{"id":"https://openalex.org/W4416748995","doi":"https://doi.org/10.1109/iros60139.2025.11247165","title":"Navi2Gaze: Leveraging Foundation Models for Navigation and Target Gazing","display_name":"Navi2Gaze: Leveraging Foundation Models for Navigation and Target Gazing","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748995","doi":"https://doi.org/10.1109/iros60139.2025.11247165"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5002320979","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0001-8944-2355"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039510234","display_name":"Zihao Du","orcid":"https://orcid.org/0000-0002-3981-7160"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Du","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073768917","display_name":"Haotian Xu","orcid":"https://orcid.org/0000-0001-8336-4536"},"institutions":[{"id":"https://openalex.org/I4210136277","display_name":"Institute of Space and Astronautical Science","ror":"https://ror.org/034gcgw60","country_code":"JP","type":"facility","lineage":["https://openalex.org/I2800865746","https://openalex.org/I4210136277"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haotian Xu","raw_affiliation_strings":["Beijing Institute of Astronautical Systems Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Astronautical Systems Engineering","institution_ids":["https://openalex.org/I4210136277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045706166","display_name":"Fengbo Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengbo Lan","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056521090","display_name":"Zilong Zheng","orcid":"https://orcid.org/0000-0003-1219-5151"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong Zheng","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109297964","display_name":"Bo Ma","orcid":"https://orcid.org/0000-0001-9939-8685"},"institutions":[{"id":"https://openalex.org/I4210094459","display_name":"Craft Group (China)","ror":"https://ror.org/00gxm5663","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210094459"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ma","raw_affiliation_strings":["Chengdu Aircraft Design &amp; Research Institute,National Key Laboratory of Digital and Agile Aircraft Design AVIC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chengdu Aircraft Design &amp; Research Institute,National Key Laboratory of Digital and Agile Aircraft Design AVIC","institution_ids":["https://openalex.org/I4210094459"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042476440","display_name":"Shengjie Wang","orcid":"https://orcid.org/0000-0002-9311-102X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjie Wang","raw_affiliation_strings":["Tsinghua University,Institute for Interdisciplinary Information Sciences (IIIS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for Interdisciplinary Information Sciences (IIIS)","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034894860","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-3870-4607"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Tsinghua University,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.42373472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20394","last_page":"20401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6202999949455261,"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":0.6202999949455261,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.18770000338554382,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.061400000005960464,"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/orientation","display_name":"Orientation (vector space)","score":0.7085000276565552},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6919999718666077},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5304999947547913},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5015000104904175},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4505000114440918},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.44440001249313354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495999932289124},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.7085000276565552},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6919999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6539000272750854},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5242999792098999},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5002999901771545},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.44440001249313354},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2119344328","https://openalex.org/W2895439318","https://openalex.org/W3008770127","https://openalex.org/W3009928773","https://openalex.org/W4226344024","https://openalex.org/W4285192809","https://openalex.org/W4312956471","https://openalex.org/W4383108296","https://openalex.org/W4383108538","https://openalex.org/W4383108895","https://openalex.org/W4385416186","https://openalex.org/W4386066287","https://openalex.org/W4386075737","https://openalex.org/W4390204337","https://openalex.org/W4390873481","https://openalex.org/W4390874575","https://openalex.org/W4391451889","https://openalex.org/W4401413959","https://openalex.org/W4401417236","https://openalex.org/W4409261941"],"related_works":[],"abstract_inverted_index":{"Task-aware":[0],"navigation":[1,114],"continues":[2],"to":[3,52,60,86,127,157,167],"be":[4,174],"a":[5,54,75,106,162],"challenging":[6],"area":[7],"of":[8,31,46,82],"research,":[9],"especially":[10],"in":[11,80,161,165],"scenarios":[12],"involving":[13],"open":[14,53],"vocabulary.":[15],"Previous":[16],"studies":[17],"primarily":[18],"focus":[19],"on":[20,119,140,176],"finding":[21],"suitable":[22],"locations":[23],"for":[24,41,112],"task":[25,120],"completion,":[26],"often":[27],"overlooking":[28],"the":[29,32,36,63,87,125,131,153,177],"importance":[30],"robot\u2019s":[33,37],"pose.":[34],"However,":[35],"orientation":[38,65,155],"is":[39],"crucial":[40],"successfully":[42],"completing":[43],"tasks":[44],"because":[45],"how":[47],"objects":[48,61],"are":[49],"arranged":[50],"(e.g.,":[51],"refrigerator":[55],"door).":[56],"Humans":[57],"intuitively":[58],"navigate":[59],"with":[62,99],"right":[64],"using":[66],"semantics":[67],"and":[68,115,129],"common":[69,101],"sense.":[70,102],"For":[71],"instance,":[72],"when":[73],"opening":[74],"refrigerator,":[76],"we":[77,104],"naturally":[78],"stand":[79],"front":[81],"it":[83],"rather":[84],"than":[85],"side.":[88],"Recent":[89],"advances":[90],"suggest":[91],"that":[92],"Vision-Language":[93],"Models":[94],"(VLMs)":[95],"can":[96,173],"provide":[97],"robots":[98],"similar":[100],"Therefore,":[103],"develop":[105],"VLM-driven":[107],"method":[108,123],"called":[109],"Navigation-to-Gaze":[110],"(Navi2Gaze)":[111],"efficient":[113],"object":[116],"gazing":[117],"based":[118],"descriptions.":[121],"This":[122],"uses":[124],"VLM":[126],"score":[128],"select":[130],"best":[132],"pose":[133],"from":[134],"numerous":[135],"candidates":[136],"automatically.":[137],"In":[138],"evaluations":[139],"multiple":[141],"photorealistic":[142],"simulation":[143],"benchmarks,":[144],"Navi2Gaze":[145],"significantly":[146],"outperforms":[147],"existing":[148],"approaches":[149],"by":[150],"precisely":[151],"determining":[152],"optimal":[154],"relative":[156],"target":[158],"objects,":[159],"resulting":[160],"68.8%":[163],"reduction":[164],"Distance":[166],"Goal":[168],"(DTG).":[169],"Real-world":[170],"video":[171],"demonstrations":[172],"found":[175],"supplementary":[178],"website1.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}
