{"id":"https://openalex.org/W4401414530","doi":"https://doi.org/10.1109/icra57147.2024.10610618","title":"CoFRIDA: Self-Supervised Fine-Tuning for Human-Robot Co-Painting","display_name":"CoFRIDA: Self-Supervised Fine-Tuning for Human-Robot Co-Painting","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414530","doi":"https://doi.org/10.1109/icra57147.2024.10610618"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610618","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/A5047422379","display_name":"Peter Schaldenbrand","orcid":"https://orcid.org/0000-0001-5296-6497"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Schaldenbrand","raw_affiliation_strings":["Carnegie Mellon University,The Robotics Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,The Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030443008","display_name":"Gaurav Parmar","orcid":"https://orcid.org/0000-0001-8640-2243"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Parmar","raw_affiliation_strings":["Carnegie Mellon University,The Robotics Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,The Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102883508","display_name":"Jun-Yan Zhu","orcid":"https://orcid.org/0000-0001-8504-3410"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-Yan Zhu","raw_affiliation_strings":["Carnegie Mellon University,The Robotics Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,The Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088609249","display_name":"James C. McCann","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James McCann","raw_affiliation_strings":["Carnegie Mellon University,The Robotics Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,The Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019807694","display_name":"Jean Oh","orcid":"https://orcid.org/0000-0001-9709-2658"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean Oh","raw_affiliation_strings":["Carnegie Mellon University,The Robotics Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,The Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2823,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95943454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2296","last_page":"2302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9901999831199646,"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"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6560006737709045},{"id":"https://openalex.org/keywords/painting","display_name":"Painting","score":0.6083741188049316},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6048810482025146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5637471675872803},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4935699701309204},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32383328676223755},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.16276824474334717},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.1357659101486206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560006737709045},{"id":"https://openalex.org/C205783811","wikidata":"https://www.wikidata.org/wiki/Q11629","display_name":"Painting","level":2,"score":0.6083741188049316},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6048810482025146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5637471675872803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4935699701309204},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32383328676223755},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.16276824474334717},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.1357659101486206}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610618","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":39,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2333722819","https://openalex.org/W2606712314","https://openalex.org/W2889450228","https://openalex.org/W3015175222","https://openalex.org/W3024462738","https://openalex.org/W3028790492","https://openalex.org/W3094335732","https://openalex.org/W3094678328","https://openalex.org/W3133059214","https://openalex.org/W3153469116","https://openalex.org/W3162981174","https://openalex.org/W3176112398","https://openalex.org/W3185440763","https://openalex.org/W3203737321","https://openalex.org/W4212774754","https://openalex.org/W4283388932","https://openalex.org/W4285102604","https://openalex.org/W4286611322","https://openalex.org/W4294891613","https://openalex.org/W4312933868","https://openalex.org/W4360991290","https://openalex.org/W4383066088","https://openalex.org/W4383682782","https://openalex.org/W4383960508","https://openalex.org/W4386076215","https://openalex.org/W4386242492","https://openalex.org/W4390874575","https://openalex.org/W4391631639","https://openalex.org/W6736562241","https://openalex.org/W6758418307","https://openalex.org/W6777259300","https://openalex.org/W6782691309","https://openalex.org/W6791353385","https://openalex.org/W6802142950","https://openalex.org/W6802645703","https://openalex.org/W6811013733","https://openalex.org/W6839643428","https://openalex.org/W6846007759"],"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":{"Prior":[0],"robot":[1,47,101],"painting":[2,48],"and":[3,16,55,97,102,114,152,169,185],"drawing":[4],"work,":[5],"such":[6],"as":[7,194],"FRIDA,":[8,163],"has":[9],"focused":[10],"on":[11],"decreasing":[12],"the":[13,23,32,43,80,95,100,112,129,143,156,182],"sim-to-real":[14,200],"gap":[15],"expanding":[17],"input":[18,33,157],"modalities":[19],"for":[20,198],"users,":[21],"but":[22],"interaction":[24],"with":[25,57,137,171],"these":[26],"systems":[27],"generally":[28],"exists":[29],"only":[30],"in":[31,79,142],"stages.":[34],"To":[35,65],"support":[36],"interactive,":[37],"human-robot":[38],"collaborative":[39],"painting,":[40],"we":[41],"introduce":[42],"Collaborative":[44],"FRIDA":[45],"(CoFRIDA)":[46],"framework,":[49],"which":[50],"can":[51,124],"co-paint":[52],"by":[53,61],"modifying":[54],"engaging":[56],"content":[58],"already":[59],"painted":[60],"a":[62,119,166,188],"human":[63,172],"collaborator.":[64],"improve":[66],"text-image":[67,134],"alignment\u2013FRIDA\u2019s":[68],"major":[69],"weakness\u2013our":[70],"system":[71],"uses":[72],"pre-trained":[73,77,132],"text-to-image":[74],"models;":[75],"however,":[76],"models":[78,136],"context":[81],"of":[82,99,131],"real-world":[83],"co-painting":[84,106,141],"do":[85,92],"not":[86,93],"perform":[87,105],"well":[88],"because":[89],"they":[90],"(1)":[91],"understand":[94],"constraints":[96,184],"abilities":[98,186],"(2)":[103],"cannot":[104],"without":[107],"making":[108],"unrealistic":[109],"edits":[110],"to":[111,139],"canvas":[113,168],"overwriting":[115],"content.":[116],"We":[117],"propose":[118],"self-supervised":[120],"fine-tuning":[121,178],"procedure":[122,179],"that":[123,154],"tackle":[125],"both":[126,164],"issues,":[127],"allowing":[128],"use":[130],"state-of-the-art":[133],"alignment":[135],"robots":[138],"enable":[140],"physical":[144],"world.":[145],"Our":[146],"open-source":[147],"approach,":[148],"CoFRIDA,":[149],"creates":[150],"paintings":[151],"drawings":[153],"match":[155],"text":[158],"prompt":[159],"more":[160],"clearly":[161],"than":[162],"from":[165],"blank":[167],"one":[170],"created":[173],"work.":[174],"More":[175],"generally,":[176],"our":[177],"successfully":[180],"encodes":[181],"robot\u2019s":[183],"into":[187],"foundation":[189],"model,":[190],"showcasing":[191],"promising":[192],"results":[193],"an":[195],"effective":[196],"method":[197],"reducing":[199],"gaps.":[201],"https://pschaldenbrand.github.io/cofrida/":[202]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}