{"id":"https://openalex.org/W4405785334","doi":"https://doi.org/10.1109/iros58592.2024.10802845","title":"Hierarchical Action Chunking Transformer: Learning Temporal Multimodality from Demonstrations with Fast Imitation Behavior","display_name":"Hierarchical Action Chunking Transformer: Learning Temporal Multimodality from Demonstrations with Fast Imitation Behavior","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785334","doi":"https://doi.org/10.1109/iros58592.2024.10802845"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802845","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/A5032063647","display_name":"J. Hyeon Park","orcid":"https://orcid.org/0000-0001-8410-4568"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"J. Hyeon Park","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775809","display_name":"Wonhyuk Choi","orcid":"https://orcid.org/0000-0001-7030-0031"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonhyuk Choi","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102160048","display_name":"Sunpyo Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunpyo Hong","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103058532","display_name":"Hoseong Seo","orcid":"https://orcid.org/0000-0002-1485-3712"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoseong Seo","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006220725","display_name":"Joonmo Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonmo Ahn","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069920778","display_name":"Changsu Ha","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changsu Ha","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077680955","display_name":"Heungwoo Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heungwoo Han","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054994110","display_name":"Junghyun Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junghyun Kwon","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co. Ltd,Seoul,Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5032063647"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":0.7836,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74810451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12648","last_page":"12654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926000237464905,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9768999814987183,"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/multimodality","display_name":"Multimodality","score":0.7812760472297668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6625354886054993},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6383659839630127},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.5409091711044312},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4431878328323364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4137713611125946},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11752629280090332},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1147172749042511},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08895042538642883},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06619307398796082},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05752083659172058}],"concepts":[{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.7812760472297668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625354886054993},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6383659839630127},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.5409091711044312},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4431878328323364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4137713611125946},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11752629280090332},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1147172749042511},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08895042538642883},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06619307398796082},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05752083659172058},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802845","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W3035069850","https://openalex.org/W3096609285","https://openalex.org/W4385245566","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4386076288","https://openalex.org/W6738261575","https://openalex.org/W6838833932"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4205899436"],"abstract_inverted_index":{"Behavioral":[0],"cloning":[1],"from":[2],"human":[3],"demonstrations":[4,132,155],"has":[5],"succeeded":[6],"in":[7,73,147],"programming":[8],"a":[9,34,84,91,97],"robot":[10,35,45],"to":[11,20,68,75,87,100],"generate":[12],"fine-grained":[13,76],"motion,":[14],"but":[15],"it":[16],"is":[17,179],"still":[18],"challenging":[19],"learn":[21,70,128],"multimodal":[22,129],"trajectories":[23],"such":[24],"as":[25,119],"with":[26,65,106,156,162,173],"various":[27,157],"speeds.":[28,158],"This":[29],"restricts":[30],"the":[31,41,48,107,135,163,169],"use":[32],"of":[33,44,53,83,131,137],"dataset":[36,49],"collected":[37,154],"by":[38],"multiusers":[39],"because":[40],"different":[42],"proficiency":[43],"operators":[46],"makes":[47],"have":[50],"diverse":[51],"distributions":[52,130],"speed.":[54],"To":[55],"tackle":[56],"this":[57],"issue,":[58],"we":[59,142],"develop":[60],"Hierarchical":[61],"Action":[62],"Chunking":[63],"Transformer":[64],"Vector-quantization":[66],"(HACT-Vq)":[67],"efficiently":[69,127],"temporal":[71],"multimodality":[72],"addition":[74],"motion.":[77],"The":[78,112,159],"proposed":[79,160],"hierarchical":[80],"model":[81,161],"consists":[82],"high-level":[85,124],"policy":[86,99,125],"make":[88],"planning":[89],"for":[90],"latent":[92,108,113],"subgoal":[93,109,114,165],"and":[94,96,110,115,133,150,153,166],"style,":[95],"low-level":[98],"predict":[101],"an":[102],"action":[103],"chunk":[104],"conditioned":[105],"style.":[111],"style":[116,167],"are":[117],"trained":[118],"discrete":[120],"representations":[121],"so":[122],"that":[123],"can":[126],"retrieve":[134],"mode":[136],"fast":[138,174],"behavior.":[139,176],"In":[140],"experiments,":[141],"set":[143],"up":[144],"bimanual":[145],"robots":[146],"both":[148],"simulation":[149],"real-world":[151],"environments,":[152],"quantized":[164],"showed":[168],"highest":[170],"success":[171],"rates":[172],"imitation":[175],"Our":[177],"code":[178],"available":[180],"at":[181],"https://github.com/SamsungLabs/hierarchical-act.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}