{"id":"https://openalex.org/W4416747754","doi":"https://doi.org/10.1109/iros60139.2025.11245926","title":"Look Before You Leap: Using Serialized State Machine for Language Conditioned Robotic Manipulation","display_name":"Look Before You Leap: Using Serialized State Machine for Language Conditioned Robotic Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416747754","doi":"https://doi.org/10.1109/iros60139.2025.11245926"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5114637220","display_name":"Tong Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Mu","raw_affiliation_strings":["Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696070","display_name":"Yihao Liu","orcid":"https://orcid.org/0000-0002-2654-9793"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yihao Liu","raw_affiliation_strings":["Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090301235","display_name":"Mehran Armand","orcid":"https://orcid.org/0000-0003-1028-8303"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehran Armand","raw_affiliation_strings":["Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48964287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8096","last_page":"8102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.37880000472068787,"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":0.37880000472068787,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2818000018596649,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.08139999955892563,"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/set","display_name":"Set (abstract data type)","score":0.6420999765396118},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5759000182151794},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5271999835968018},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5042999982833862},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4961000084877014},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.4472000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527999877929688},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6420999765396118},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4961000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47429999709129333},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337362","display_name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","ror":"https://ror.org/006zn3t30"},{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1978892650","https://openalex.org/W1986014385","https://openalex.org/W2081203294","https://openalex.org/W2135639338","https://openalex.org/W2161414194","https://openalex.org/W2166302491","https://openalex.org/W2337392266","https://openalex.org/W2794908222","https://openalex.org/W2912694244","https://openalex.org/W2994446013","https://openalex.org/W3001865277","https://openalex.org/W3099130708","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4388720459","https://openalex.org/W4402670718","https://openalex.org/W4405787555","https://openalex.org/W4409158105","https://openalex.org/W4416749665"],"related_works":[],"abstract_inverted_index":{"Imitation":[0],"learning":[1],"frameworks":[2,23],"for":[3,153],"robotic":[4],"manipulation":[5,83],"have":[6],"drawn":[7],"attention":[8],"in":[9,45,56,82,122,144],"the":[10,19,22,27,30,34,49,79,127],"recent":[11],"development":[12],"of":[13,21,29,41,89,118,139],"language":[14],"model":[15],"grounded":[16],"robotics.":[17],"However,":[18],"success":[20,80,116,137],"largely":[24],"depends":[25],"on":[26],"coverage":[28],"demonstration":[31,35],"cases:":[32],"When":[33],"set":[36],"does":[37],"not":[38],"include":[39],"examples":[40],"how":[42],"to":[43,74,120,126,141],"act":[44],"all":[46],"possible":[47],"situations,":[48],"action":[50],"may":[51],"fail":[52],"and":[53,77,100],"can":[54,156],"result":[55],"cascading":[57],"errors.":[58],"To":[59,92],"solve":[60],"this":[61,154],"problem,":[62],"we":[63,96],"propose":[64],"a":[65,86,115,136],"framework":[66],"that":[67,103,111],"uses":[68],"serialized":[69],"Finite":[70],"State":[71],"Machine":[72],"(FSM)":[73],"generate":[75],"demonstrations":[76],"improve":[78],"rate":[81,117,138],"tasks":[84],"requiring":[85],"long":[87,105],"sequence":[88],"precise":[90],"interactions.":[91],"validate":[93],"its":[94],"effectiveness,":[95],"use":[97],"environmentally":[98],"evolving":[99],"long-horizon":[101],"puzzles":[102],"require":[104],"sequential":[106],"actions.":[107],"Experimental":[108],"results":[109],"show":[110],"our":[112],"approach":[113],"achieves":[114],"up":[119,140],"98%":[121],"these":[123],"tasks,":[124,146],"compared":[125],"controlled":[128],"condition":[129],"using":[130],"existing":[131],"approaches,":[132],"which":[133],"only":[134],"had":[135],"60%,":[142],"and,":[143],"some":[145],"almost":[147],"failed":[148],"completely.":[149],"The":[150],"source":[151],"code":[152],"project":[155],"be":[157],"accessed":[158],"at":[159],"https://imitate.finite-state.com/.":[160]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}