{"id":"https://openalex.org/W7167412305","doi":"https://doi.org/10.1145/3805760.3814910","title":"VISOR: A Vision-Language Model-Based Test Oracle for Testing Robots","display_name":"VISOR: A Vision-Language Model-Based Test Oracle for Testing Robots","publication_year":2026,"publication_date":"2026-07-05","ids":{"openalex":"https://openalex.org/W7167412305","doi":"https://doi.org/10.1145/3805760.3814910"},"language":null,"primary_location":{"id":"doi:10.1145/3805760.3814910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805760.3814910","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM International Conference on AI-Powered Software","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805760.3814910","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107100741","display_name":"Prasun Saurabh","orcid":"https://orcid.org/0009-0000-7139-1043"},"institutions":[{"id":"https://openalex.org/I184531372","display_name":"OsloMet \u2013 Oslo Metropolitan University","ror":"https://ror.org/04q12yn84","country_code":"NO","type":"education","lineage":["https://openalex.org/I184531372"]},{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Prasun Saurabh","raw_affiliation_strings":["Oslo Metropolitan University, Oslo, Norway","Simula Research Laboratory, Department of Engineering Complex Software Systems, Oslo, Norway"],"raw_orcid":"https://orcid.org/0009-0000-7139-1043","affiliations":[{"raw_affiliation_string":"Oslo Metropolitan University, Oslo, Norway","institution_ids":["https://openalex.org/I184531372"]},{"raw_affiliation_string":"Simula Research Laboratory, Department of Engineering Complex Software Systems, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050340889","display_name":"Pablo Valle","orcid":"https://orcid.org/0000-0002-0588-316X"},"institutions":[{"id":"https://openalex.org/I162361429","display_name":"Mondragon Unibertsitatea","ror":"https://ror.org/00wvqgd19","country_code":"ES","type":"education","lineage":["https://openalex.org/I162361429"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Valle","raw_affiliation_strings":["Mondragon University, Mondrag\u00f3n, Spain"],"raw_orcid":"https://orcid.org/0000-0002-0588-316X","affiliations":[{"raw_affiliation_string":"Mondragon University, Mondrag\u00f3n, Spain","institution_ids":["https://openalex.org/I162361429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079122801","display_name":"Aitor Arrieta","orcid":"https://orcid.org/0000-0001-7507-5080"},"institutions":[{"id":"https://openalex.org/I162361429","display_name":"Mondragon Unibertsitatea","ror":"https://ror.org/00wvqgd19","country_code":"ES","type":"education","lineage":["https://openalex.org/I162361429"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Aitor Arrieta","raw_affiliation_strings":["Mondragon University, Mondrag\u00f3n, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7507-5080","affiliations":[{"raw_affiliation_string":"Mondragon University, Mondrag\u00f3n, Spain","institution_ids":["https://openalex.org/I162361429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076142098","display_name":"Shaukat Ali","orcid":"https://orcid.org/0000-0002-9979-3519"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Shaukat Ali","raw_affiliation_strings":["Simula Research Laboratory, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-9979-3519","affiliations":[{"raw_affiliation_string":"Simula Research Laboratory, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021486887","display_name":"Paolo Arcaini","orcid":"https://orcid.org/0000-0002-6253-4062"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Paolo Arcaini","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6253-4062","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.4918999969959259,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.4918999969959259,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.13079999387264252,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.1096000000834465,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.8925999999046326},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.8871999979019165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7053999900817871},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6660000085830688},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5049999952316284},{"id":"https://openalex.org/keywords/symbolic-execution","display_name":"Symbolic