{"id":"https://openalex.org/W4401414354","doi":"https://doi.org/10.1109/icra57147.2024.10611076","title":"Leveraging the efficiency of multi-task robot manipulation via task-evoked planner and reinforcement learning","display_name":"Leveraging the efficiency of multi-task robot manipulation via task-evoked planner and reinforcement learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414354","doi":"https://doi.org/10.1109/icra57147.2024.10611076"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611076","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10611076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071856936","display_name":"Haofu Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofu Qian","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310030","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461120","display_name":"Haoyang Zhang","orcid":"https://orcid.org/0000-0002-1674-2282"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Zhang","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310030","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109760539","display_name":"Jun Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Shao","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310030","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101756385","display_name":"Jiatao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiatao Zhang","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310030","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010340252","display_name":"Jason Gu","orcid":"https://orcid.org/0000-0002-7626-1077"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jason Gu","raw_affiliation_strings":["Zhejiang Lab,Research Center for Intelligent Robotics,Research Institute of Interdisciplinary Innovation,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Center for Intelligent Robotics,Research Institute of Interdisciplinary Innovation,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021043499","display_name":"Wei Song","orcid":"https://orcid.org/0000-0002-7084-5231"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Song","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310030","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039356472","display_name":"Shiqiang Zhu","orcid":"https://orcid.org/0000-0002-5687-4001"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqiang Zhu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310030","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"9220","last_page":"9226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.840935468673706},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.820907711982727},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7761979103088379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7747519016265869},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6071039438247681},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5761051177978516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086849331855774},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11821338534355164}],"concepts":[{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.840935468673706},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.820907711982727},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7761979103088379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7747519016265869},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6071039438247681},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5761051177978516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086849331855774},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11821338534355164},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611076","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10611076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1907729166","https://openalex.org/W2075830955","https://openalex.org/W2149398074","https://openalex.org/W2517190429","https://openalex.org/W2575705757","https://openalex.org/W2585510649","https://openalex.org/W2735995851","https://openalex.org/W2772449134","https://openalex.org/W2904246096","https://openalex.org/W2912063360","https://openalex.org/W2938421504","https://openalex.org/W2962793652","https://openalex.org/W2963411833","https://openalex.org/W2964335674","https://openalex.org/W3004584758","https://openalex.org/W3006033038","https://openalex.org/W3013821552","https://openalex.org/W3090717212","https://openalex.org/W3091544428","https://openalex.org/W3103850820","https://openalex.org/W3146696145","https://openalex.org/W3204657926","https://openalex.org/W3206518906","https://openalex.org/W3206530605","https://openalex.org/W4224329734","https://openalex.org/W4226067323","https://openalex.org/W4288331462","https://openalex.org/W4309395337","https://openalex.org/W4310336120","https://openalex.org/W4313178149","https://openalex.org/W4313887929","https://openalex.org/W4383097621","https://openalex.org/W4383108741","https://openalex.org/W6682178038","https://openalex.org/W6685145238","https://openalex.org/W6740879895","https://openalex.org/W6748566876","https://openalex.org/W6764173040","https://openalex.org/W6769596995","https://openalex.org/W6784521679","https://openalex.org/W6790190981","https://openalex.org/W6803178138","https://openalex.org/W6803665686"],"related_works":["https://openalex.org/W1568779110","https://openalex.org/W804484174","https://openalex.org/W4244698559","https://openalex.org/W4246538999","https://openalex.org/W56933075","https://openalex.org/W99657755","https://openalex.org/W2998826171","https://openalex.org/W2036736859","https://openalex.org/W3213722473","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Multi-task":[0],"learning":[1,21,58,68,84,129],"has":[2,139],"expanded":[3],"the":[4,10,36,78,81,99,107,117],"boundaries":[5],"of":[6,12,38,83,128],"robotic":[7],"manipulation,":[8],"enabling":[9],"execution":[11],"increasingly":[13],"complex":[14],"tasks.":[15],"However,":[16],"policies":[17,40],"learned":[18],"through":[19],"reinforcement":[20,57,67,93],"exhibit":[22],"limited":[23],"generalization":[24,42],"and":[25,43,65,97,104,120,131,145],"narrow":[26],"distributions,":[27],"which":[28],"restrict":[29],"their":[30],"effectiveness":[31],"in":[32,92,109,126],"multi-task":[33,110],"training.":[34],"Addressing":[35],"challenge":[37],"obtaining":[39],"with":[41,70,80,123],"stability":[44],"represents":[45],"a":[46,55,62,66],"non-trivial":[47],"problem.":[48],"To":[49],"tackle":[50],"this":[51,114],"issue,":[52],"we":[53],"propose":[54],"planning-guided":[56],"method.":[59],"It":[60],"leverages":[61],"task-evoked":[63],"planner(TEP)":[64],"approach":[69,115],"planner\u2019s":[71],"guidance.":[72],"TEP":[73,95],"utilizes":[74],"reusable":[75],"samples":[76],"as":[77],"source,":[79],"aim":[82],"reachability":[85],"information":[86],"across":[87],"different":[88],"task":[89],"scenarios.":[90],"Then":[91],"learning,":[94],"assesses":[96],"guides":[98],"Actor":[100],"towards":[101],"better":[102],"outputs":[103],"smoothly":[105],"enhances":[106],"performance":[108],"benchmarks.":[111],"We":[112],"evaluate":[113],"within":[116],"Meta-World":[118],"framework":[119],"compare":[121],"it":[122],"prior":[124],"works":[125],"terms":[127],"efficiency":[130],"effectiveness.":[132],"Depending":[133],"on":[134],"experimental":[135],"results,":[136],"our":[137],"method":[138],"more":[140,147],"efficiency,":[141],"higher":[142],"success":[143],"rates,":[144],"demonstrates":[146],"realistic":[148],"behavior.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}