{"id":"https://openalex.org/W4403296141","doi":"https://doi.org/10.1109/iwis62722.2024.10706068","title":"Generating Robot Action Sequences: An Efficient Vision-Language Models with Visual Prompts","display_name":"Generating Robot Action Sequences: An Efficient Vision-Language Models with Visual Prompts","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4403296141","doi":"https://doi.org/10.1109/iwis62722.2024.10706068"},"language":"en","primary_location":{"id":"doi:10.1109/iwis62722.2024.10706068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwis62722.2024.10706068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Workshop on Intelligent Systems (IWIS)","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/A5113427543","display_name":"Weihao CAI","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Weihao CAI","raw_affiliation_strings":["Ritsumeikan University,Interaction Laboratory,Osaka,Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Interaction Laboratory,Osaka,Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036073690","display_name":"Yoshiki Mori","orcid":"https://orcid.org/0000-0002-6223-8634"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiki MORI","raw_affiliation_strings":["Ritsumeikan University,Interaction Laboratory,Osaka,Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Interaction Laboratory,Osaka,Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032660436","display_name":"Nobutaka Shimada","orcid":"https://orcid.org/0000-0002-1100-087X"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka SHIMADA","raw_affiliation_strings":["Ritsumeikan University,Interaction Laboratory,Osaka,Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Interaction Laboratory,Osaka,Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113427543"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54841683,"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":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9914000034332275,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9850999712944031,"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":0.7649247050285339},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6520488262176514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5902716517448425},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5902420878410339},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5890927314758301},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4894210398197174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649247050285339},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6520488262176514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5902716517448425},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5902420878410339},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5890927314758301},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4894210398197174},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwis62722.2024.10706068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwis62722.2024.10706068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Workshop on Intelligent Systems (IWIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1520597402","https://openalex.org/W2045146498","https://openalex.org/W3168867926","https://openalex.org/W4312933868","https://openalex.org/W4318718936","https://openalex.org/W4364383163","https://openalex.org/W4379958270","https://openalex.org/W4386320380","https://openalex.org/W4387800098","https://openalex.org/W4389218004","https://openalex.org/W4389520252","https://openalex.org/W4392538897","https://openalex.org/W6849177959","https://openalex.org/W6852293568","https://openalex.org/W6853242345","https://openalex.org/W6857660107","https://openalex.org/W6858576426","https://openalex.org/W6862193169"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2772917594","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","https://openalex.org/W2775347418"],"abstract_inverted_index":{"This":[0,67],"paper":[1,68],"focuses":[2],"on":[3,107],"equipping":[4],"robots":[5],"with":[6,29,49],"the":[7,88,108,137],"capability":[8],"to":[9,111],"comprehend":[10],"human":[11],"commands,":[12],"plan":[13],"appropriate":[14],"actions,":[15],"and":[16,81,114,152],"execute":[17],"them":[18],"effectively.":[19],"Recent":[20],"research":[21],"advances":[22],"suggest":[23],"that":[24],"Large":[25],"Language":[26,31],"Models":[27,83],"(LLMs)":[28],"Visual":[30],"Model":[32],"(VLM)":[33],"components":[34],"show":[35],"promising":[36,147],"prospects":[37],"in":[38,118,131],"robot":[39,154],"task":[40,139],"planning.":[41],"However,":[42],"they":[43],"sometimes":[44],"encounter":[45],"difficulties":[46],"when":[47],"dealing":[48],"ambiguous":[50],"scenarios,":[51],"such":[52],"as":[53,100],"understanding":[54,91],"spatial":[55],"relationships":[56],"between":[57,61],"objects":[58],"or":[59,123],"distinguishing":[60],"different":[62],"degrees":[63],"of":[64,96,120],"drawer":[65],"openings.":[66],"presents":[69],"a":[70,94,146],"novel":[71],"approach":[72,86],"for":[73,149],"generating":[74],"robot-executable":[75],"action":[76,104,121],"sequences":[77,105,117],"using":[78,93],"visual":[79],"prompts":[80],"Vision-Language":[82],"(VLMs).":[84],"Our":[85],"enhances":[87],"robot's":[89,138],"environmental":[90],"by":[92],"set":[95],"annotations":[97],"(boxes,":[98],"labels)":[99],"input.":[101],"It":[102],"generates":[103],"based":[106],"current":[109],"environment":[110],"achieve":[112],"goals":[113],"creates":[115],"new":[116],"case":[119],"failure":[122],"external":[124],"disturbances.":[125],"Experimental":[126],"results":[127],"demonstrate":[128],"outstanding":[129],"performance":[130],"executing":[132],"complex":[133],"tasks,":[134],"significantly":[135],"improving":[136],"completion":[140],"capabilities.":[141],"The":[142],"proposed":[143],"technique":[144],"offers":[145],"solution":[148],"more":[150],"efficient":[151],"adaptable":[153],"behavior":[155],"acquisition.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}