execution","score":0.48910000920295715},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4059000015258789},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.35179999470710754}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.8925999999046326},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8871999979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540000081062317},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7053999900817871},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.48910000920295715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43549999594688416},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C2984328558","wikidata":"https://www.wikidata.org/wiki/Q188522","display_name":"Software testing","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C7166840","wikidata":"https://www.wikidata.org/wiki/Q1199682","display_name":"System testing","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C169168650","wikidata":"https://www.wikidata.org/wiki/Q1675637","display_name":"Keyword-driven testing","level":5,"score":0.25600001215934753},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805760.3814910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805760.3814910","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM International Conference on AI-Powered Software","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805760.3814910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805760.3814910","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM International Conference on AI-Powered Software","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2041713059","https://openalex.org/W2077099824","https://openalex.org/W2138428785","https://openalex.org/W2493990996","https://openalex.org/W2792705209","https://openalex.org/W2798786289","https://openalex.org/W3007769740","https://openalex.org/W3042703469","https://openalex.org/W3184557462","https://openalex.org/W4200545681","https://openalex.org/W4320458302","https://openalex.org/W4391833078","https://openalex.org/W4392172801","https://openalex.org/W4399115126","https://openalex.org/W4400601342","https://openalex.org/W4401414087","https://openalex.org/W4402309652","https://openalex.org/W4402354126","https://openalex.org/W4402716288","https://openalex.org/W4404350116","https://openalex.org/W4404509535","https://openalex.org/W4405022833","https://openalex.org/W4405783861","https://openalex.org/W4405786713","https://openalex.org/W4406191642","https://openalex.org/W4406884719","https://openalex.org/W4407815020","https://openalex.org/W4411449683","https://openalex.org/W4414901575","https://openalex.org/W4415898238","https://openalex.org/W4416119086","https://openalex.org/W4416546230","https://openalex.org/W4416748491","https://openalex.org/W6948369276","https://openalex.org/W7155057654"],"related_works":[],"abstract_inverted_index":{"Testing":[0],"robots":[1],"requires":[2],"assessing":[3],"whether":[4],"they":[5],"perform":[6],"their":[7],"intended":[8],"tasks":[9,135],"correctly,":[10],"dependably,":[11],"and":[12,38,50,83,96,130,148],"with":[13],"high":[14],"quality,":[15,84],"a":[16,58],"challenge":[17],"known":[18],"as":[19],"the":[20,70,86,107],"test":[21,65,91,120],"oracle":[22,66],"problem":[23],"in":[24,110],"software":[25],"testing.":[26],"Traditionally,":[27],"this":[28],"assessment":[29,67],"relies":[30],"on":[31,39,136],"task-specific":[32,95],"symbolic":[33,90],"oracles":[34],"for":[35,63],"task":[36,81,104],"correctness":[37,82],"human":[40,74],"manual":[41],"evaluation":[42,79],"of":[43,72,80,88],"robot":[44],"behavior,":[45],"which":[46,93],"is":[47],"time-consuming,":[48],"subjective,":[49],"error-prone.":[51],"To":[52],"address":[53],"this,":[54],"we":[55],"propose":[56],"VISOR,":[57],"Vision-Language":[59],"Model":[60],"(VLM)\u2013based":[61],"approach":[62],"automated":[64,78],"that":[68,143],"eliminates":[69],"need":[71],"expensive":[73],"evaluations.":[75],"VISOR":[76,112,124],"performs":[77],"addressing":[85],"limitations":[87],"existing":[89],"oracles,":[92],"are":[94],"provide":[97],"binary":[98],"pass/fail":[99],"judgments":[100],"without":[101],"explicitly":[102,114],"quantifying":[103],"quality.":[105],"Given":[106],"inherent":[108],"uncertainty":[109,118],"VLMs,":[111,127],"also":[113],"quantifies":[115],"its":[116],"own":[117],"during":[119],"assessments.":[121],"We":[122],"evaluated":[123],"using":[125],"two":[126],"i.e.,":[128],"GPT":[129,149],"Gemini,":[131],"across":[132],"four":[133],"robotic":[134],"over":[137],"1,000":[138],"videos.":[139],"Our":[140],"results":[141],"show":[142],"Gemini":[144],"achieves":[145],"higher":[146],"recall":[147],"produces":[150],"more":[151],"precise":[152],"predictions,":[153],"while":[154],"both":[155],"models":[156],"exhibit":[157],"low":[158],"uncertainty.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-06T00:00:00"}