{"id":"https://openalex.org/W4416748371","doi":"https://doi.org/10.1109/iros60139.2025.11247043","title":"Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation","display_name":"Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748371","doi":"https://doi.org/10.1109/iros60139.2025.11247043"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247043","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":"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/A5035866142","display_name":"Sheng Quan Xie","orcid":"https://orcid.org/0000-0003-2641-2620"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senwei Xie","raw_affiliation_strings":["Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086861087","display_name":"Hongyu Wang","orcid":"https://orcid.org/0000-0002-2288-5116"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Wang","raw_affiliation_strings":["Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhanqi Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanqi Xiao","raw_affiliation_strings":["Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614962","display_name":"Ruiping Wang","orcid":"https://orcid.org/0000-0003-1830-2595"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiping Wang","raw_affiliation_strings":["Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111681970","display_name":"Xilin Chen","orcid":"https://orcid.org/0009-0005-2633-8637"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences (CAS),Key Laboratory of AI Safety of CAS, Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31712751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14923","last_page":"14930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6818000078201294,"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":0.6818000078201294,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.12330000102519989,"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":0.04450000077486038,"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/executable","display_name":"Executable","score":0.8719000220298767},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6517000198364258},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5722000002861023},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5555999875068665},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5138000249862671},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.40639999508857727},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.39259999990463257}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.8719000220298767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739999890327454},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6517000198364258},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5722000002861023},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5138000249862671},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43630000948905945},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.33559998869895935},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247043","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2112474089","https://openalex.org/W3007769740","https://openalex.org/W4382366145","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4385245566","https://openalex.org/W4386065350","https://openalex.org/W4390873312","https://openalex.org/W4402354047","https://openalex.org/W4402727764","https://openalex.org/W4404575065","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"generalization":[1,33],"across":[2],"various":[3],"robots,":[4],"tasks":[5],"and":[6,27,39,62,81,107,128,159],"environments":[7],"remains":[8],"a":[9,51,74],"significant":[10],"challenge":[11],"in":[12,73,84,125],"robotic":[13,52,68,90,123],"manipulation.":[14],"Policy":[15],"code":[16,21,72,87,98],"generation":[17],"methods":[18],"use":[19],"executable":[20,97],"to":[22,66,95,154],"connect":[23],"high-level":[24],"task":[25],"descriptions":[26],"low-level":[28],"action":[29],"sequences,":[30],"leveraging":[31],"the":[32,56,118,132,144],"capabilities":[34],"of":[35,58,136],"large":[36,109],"language":[37,110],"models":[38],"atomic":[40],"skill":[41,160],"libraries.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,92],"propose":[47],"Robotic":[48],"Programmer":[49],"(RoboPro),":[50],"foundation":[53],"model,":[54],"enabling":[55],"capability":[57],"perceiving":[59],"visual":[60],"information":[61],"following":[63],"free-form":[64],"instructions":[65],"perform":[67],"manipulation":[69,124],"with":[70,103,143],"policy":[71],"zero-shot":[75,120,133],"manner.":[76],"To":[77],"address":[78],"low":[79],"efficiency":[80],"high":[82],"cost":[83],"collecting":[85],"runtime":[86],"data":[88],"for":[89],"tasks,":[91],"devise":[93],"Video2Code":[94],"synthesize":[96],"from":[99],"extensive":[100],"videos":[101],"in-the-wild":[102],"off-the-shelf":[104],"vision-language":[105],"model":[106,146],"code-domain":[108],"model.":[111],"Extensive":[112],"experiments":[113],"show":[114],"that":[115],"RoboPro":[116,137,151],"achieves":[117],"state-of-the-art":[119,145],"performance":[121],"on":[122,138,156],"both":[126],"simulators":[127],"real-world":[129],"environments.":[130],"Specifically,":[131],"success":[134],"rate":[135],"RLBench":[139],"surpasses":[140],"Code-as-Policies":[141],"equipped":[142],"GPT-4o":[147],"by":[148],"11.6%.":[149],"Furthermore,":[150],"is":[152],"robust":[153],"variations":[155],"API":[157],"formats":[158],"sets.":[161],"Our":[162],"website":[163],"can":[164],"be":[165],"found":[166],"at":[167],"https://video2code.github.io/RoboPro-website/.":[168]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}
