{"id":"https://openalex.org/W4413926275","doi":"https://doi.org/10.1109/icra55743.2025.11128671","title":"SpatialBot: Precise Spatial Understanding with Vision Language Models","display_name":"SpatialBot: Precise Spatial Understanding with Vision Language Models","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413926275","doi":"https://doi.org/10.1109/icra55743.2025.11128671"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5006542544","display_name":"Wenxiao Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CA","CN"],"is_corresponding":true,"raw_author_name":"Wenxiao Cai","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104261352","display_name":"Iaroslav Ponomarenko","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Iaroslav Ponomarenko","raw_affiliation_strings":["Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027913576","display_name":"Jianhao Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianhao Yuan","raw_affiliation_strings":["University of Oxford,England"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,England","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634697","display_name":"Xiaoqi Li","orcid":"https://orcid.org/0000-0001-7462-6303"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqi Li","raw_affiliation_strings":["Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748706","display_name":"Wankou Yang","orcid":"https://orcid.org/0000-0002-6385-6776"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wankou Yang","raw_affiliation_strings":["Southeast University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389347","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-0132-0239"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Dong","raw_affiliation_strings":["Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103114339","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-2120-2571"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5006542544"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210164862"],"apc_list":null,"apc_paid":null,"fwci":17.5089,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.99368749,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9490","last_page":"9498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9864000082015991,"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":0.9864000082015991,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.958899974822998,"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/T12031","display_name":"Speech and dialogue systems","score":0.9567999839782715,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6900544762611389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4763655662536621},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3877820372581482},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.329248309135437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900544762611389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4763655662536621},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3877820372581482},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.329248309135437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8877833081","display_name":null,"funder_award_id":"62306046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2099940712","https://openalex.org/W2102127923","https://openalex.org/W2111650091","https://openalex.org/W2428327932","https://openalex.org/W2955399703","https://openalex.org/W2955639361","https://openalex.org/W2963488291","https://openalex.org/W2963518342","https://openalex.org/W2998859407","https://openalex.org/W3016211260","https://openalex.org/W3027647924","https://openalex.org/W3035198432","https://openalex.org/W4389523832","https://openalex.org/W4390874575","https://openalex.org/W4401417048","https://openalex.org/W4402354047","https://openalex.org/W4402727730","https://openalex.org/W4405785328","https://openalex.org/W4407690624","https://openalex.org/W4408741774","https://openalex.org/W4409346388"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Vision":[0],"Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"achieved":[5],"impressive":[6],"performance":[7],"in":[8],"2D":[9],"image":[10],"understanding;":[11],"however,":[12],"they":[13],"still":[14],"struggle":[15],"with":[16],"spatial":[17,36,80],"understanding,":[18],"which":[19,61],"is":[20,73],"fundamental":[21],"to":[22,34,76],"embodied":[23,96],"AI.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,51],"propose":[29],"SpatialBot,":[30],"a":[31],"model":[32],"designed":[33],"enhance":[35],"understanding":[37,81],"by":[38,104],"utilizing":[39],"both":[40],"RGB":[41],"and":[42,55,69,95,109],"depth":[43,49],"images.":[44],"To":[45],"train":[46],"VLMs":[47],"for":[48],"perception,":[50],"introduce":[52],"the":[53,100],"SpatialQA":[54,56],"<tex":[57],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[58],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\boldsymbol{E}$</tex>":[59],"datasets,":[60],"include":[62],"multi-level":[63],"depth-related":[64],"questions":[65],"spanning":[66],"various":[67],"scenarios":[68],"embodiment":[70],"tasks.":[71],"SpatialBench":[72],"also":[74],"developed":[75],"comprehensively":[77],"evaluate":[78],"VLMs'":[79],"capabilities":[82],"across":[83],"different":[84],"levels.":[85],"Extensive":[86],"experiments":[87],"on":[88],"our":[89],"spatial-understanding":[90],"benchmark,":[91],"general":[92],"VLM":[93],"benchmarks,":[94],"AI":[97],"tasks":[98],"demonstrate":[99],"remarkable":[101],"improvements":[102],"offered":[103],"SpatialBot.":[105],"The":[106],"model,":[107],"code,":[108],"datasets":[110],"are":[111],"available":[112],"at":[113],"https://github.com/BAAI-DCAI/SpatialBot.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}