{"id":"https://openalex.org/W4403677113","doi":"https://doi.org/10.1109/case59546.2024.10711845","title":"Vision-language model-driven scene understanding and robotic object manipulation","display_name":"Vision-language model-driven scene understanding and robotic object manipulation","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4403677113","doi":"https://doi.org/10.1109/case59546.2024.10711845"},"language":"en","primary_location":{"id":"doi:10.1109/case59546.2024.10711845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case59546.2024.10711845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","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/A5068371109","display_name":"Sichao Liu","orcid":"https://orcid.org/0000-0002-1909-0507"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sichao Liu","raw_affiliation_strings":["KTH,Department of Production Engineering,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH,Department of Production Engineering,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075712660","display_name":"Jianjing Zhang","orcid":"https://orcid.org/0000-0002-5760-6893"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianjing Zhang","raw_affiliation_strings":["Case Western Reserve University,Department of Mechanical and Aerospace Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Western Reserve University,Department of Mechanical and Aerospace Engineering,USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060566070","display_name":"Robert X. Gao","orcid":"https://orcid.org/0000-0003-3595-3728"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert X. Gao","raw_affiliation_strings":["Case Western Reserve University,Department of Mechanical and Aerospace Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Western Reserve University,Department of Mechanical and Aerospace Engineering,USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062473662","display_name":"Xi Vincent Wang","orcid":"https://orcid.org/0000-0001-9694-0483"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xi Vincent Wang","raw_affiliation_strings":["KTH,Department of Production Engineering,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH,Department of Production Engineering,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100434965","display_name":"Lihui Wang","orcid":"https://orcid.org/0000-0001-8679-8049"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Lihui Wang","raw_affiliation_strings":["KTH,Department of Production Engineering,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH,Department of Production Engineering,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7184,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94519146,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8934000134468079,"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":0.8934000134468079,"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":0.8931999802589417,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.8309999704360962,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.7435590028762817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6392462253570557},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5994876623153687},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5794336199760437},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44727474451065063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435590028762817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6392462253570557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5994876623153687},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5794336199760437},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44727474451065063}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case59546.2024.10711845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case59546.2024.10711845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5299999713897705,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2175462310","https://openalex.org/W2340897893","https://openalex.org/W2896457183","https://openalex.org/W3010797203","https://openalex.org/W3094502228","https://openalex.org/W3098201885","https://openalex.org/W3129367582","https://openalex.org/W3144293453","https://openalex.org/W4224912544","https://openalex.org/W4283026156","https://openalex.org/W4285819600","https://openalex.org/W4303648971","https://openalex.org/W4318718936","https://openalex.org/W4323572061","https://openalex.org/W4377164392","https://openalex.org/W4377942506","https://openalex.org/W4377968606","https://openalex.org/W4382246105","https://openalex.org/W4383097638","https://openalex.org/W4383108296","https://openalex.org/W4383108457","https://openalex.org/W4383109139","https://openalex.org/W4385217308","https://openalex.org/W4385495736","https://openalex.org/W4387723654","https://openalex.org/W4391424862","https://openalex.org/W4394828156","https://openalex.org/W4395053967","https://openalex.org/W6784155536"],"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":{"Humans":[0],"often":[1],"use":[2],"natural":[3],"language":[4,70,83,141,153],"instructions":[5,31,154],"to":[6,20,24,57,64,108,117,146],"control":[7,149],"and":[8,28,41,91,112,119,131,151],"interact":[9],"with":[10,155],"robots":[11,21],"for":[12,88,158],"task":[13],"execution.":[14],"This":[15],"poses":[16],"a":[17,52,72,105,138,175],"big":[18],"challenge":[19],"that":[22],"need":[23],"not":[25],"only":[26],"parse":[27],"understand":[29],"human":[30],"but":[32],"also":[33],"realise":[34],"semantic":[35],"understanding":[36,59],"of":[37,60,101,122,135,163],"an":[38,61],"unknown":[39,62],"environment":[40,63],"its":[42],"constituent":[43],"elements.":[44],"To":[45],"address":[46],"this":[47,49],"challenge,":[48],"study":[50],"presents":[51],"vision-language":[53,74],"model":[54,75,84,142],"(VLM)-driven":[55],"approach":[56,107,166],"scene":[58,92,126],"enable":[65],"robotic":[66],"object":[67,113,172],"manipulation.":[68],"Given":[69],"instructions,":[71],"pre-tained":[73],"built":[76],"on":[77],"open-sourced":[78],"Llama2-chat":[79],"(7B)":[80],"as":[81],"the":[82,102,125,136,164],"backbone":[85],"is":[86,115,144,167],"adopted":[87,145],"image":[89],"description":[90],"understanding,":[93],"which":[94],"translates":[95],"visual":[96,110],"information":[97],"into":[98],"text":[99],"descriptions":[100],"scene.":[103],"Next,":[104],"zero-shot-based":[106],"fine-grained":[109],"grounding":[111],"detection":[114],"developed":[116,165],"extract":[118],"localise":[120],"objects":[121],"interest":[123],"from":[124],"task.":[127],"Upon":[128],"3D":[129],"reconstruction":[130],"pose":[132],"estimate":[133],"establishment":[134],"object,":[137],"code-writing":[139],"large":[140],"(LLM)":[143],"generate":[147],"high-level":[148],"codes":[150],"link":[152],"robot":[156],"actions":[157],"downstream":[159],"tasks.":[160],"The":[161],"performance":[162],"experimentally":[168],"validated":[169],"through":[170],"table-top":[171],"manipulation":[173],"by":[174],"robot.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}