{"id":"https://openalex.org/W4413393736","doi":"https://doi.org/10.23919/acc63710.2025.11107751","title":"Robot Failure Recovery Using Vision-Language Models With Optimized Prompts","display_name":"Robot Failure Recovery Using Vision-Language Models With Optimized Prompts","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393736","doi":"https://doi.org/10.23919/acc63710.2025.11107751"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107751","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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/A5100428541","display_name":"Hongyi Chen","orcid":"https://orcid.org/0000-0001-8241-6648"},"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":true,"raw_author_name":"Hongyi Chen","raw_affiliation_strings":["Carnegie Mellon University,Robotics Institute"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033459015","display_name":"Yunchao Yao","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":"Yunchao Yao","raw_affiliation_strings":["Carnegie Mellon University,Robotics Institute"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101507732","display_name":"Ruixuan Liu","orcid":"https://orcid.org/0000-0001-6249-5473"},"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":"Ruixuan Liu","raw_affiliation_strings":["Carnegie Mellon University,Robotics Institute"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040156274","display_name":"Changliu Liu","orcid":"https://orcid.org/0000-0002-3767-5517"},"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":"Changliu Liu","raw_affiliation_strings":["Carnegie Mellon University,Robotics Institute"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005587345","display_name":"Jeffrey Ichnowski","orcid":"https://orcid.org/0000-0003-4874-9478"},"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":"Jeffrey Ichnowski","raw_affiliation_strings":["Carnegie Mellon University,Robotics Institute"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Robotics Institute","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100428541"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84594979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1983","last_page":"1988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9717000126838684,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9717000126838684,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9682999849319458,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.957099974155426,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230662107467651},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.60284823179245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47534677386283875},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.428041934967041},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38885438442230225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230662107467651},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.60284823179245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47534677386283875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.428041934967041},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38885438442230225}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107751","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306185","display_name":"Richard King Mellon Foundation","ror":"https://ror.org/03qevzg44"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3099659757","https://openalex.org/W3189000042","https://openalex.org/W4285124275","https://openalex.org/W4312424618","https://openalex.org/W4378574344","https://openalex.org/W4401417251","https://openalex.org/W4401987865","https://openalex.org/W4402354098","https://openalex.org/W4402354151","https://openalex.org/W4402716288","https://openalex.org/W4405785183"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"Current":[0],"robot":[1,113],"autonomy":[2],"struggles":[3],"to":[4,26,38,53,102,112,139,206,229],"operate":[5],"beyond":[6],"the":[7,13,22,29,65,132,157,177,218],"assumed":[8],"Operational":[9],"Design":[10],"Domain":[11],"(ODD),":[12],"specific":[14,68],"set":[15],"of":[16,61,67,75,135,243],"conditions":[17],"and":[18,64,88,115,127,150,175,183,200,224,234],"environments":[19],"in":[20,98,164,170,195,226,246],"which":[21,76,83],"system":[23],"is":[24,31],"designed":[25],"function,":[27],"while":[28],"real-world":[30],"rife":[32],"with":[33,208],"uncertainties":[34],"that":[35],"may":[36],"lead":[37],"failures.":[39,155],"Automating":[40],"recovery":[41,69,152,236],"remains":[42],"a":[43,104,240],"significant":[44],"challenge.":[45],"Traditional":[46],"methods":[47],"often":[48],"rely":[49],"on":[50],"human":[51],"intervention":[52],"manually":[54],"address":[55],"failures":[56],"or":[57],"require":[58],"exhaustive":[59],"enumeration":[60],"failure":[62,181],"cases":[63],"design":[66],"policies":[70],"for":[71,107,145,173,180,212],"each":[72],"scenario,":[73],"both":[74,146],"are":[77],"labor-intensive.":[78],"Foundational":[79],"Vision-Language":[80],"Models":[81,194],"(VLMs),":[82],"demonstrate":[84],"remarkable":[85],"common-sense":[86],"generalization":[87],"reasoning":[89,100,134,178],"capabilities,":[90],"have":[91],"broader,":[92],"potentially":[93],"unbounded":[94],"ODDs.":[95],"However,":[96],"limitations":[97],"spatial":[99,133],"continue":[101],"be":[103],"common":[105],"challenge":[106],"many":[108],"VLMs":[109,207],"when":[110],"applied":[111],"control":[114,184],"motion-level":[116,147,197],"error":[117],"recovery.":[118],"In":[119,186],"this":[120],"paper,":[121],"we":[122],"investigate":[123],"how":[124],"optimizing":[125],"visual":[126,162,165],"text":[128,171],"prompts":[129,172,216],"can":[130],"enhance":[131],"VLMs,":[136],"enabling":[137],"them":[138],"function":[140],"effectively":[141],"as":[142],"black-box":[143],"controllers":[144],"position":[148,198],"correction":[149],"task-level":[151,213],"from":[153],"unknown":[154,244],"Specifically,":[156],"optimizations":[158,189],"include":[159],"identifying":[160],"key":[161],"elements":[163,169],"prompts,":[166],"highlighting":[167],"these":[168],"querying,":[174],"decomposing":[176],"process":[179],"detection":[182],"generation.":[185],"experiments,":[187],"prompt":[188],"significantly":[190],"outperform":[191],"pre-trained":[192],"Vision-Language-Action":[193],"correcting":[196],"errors":[199,245],"improve":[201],"accuracy":[202],"by":[203,221],"65.78%":[204],"compared":[205],"unoptimized":[209],"prompts.":[210],"Additionally,":[211],"failures,":[214,231],"optimized":[215],"enhanced":[217],"success":[219],"rate":[220],"5.8%,":[222,223],"7.5%":[225],"VLMs\u2019":[227],"abilities":[228],"detect":[230],"analyze":[232],"issues,":[233],"generate":[235],"plans,":[237],"respectively,":[238],"across":[239],"wide":[241],"range":[242],"Lego":[247],"assembly.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}