{"id":"https://openalex.org/W4401416094","doi":"https://doi.org/10.1109/icra57147.2024.10611121","title":"MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation","display_name":"MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416094","doi":"https://doi.org/10.1109/icra57147.2024.10611121"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5050178343","display_name":"Patrick Lancaster","orcid":"https://orcid.org/0000-0003-3398-132X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Patrick Lancaster","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086722753","display_name":"Nicklas Hansen","orcid":"https://orcid.org/0000-0001-9897-4003"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicklas Hansen","raw_affiliation_strings":["University of California,San Diego"],"affiliations":[{"raw_affiliation_string":"University of California,San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732794","display_name":"Aravind Rajeswaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aravind Rajeswaran","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383672","display_name":"Vikash Kumar","orcid":"https://orcid.org/0000-0002-3168-7955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vikash Kumar","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050178343"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5798,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83101351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7530","last_page":"7537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9922999739646912,"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/T11687","display_name":"Teleoperation and Haptic Systems","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/computer-science","display_name":"Computer science","score":0.628797709941864},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5515817403793335},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38934677839279175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38312414288520813},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33823081851005554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.628797709941864},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5515817403793335},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38934677839279175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38312414288520813},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33823081851005554}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":51,"referenced_works":["https://openalex.org/W1540685400","https://openalex.org/W2201912979","https://openalex.org/W2605102758","https://openalex.org/W2778821583","https://openalex.org/W2788084076","https://openalex.org/W2902125520","https://openalex.org/W2910781732","https://openalex.org/W2920362155","https://openalex.org/W2952629144","https://openalex.org/W2962736495","https://openalex.org/W2963411833","https://openalex.org/W2968340082","https://openalex.org/W2985692297","https://openalex.org/W2989847975","https://openalex.org/W3009331570","https://openalex.org/W3035060554","https://openalex.org/W3047403664","https://openalex.org/W3116043511","https://openalex.org/W3118210634","https://openalex.org/W3175254947","https://openalex.org/W3195968524","https://openalex.org/W3208460365","https://openalex.org/W4212774754","https://openalex.org/W4221164079","https://openalex.org/W4252189904","https://openalex.org/W4287209565","https://openalex.org/W4287553323","https://openalex.org/W4294562617","https://openalex.org/W4298206671","https://openalex.org/W4307078757","https://openalex.org/W4307537902","https://openalex.org/W4311429168","https://openalex.org/W4383108265","https://openalex.org/W4383109237","https://openalex.org/W4385430679","https://openalex.org/W4385430825","https://openalex.org/W4387561527","https://openalex.org/W6632235069","https://openalex.org/W6748839928","https://openalex.org/W6751494529","https://openalex.org/W6751535212","https://openalex.org/W6754184789","https://openalex.org/W6756256016","https://openalex.org/W6761443123","https://openalex.org/W6767997047","https://openalex.org/W6779756738","https://openalex.org/W6796613488","https://openalex.org/W6802366246","https://openalex.org/W6803162731","https://openalex.org/W6803519892","https://openalex.org/W6810080435"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Robotic":[0],"systems":[1,20,64],"that":[2,99],"aspire":[3],"to":[4,22,69,93,113],"operate":[5],"in":[6,78,125,136,153,164,188,194,220],"uninstrumented":[7,127],"real-world":[8,80,169],"environments":[9,74],"must":[10],"perceive":[11],"the":[12,24,35,43,56,79,82,107,126,132,154,183,198,202,210,221],"world":[13,36],"directly":[14,124,152,219],"via":[15],"onboard":[16],"sensing.":[17],"Vision-based":[18],"learning":[19,121,139,166],"aim":[21],"eliminate":[23],"need":[25],"for":[26,161,214,226],"environment":[27],"instrumentation":[28],"by":[29],"building":[30],"an":[31],"implicit":[32],"understanding":[33],"of":[34,58,62,84,120,185,204],"based":[37],"on":[38,131],"raw":[39],"pixels,":[40],"but":[41],"navigating":[42],"contact-rich":[44,122,148],"high-dimensional":[45],"search":[46],"space":[47],"from":[48],"solely":[49],"sparse":[50],"visual":[51,216],"reward":[52],"signals":[53],"significantly":[54],"exacerbates":[55],"challenge":[57],"exploration.":[59],"The":[60],"applicability":[61],"such":[63],"is":[65],"thus":[66],"typically":[67],"restricted":[68],"simulated":[70],"or":[71],"heavily":[72],"engineered":[73],"since":[75],"agent":[76],"exploration":[77,173],"without":[81],"guidance":[83],"explicit":[85],"state":[86],"estimation":[87],"and":[88,96,142,177,197,228],"dense":[89],"rewards":[90],"can":[91,146],"lead":[92],"unsafe":[94],"behavior":[95],"safety":[97,170],"faults":[98],"are":[100],"catastrophic.":[101],"In":[102],"this":[103],"study,":[104],"we":[105],"isolate":[106],"root":[108],"causes":[109],"behind":[110],"these":[111,186],"limitations":[112],"develop":[114],"a":[115],"system,":[116],"called":[117],"MoDem-V2,":[118],"capable":[119],"manipulation":[123,150,192],"real":[128,155,199,222],"world.":[129,156,200,223],"Building":[130],"latest":[133],"algorithmic":[134],"advancements":[135],"model-based":[137],"reinforcement":[138],"(MBRL),":[140],"demo-bootstrapping,":[141],"effective":[143],"exploration,":[144],"MoDem-V2":[145],"acquire":[147],"dexterous":[149],"skills":[151],"We":[157,180],"identify":[158],"key":[159],"ingredients":[160,187],"leveraging":[162],"demonstrations":[163],"model":[165],"while":[167],"respecting":[168],"considerations":[171],"\u2013":[172],"centering,":[174],"agency":[175],"handover,":[176],"actor-critic":[178],"ensembles.":[179],"empirically":[181],"demonstrate":[182],"contribution":[184],"four":[189],"complex":[190],"visuo-motor":[191],"problems":[193],"both":[195],"simulation":[196],"To":[201],"best":[203],"our":[205,207],"knowledge,":[206],"work":[208],"presents":[209],"first":[211],"successful":[212],"system":[213],"demonstration-augmented":[215],"MBRL":[217],"trained":[218],"Visit":[224],"sites.google.com/view/modem-v2":[225],"videos":[227],"more":[229],"details.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}