{"id":"https://openalex.org/W4405786873","doi":"https://doi.org/10.1109/iros58592.2024.10801334","title":"Multi-Agent Behavior Retrieval: Retrieval-Augmented Policy Training for Cooperative Push Manipulation by Mobile Robots","display_name":"Multi-Agent Behavior Retrieval: Retrieval-Augmented Policy Training for Cooperative Push Manipulation by Mobile Robots","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786873","doi":"https://doi.org/10.1109/iros58592.2024.10801334"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5084829137","display_name":"So Kuroki","orcid":"https://orcid.org/0000-0002-6151-1424"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"So Kuroki","raw_affiliation_strings":["OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090289668","display_name":"Mai Nishimura","orcid":"https://orcid.org/0000-0002-9730-3555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mai Nishimura","raw_affiliation_strings":["OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070075141","display_name":"Tadashi Kozuno","orcid":"https://orcid.org/0000-0002-8820-1362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tadashi Kozuno","raw_affiliation_strings":["OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084829137"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70325439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12671","last_page":"12678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9678000211715698,"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":0.9678000211715698,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7558644413948059},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5554879903793335},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5356793999671936},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5217562317848206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4628652036190033},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34829914569854736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7558644413948059},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5554879903793335},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5356793999671936},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5217562317848206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4628652036190033},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34829914569854736},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1976517551","https://openalex.org/W2054381558","https://openalex.org/W2142943472","https://openalex.org/W2144994235","https://openalex.org/W2162912282","https://openalex.org/W2963219401","https://openalex.org/W3205685096","https://openalex.org/W3206518075","https://openalex.org/W3208451383","https://openalex.org/W4240592325","https://openalex.org/W4283756722","https://openalex.org/W4360897637","https://openalex.org/W4385245566","https://openalex.org/W4385430535","https://openalex.org/W4387764390","https://openalex.org/W4392224077","https://openalex.org/W4401415042","https://openalex.org/W6631190155","https://openalex.org/W6735698609","https://openalex.org/W6747473740","https://openalex.org/W6753526802","https://openalex.org/W6755243447","https://openalex.org/W6766956246","https://openalex.org/W6776601253","https://openalex.org/W6846049332","https://openalex.org/W6846271118"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W2122871747","https://openalex.org/W3114279067"],"abstract_inverted_index":{"Due":[0],"to":[1,21,25,30,32,61,73,101],"the":[2,42,94,97,103,110,140],"complex":[3],"interactions":[4,70],"between":[5],"agents,":[6],"learning":[7],"multi-agent":[8,23],"control":[9],"policy":[10,104],"often":[11],"requires":[12],"a":[13,37,47,51,77,88,106,120,147,151],"prohibitive":[14],"amount":[15],"of":[16,53,91,93,142,153],"data.":[17],"This":[18],"paper":[19],"aims":[20],"enable":[22],"systems":[24],"effectively":[26,67],"utilize":[27],"past":[28],"memories":[29],"adapt":[31],"novel":[33],"collaborative":[34],"tasks":[35,128],"in":[36,125,146],"data-efficient":[38],"fashion.":[39],"We":[40],"propose":[41],"Multi-Agent":[43],"Coordination":[44],"Skill":[45],"Database,":[46],"repository":[48],"for":[49,81],"storing":[50],"collection":[52],"coordinated":[54,83],"behaviors":[55],"associated":[56],"with":[57,109,130],"key":[58],"vectors":[59],"distinctive":[60],"them.":[62],"Our":[63],"Transformer-based":[64],"skill":[65,79],"encoder":[66],"captures":[68],"spatio-temporal":[69],"that":[71,116],"contribute":[72],"coordination":[74],"and":[75],"provides":[76],"unique":[78],"representation":[80],"each":[82],"behavior.":[84],"By":[85],"leveraging":[86],"only":[87],"small":[89],"number":[90],"demonstrations":[92],"target":[95],"task,":[96],"database":[98],"enables":[99],"us":[100],"train":[102],"using":[105,150],"dataset":[107],"augmented":[108],"retrieved":[111],"demonstrations.":[112],"Experimental":[113],"evaluations":[114],"demonstrate":[115],"our":[117,143],"method":[118],"achieves":[119],"significantly":[121],"higher":[122],"success":[123],"rate":[124],"push":[126],"manipulation":[127],"compared":[129],"baseline":[131],"methods":[132],"like":[133],"few-shot":[134],"imitation":[135],"learning.":[136],"Furthermore,":[137],"we":[138],"validate":[139],"effectiveness":[141],"retrieve-and-learn":[144],"framework":[145],"real":[148],"environment":[149],"team":[152],"wheeled":[154],"robots.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}