{"id":"https://openalex.org/W4415190520","doi":"https://doi.org/10.1109/iccv51701.2025.00605","title":"RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction","display_name":"RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415190520","doi":"https://doi.org/10.1109/iccv51701.2025.00605"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.18525","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035189764","display_name":"Yufeng Zhong","orcid":"https://orcid.org/0000-0003-2253-1497"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufeng Zhong","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101303327","display_name":"Chengjian Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengjian Feng","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101393758","display_name":"Feng Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Yan","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079874557","display_name":"Fanfan Liu","orcid":"https://orcid.org/0000-0001-5475-1465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanfan Liu","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101729358","display_name":"Liming Zheng","orcid":"https://orcid.org/0009-0009-0528-769X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liming Zheng","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100462142","display_name":"Lin Ma","orcid":"https://orcid.org/0009-0005-2568-2735"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30810522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6416","last_page":"6425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9761999845504761,"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":0.9761999845504761,"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":0.9686999917030334,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9406999945640564,"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/embodied-cognition","display_name":"Embodied cognition","score":0.704200029373169},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5600000023841858},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4839000105857849},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.39329999685287476},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.38580000400543213},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.37220001220703125},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.37059998512268066},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3449999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613999843597412},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.704200029373169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853999853134155},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4902999997138977},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.38580000400543213},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.2773999869823456},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.18525","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.18525","pdf_url":"https://arxiv.org/pdf/2503.18525","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.18525","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.18525","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.18525","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.18525","pdf_url":"https://arxiv.org/pdf/2503.18525","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,52],"language-guided":[1],"visual":[2,109],"navigation,":[3,39],"agents":[4,21,32],"locate":[5],"target":[6],"objects":[7],"in":[8,18,112,122],"unseen":[9],"environments":[10],"using":[11],"natural":[12],"language":[13,101],"instructions.":[14],"For":[15],"reliable":[16],"navigation":[17,72,80,114,125],"unfamiliar":[19],"scenes,":[20,110],"should":[22],"possess":[23],"strong":[24],"perception,":[25,63],"planning,":[26,64],"and":[27,44,65,73,93,107],"prediction":[28,66],"capabilities.":[29],"Additionally,":[30],"when":[31],"revisit":[33],"previously":[34],"explored":[35],"areas":[36],"during":[37],"long-term":[38],"they":[40],"may":[41],"retain":[42],"irrelevant":[43],"redundant":[45],"historical":[46,96],"perceptions,":[47],"leading":[48],"to":[49,91],"suboptimal":[50],"results.":[51],"this":[53],"work,":[54],"we":[55],"propose":[56],"RoboTron-Nav,":[57],"a":[58,131],"unified":[59],"framework":[60],"that":[61],"integrates":[62],"capabilities":[67],"through":[68],"multitask":[69],"collaborations":[70],"on":[71,126],"embodied":[74],"question":[75],"answering":[76],"tasks,":[77],"thereby":[78],"enhancing":[79],"performances.":[81],"Furthermore,":[82],"RoboTron-Nav":[83,103,116],"employs":[84],"an":[85,118],"adaptive":[86],"3D-aware":[87],"history":[88],"sampling":[89],"strategy":[90],"effectively":[92],"efficiently":[94],"utilize":[95],"observations.":[97],"By":[98],"leveraging":[99],"large":[100],"model,":[102],"comprehends":[104],"diverse":[105],"commands":[106],"complex":[108],"resulting":[111],"appropriate":[113],"actions.":[115],"achieves":[117],"81.1%":[119],"success":[120],"rate":[121],"object":[123],"goal":[124],"the":[127],"$\\mathrm{CHORES}$-$\\mathbb{S}$":[128],"benchmark,":[129],"setting":[130],"new":[132],"state-of-the-art":[133],"performance.":[134],"Project":[135],"page:":[136],"https://yvfengzhong.github.io/RoboTron-Nav":[137]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-15T00:00:00"}