{"id":"https://openalex.org/W7128422348","doi":"https://doi.org/10.1109/lra.2026.3662582","title":"HiMRAG: Hierarchical Multimodal Retrieval-Augmented Generation for Robot Task Planning","display_name":"HiMRAG: Hierarchical Multimodal Retrieval-Augmented Generation for Robot Task Planning","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128422348","doi":"https://doi.org/10.1109/lra.2026.3662582"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3662582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3662582","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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/A5125444766","display_name":"Zhuoyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyi Zhang","raw_affiliation_strings":["School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-6015-7275","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085565570","display_name":"Yixin Han","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Han","raw_affiliation_strings":["School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-9771-3489","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125465684","display_name":"Renjun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renjun Li","raw_affiliation_strings":["Rosiwit Technology Company, Ltd, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rosiwit Technology Company, Ltd, Nanjing, China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125443645","display_name":"Xiao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Li","raw_affiliation_strings":["School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2565-9883","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.15586765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"3","first_page":"3883","last_page":"3890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8938999772071838,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8938999772071838,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.04039999842643738,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.013500000350177288,"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/executable","display_name":"Executable","score":0.5896000266075134},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.579800009727478},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5791000127792358},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5669000148773193},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5095000267028809},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5037999749183655},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.4569999873638153},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4489000141620636},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42879998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508999705314636},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5782999992370605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253999829292297},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3605000078678131},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2776228582","wikidata":"https://www.wikidata.org/wiki/Q7455797","display_name":"Service robot","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3662582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3662582","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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/G6244767003","display_name":null,"funder_award_id":"24511103400","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G676121582","display_name":null,"funder_award_id":"52405029","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"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W3200291013","https://openalex.org/W3207057769","https://openalex.org/W4389665575","https://openalex.org/W4392866655","https://openalex.org/W4401414856","https://openalex.org/W4402783855","https://openalex.org/W4403791353","https://openalex.org/W4408200798","https://openalex.org/W4409364594","https://openalex.org/W4412888464","https://openalex.org/W4413925401","https://openalex.org/W4415970897"],"related_works":[],"abstract_inverted_index":{"Data-driven":[0],"methods":[1],"offer":[2],"promising":[3],"solutions":[4],"for":[5],"robotic":[6,132],"manipulation":[7],"in":[8],"human-centric":[9],"environments,":[10],"but":[11],"enabling":[12],"robots":[13],"to":[14,40,72,88],"operate":[15],"complex":[16],"appliances":[17],"from":[18,79],"natural":[19],"language":[20,64],"remains":[21],"a":[22,52,69,80,84,108,131],"significant":[23],"challenge.":[24],"The":[25],"ambiguity":[26],"of":[27,34,111],"human":[28],"instructions":[29],"and":[30,43,76,96,103,116,121,127],"the":[31],"visual":[32,61],"diversity":[33],"real-world":[35],"objects":[36],"make":[37],"it":[38],"difficult":[39],"generate":[41,97],"precise":[42],"reliable":[44],"action":[45,99],"sequences.":[46,100],"In":[47],"this":[48,105],"paper,":[49],"we":[50],"propose":[51],"hierarchical":[53],"multimodal":[54],"Retrieval-Augmented":[55],"Generation":[56],"(RAG)":[57],"framework":[58,67,106],"that":[59],"fuses":[60],"perception":[62],"with":[63],"understanding.":[65],"Our":[66],"uses":[68],"vision-based":[70],"module":[71],"identify":[73],"an":[74],"appliance":[75],"its":[77,118],"documentation":[78],"snapshot,":[81],"then":[82],"leverages":[83],"task-oriented":[85],"RAG":[86],"pipeline":[87],"process":[89],"user":[90],"instructions,":[91],"retrieve":[92],"relevant":[93],"manual":[94],"sections,":[95],"executable":[98],"We":[101],"train":[102],"validate":[104],"on":[107,130],"custom":[109],"dataset":[110],"microwave":[112],"oven":[113],"operation":[114],"tasks":[115],"demonstrate":[117],"effectiveness,":[119],"robustness,":[120],"practical":[122],"viability":[123],"through":[124],"extensive":[125],"virtual":[126],"physical":[128],"experiments":[129],"platform.":[133]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-10T00:00:00"}
