{"id":"https://openalex.org/W4416748744","doi":"https://doi.org/10.1109/iros60139.2025.11246352","title":"RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation","display_name":"RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748744","doi":"https://doi.org/10.1109/iros60139.2025.11246352"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246352","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/A5016790392","display_name":"Lin Yang","orcid":"https://orcid.org/0000-0002-0217-9353"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Liudi Yang","raw_affiliation_strings":["University of Freiburg,Department of Computer Science,Germany"],"affiliations":[{"raw_affiliation_string":"University of Freiburg,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705386","display_name":"Yang Bai","orcid":"https://orcid.org/0000-0001-5114-5777"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yang Bai","raw_affiliation_strings":["Ludwig Maximilian University of Munich,Germany"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich,Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049254859","display_name":"George Eskandar","orcid":"https://orcid.org/0000-0002-8099-8717"},"institutions":[{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"George Eskandar","raw_affiliation_strings":["Huawei Munich Research Center,Germany"],"affiliations":[{"raw_affiliation_string":"Huawei Munich Research Center,Germany","institution_ids":["https://openalex.org/I4210166625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021538087","display_name":"Fengyi Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fengyi Shen","raw_affiliation_strings":["Technical University of Munich,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001923349","display_name":"Mohammad Altillawi","orcid":"https://orcid.org/0009-0006-9102-2548"},"institutions":[{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohammad Altillawi","raw_affiliation_strings":["Huawei Munich Research Center,Germany"],"affiliations":[{"raw_affiliation_string":"Huawei Munich Research Center,Germany","institution_ids":["https://openalex.org/I4210166625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007759097","display_name":"Chen Dong","orcid":"https://orcid.org/0000-0003-2745-0258"},"institutions":[{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dong Chen","raw_affiliation_strings":["Huawei Munich Research Center,Germany"],"affiliations":[{"raw_affiliation_string":"Huawei Munich Research Center,Germany","institution_ids":["https://openalex.org/I4210166625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102917774","display_name":"Soumajit Majumder","orcid":"https://orcid.org/0000-0002-0150-1208"},"institutions":[{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Soumajit Majumder","raw_affiliation_strings":["Huawei Munich Research Center,Germany"],"affiliations":[{"raw_affiliation_string":"Huawei Munich Research Center,Germany","institution_ids":["https://openalex.org/I4210166625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702698","display_name":"Ziyuan Liu","orcid":"https://orcid.org/0000-0001-7164-088X"},"institutions":[{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziyuan Liu","raw_affiliation_strings":["Huawei Munich Research Center,Germany"],"affiliations":[{"raw_affiliation_string":"Huawei Munich Research Center,Germany","institution_ids":["https://openalex.org/I4210166625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090767423","display_name":"Gitta Kutyniok","orcid":"https://orcid.org/0000-0001-9738-2487"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gitta Kutyniok","raw_affiliation_strings":["Ludwig Maximilian University of Munich,Germany"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich,Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039639553","display_name":"Abhinav Valada","orcid":"https://orcid.org/0000-0003-4710-3114"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Abhinav Valada","raw_affiliation_strings":["University of Freiburg,Department of Computer Science,Germany"],"affiliations":[{"raw_affiliation_string":"University of Freiburg,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5016790392"],"corresponding_institution_ids":["https://openalex.org/I161046081"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40047612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21281","last_page":"21288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.47290000319480896,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.47290000319480896,"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":0.30059999227523804,"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":0.058400001376867294,"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/robot","display_name":"Robot","score":0.7240999937057495},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6251000165939331},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6126000285148621},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5771999955177307},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5390999913215637},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.46209999918937683},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4004000127315521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7849000096321106},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7240999937057495},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5483999848365784},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4584999978542328},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.33219999074935913},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.27630001306533813},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2696000039577484},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246352","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/W2158782408","https://openalex.org/W4285218426","https://openalex.org/W4385430674","https://openalex.org/W4385571093","https://openalex.org/W4391759936","https://openalex.org/W4401415888","https://openalex.org/W4402354026","https://openalex.org/W4403337227","https://openalex.org/W4403888324","https://openalex.org/W4413157524","https://openalex.org/W4413917052","https://openalex.org/W4414079054"],"related_works":[],"abstract_inverted_index":{"We":[0,99,142,156],"address":[1],"the":[2,55,68,76,81,94,110,133,138,153,164],"problem":[3],"of":[4,54,132],"generating":[5],"long-horizon":[6,29,139,190],"videos":[7],"for":[8,38,96],"robotic":[9,30],"manipulation":[10],"tasks.":[11,31,191],"Text-to-video":[12],"diffusion":[13,36,126],"models":[14,37,188],"have":[15],"made":[16],"significant":[17],"progress":[18],"in":[19,45,75,80,179],"photorealism,":[20],"language":[21],"understanding,":[22],"and":[23,42,60,79,117,182],"motion":[24],"generation":[25],"but":[26],"struggle":[27],"with":[28,121],"Recent":[32],"works":[33,50],"use":[34],"video":[35,78,180],"high-quality":[39],"simulation":[40],"data":[41],"predictive":[43],"rollouts":[44],"robot":[46,56,165],"planning.":[47],"However,":[48],"these":[49,85,122],"predict":[51],"short":[52],"sequences":[53],"achieving":[57,137],"one":[58],"task":[59],"employ":[61],"an":[62],"autoregressive":[63,97],"paradigm":[64],"to":[65,67,72,149,162],"extend":[66],"long":[69],"horizon,":[70],"leading":[71],"error":[73],"accumulations":[74],"generated":[77,135,169],"execution.":[82],"To":[83],"overcome":[84],"limitations,":[86],"we":[87,107],"propose":[88,143],"a":[89,103,144,158],"novel":[90],"pipeline":[91],"that":[92],"bypasses":[93],"need":[95],"generation.":[98],"achieve":[100],"this":[101],"through":[102],"threefold":[104],"contribution:":[105],"1)":[106],"first":[108],"decompose":[109],"high-level":[111],"goals":[112],"into":[113],"smaller":[114],"atomic":[115],"tasks":[116],"generate":[118],"keyframes":[119],"aligned":[120],"instructions.":[123],"A":[124],"second":[125],"model":[127,161],"then":[128],"interpolates":[129],"between":[130,152],"each":[131],"two":[134,177],"frames,":[136],"video.":[140],"2)":[141],"semantics":[145],"preserving":[146],"attention":[147],"module":[148],"maintain":[150],"consistency":[151,183],"keyframes.":[154],"3)":[155],"design":[157],"lightweight":[159],"policy":[160,187],"regress":[163],"joint":[166],"states":[167],"from":[168],"videos.":[170],"Our":[171],"approach":[172],"achieves":[173],"state-of-the-art":[174],"results":[175],"on":[176,189],"benchmarks":[178],"quality":[181],"while":[184],"outperforming":[185],"previous":[186]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}