{"id":"https://openalex.org/W7134846821","doi":"https://doi.org/10.48550/arxiv.2603.08475","title":"R2F: Repurposing Ray Frontiers for LLM-free Object Navigation","display_name":"R2F: Repurposing Ray Frontiers for LLM-free Object Navigation","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134846821","doi":"https://doi.org/10.48550/arxiv.2603.08475"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.08475","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069605954","display_name":"Francesco Argenziano","orcid":"https://orcid.org/0009-0004-2028-7253"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Argenziano, Francesco","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128668870","display_name":"John Mark Alexis Marcelo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcelo, John Mark Alexis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073429310","display_name":"Michele Brienza","orcid":"https://orcid.org/0009-0000-1549-9500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brienza, Michele","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117491142","display_name":"Abdel Hakim Drid","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Drid, Abdel Hakim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033491329","display_name":"Emanuele Musumeci","orcid":"https://orcid.org/0009-0004-2359-5032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Musumeci, Emanuele","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128677217","display_name":"Daniele Nardi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nardi, Daniele","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012452119","display_name":"Domenico D. Bloisi","orcid":"https://orcid.org/0000-0003-0339-8651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bloisi, Domenico D.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030500376","display_name":"Vincenzo Suriani","orcid":"https://orcid.org/0000-0003-1199-8358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suriani, Vincenzo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5069605954"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9671000242233276,"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":0.9671000242233276,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.010099999606609344,"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/T10028","display_name":"Topic Modeling","score":0.0024999999441206455,"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/inference","display_name":"Inference","score":0.5921000242233276},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5346999764442444},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5023999810218811},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42149999737739563},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3846000134944916},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3797999918460846},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.37470000982284546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805899977684021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003000140190125},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42149999737739563},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C519536355","wikidata":"https://www.wikidata.org/wiki/Q21021151","display_name":"Repurposing","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.08475","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.08475","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.08475","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.08475","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"open-vocabulary":[1,74],"object":[2,75],"navigation":[3,104,131],"has":[4],"progressed":[5],"rapidly":[6],"with":[7,189],"the":[8],"emergence":[9],"of":[10,27],"large":[11],"Vision-Language":[12],"Models":[13,18],"(VLMs)":[14],"and":[15,45,138,145,166,178],"Large":[16],"Language":[17],"(LLMs),":[19],"now":[20],"widely":[21],"used":[22,82],"as":[23,96,103],"high-level":[24],"decision-makers":[25],"instead":[26],"end-to-end":[28],"policies.":[29],"Although":[30],"effective,":[31],"such":[32],"systems":[33],"often":[34],"rely":[35],"on":[36,179],"iterative":[37,149],"large-model":[38,150],"queries":[39],"at":[40,115],"inference":[41],"time,":[42],"introducing":[43],"latency":[44],"computational":[46],"overhead":[47],"that":[48,101],"limit":[49],"real-time":[50,190],"deployment.":[51],"To":[52],"address":[53],"this":[54,129],"problem,":[55],"we":[56,92],"repurpose":[57],"ray":[58,78],"frontiers":[59,79],"(R2F),":[60],"a":[61,142,156,180],"recently":[62],"proposed":[63],"frontier-based":[64],"exploration":[65,85],"paradigm,":[66],"to":[67,83,134,194],"develop":[68],"an":[69],"LLM-free":[70],"framework":[71],"for":[72,159],"indoor":[73],"navigation.":[76],"While":[77],"were":[80],"originally":[81],"bias":[84],"using":[86,163],"semantic":[87,99],"cues":[88],"carried":[89],"along":[90,109],"rays,":[91],"reinterpret":[93],"frontier":[94,136],"regions":[95],"explicit,":[97],"direction-conditioned":[98],"hypotheses":[100],"serve":[102],"goals.":[105],"Language-aligned":[106],"features":[107],"accumulated":[108],"out-of-range":[110],"rays":[111],"are":[112],"stored":[113],"sparsely":[114],"frontiers,":[116],"where":[117],"each":[118],"region":[119],"maintains":[120],"multiple":[121],"directional":[122],"embeddings":[123],"encoding":[124],"plausible":[125],"unseen":[126],"content.":[127],"In":[128],"way,":[130],"then":[132],"reduces":[133],"embedding-based":[135],"scoring":[137],"goal":[139],"tracking":[140],"within":[141],"classical":[143],"mapping":[144],"planning":[146],"pipeline,":[147],"eliminating":[148],"reasoning.":[151],"We":[152],"further":[153],"introduce":[154],"R2F-VLN,":[155],"lightweight":[157],"extension":[158],"free-form":[160],"language":[161],"instructions":[162],"syntactic":[164],"parsing":[165],"relational":[167],"verification":[168],"without":[169],"additional":[170],"VLM":[171],"or":[172],"LLM":[173],"components.":[174],"Experiments":[175],"in":[176],"Habitat-sim":[177],"real":[181],"robotic":[182],"platform":[183],"demonstrate":[184],"competitive":[185],"state-of-the-art":[186],"zero-shot":[187],"performance":[188],"execution,":[191],"achieving":[192],"up":[193],"6":[195],"times":[196],"faster":[197],"runtime":[198],"than":[199],"VLM-based":[200],"alternatives.":[201]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-03-11T00:00:00"}