0.986255407333374},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.522372305393219},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4700521230697632},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.46053197979927063},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.4530309736728668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3043248951435089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.294830858707428},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1352682113647461},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12309873104095459},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.11041641235351562},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3412630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3412630","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":[],"awards":[{"id":"https://openalex.org/G5535474515","display_name":null,"funder_award_id":"62176138","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8239702273","display_name":null,"funder_award_id":"62176136","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8636925473","display_name":null,"funder_award_id":"U22A2058","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":36,"referenced_works":["https://openalex.org/W1674160379","https://openalex.org/W1990294885","https://openalex.org/W2049981393","https://openalex.org/W2125298120","https://openalex.org/W2158782408","https://openalex.org/W2468618434","https://openalex.org/W2938604599","https://openalex.org/W2981030070","https://openalex.org/W3000256909","https://openalex.org/W3088304681","https://openalex.org/W3090123176","https://openalex.org/W3127352841","https://openalex.org/W3134939669","https://openalex.org/W3196603227","https://openalex.org/W3198507954","https://openalex.org/W3205140045","https://openalex.org/W3206181916","https://openalex.org/W3209765550","https://openalex.org/W4200010608","https://openalex.org/W4200507518","https://openalex.org/W4211108606","https://openalex.org/W4213322786","https://openalex.org/W4214902667","https://openalex.org/W4285221346","https://openalex.org/W4313533756","https://openalex.org/W4376280030","https://openalex.org/W4382657735","https://openalex.org/W4383097672","https://openalex.org/W6763422710","https://openalex.org/W6764969207","https://openalex.org/W6771989576","https://openalex.org/W6782766965","https://openalex.org/W6801810553","https://openalex.org/W6846207995","https://openalex.org/W6846435682","https://openalex.org/W6847110631"],"related_works":["https://openalex.org/W2465876097","https://openalex.org/W2028231052","https://openalex.org/W2768832826","https://openalex.org/W3166169123","https://openalex.org/W2010045274","https://openalex.org/W2552641899","https://openalex.org/W2105329304","https://openalex.org/W2998125923","https://openalex.org/W197901881","https://openalex.org/W1551001629"],"abstract_inverted_index":{"Manipulating":[0],"objects":[1,24,114,197],"without":[2,170],"grasping":[3,180],"them":[4],"facilitates":[5],"complex":[6],"tasks,":[7],"known":[8],"as":[9,93,132],"non-prehensile":[10,45],"manipulation.":[11],"Most":[12],"previous":[13],"methods":[14],"are":[15,29],"limited":[16],"to":[17,22,104,108,127,161,184,195,208],"learning":[18],"a":[19,37,49,98,120,154,216],"single":[20],"skill":[21],"manipulate":[23],"with":[25,115,135,198,212],"primitive":[26],"shapes":[27,199],"and":[28,47,69,72,96,130,145,204],"unserviceable":[30],"for":[31,55,79],"flexible":[32],"object":[33,91,187],"manipulation":[34,46],"that":[35],"requires":[36],"combination":[38],"of":[39,142],"multiple":[40,77],"skills.":[41],"We":[42,174],"explore":[43,105],"skill-unconstrained":[44],"propose":[48,119,153],"<italic":[50,121,155],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[51,59,122,156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Multi-stage":[52],"Reinforcement":[53],"Learning":[54],"Non-prehensile":[56],"Manipulation</i>":[57],"(<bold":[58],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MRLNM</b>),":[60],"which":[61,137,182],"calculates":[62],"an":[63,178],"intermediate":[64],"state":[65],"between":[66,167],"the":[67,74,85,88,94,102,110,139,164,172,186,201,209],"initial":[68],"goal":[70],"states":[71],"divides":[73],"task":[75,146,181],"into":[76],"stages":[78],"sequential":[80],"learning.":[81],"At":[82],"each":[83],"stage,":[84],"policy":[86],"takes":[87],"desired":[89],"6-DOF":[90],"pose":[92],"goal,":[95],"proposes":[97],"spatially-continuous":[99],"action,":[100],"allowing":[101],"robot":[103],"arbitrary":[106],"skills":[107],"accomplish":[109],"task.":[111],"To":[112,148],"handle":[113],"different":[116],"shapes,":[117],"we":[118,152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">State-Goal":[123],"Fusion":[124],"Representation</i>":[125],"(SGF-Representation)":[126],"represent":[128],"observations":[129],"goals":[131],"point":[133],"clouds":[134],"motion,":[136],"improves":[138],"policy's":[140],"perception":[141],"scene":[143],"layout":[144],"goal.":[147],"improve":[149],"sample":[150],"efficiency,":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Spatially-Reachable":[157],"Distance":[158],"Metric</i>":[159],"(SR-Distance)":[160],"approximately":[162],"measure":[163],"shortest":[165],"distance":[166],"two":[168],"points":[169],"intersecting":[171],"scene.":[173],"evaluate":[175],"MRLNM":[176,192],"on":[177],"occluded":[179,190],"aims":[183],"grasp":[185],"in":[188],"initially":[189],"configurations.":[191],"demonstrates":[193],"generalization":[194],"unseen":[196],"outside":[200],"training":[202],"distribution":[203],"can":[205],"be":[206],"transferred":[207],"real":[210],"world":[211],"zero-shot":[213],"transfer,":[214],"achieving":[215],"95%":[217],"success":[218],"rate.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}