{"id":"https://openalex.org/W7214754129","doi":"https://doi.org/10.48550/arxiv.2609.32292","title":"Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation","display_name":"Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214754129","doi":"https://doi.org/10.48550/arxiv.2609.32292"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32292","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32292","pdf_url":"https://arxiv.org/pdf/2609.32292","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.32292","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127239085","display_name":"Xuekang Yang","orcid":"https://orcid.org/0000-0002-7318-8927","observed_orcids":["https://orcid.org/0000-0002-7318-8927"]},"institutions":[{"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":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Xuekang","raw_affiliation_strings":["School of Computer Science , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153530200","display_name":"Lu Chen","orcid":null,"observed_orcids":[]},"institutions":[{"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":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Lu","raw_affiliation_strings":["School of Computer Science , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153405840","display_name":"Shuang Luo","orcid":null,"observed_orcids":[]},"institutions":[{"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":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Shuang","raw_affiliation_strings":["School of Computer Science , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147583712","display_name":"Jialing Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"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":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Jialing","raw_affiliation_strings":["School of Automation and Intelligent Sensing , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153452797","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0002-1037-1361","observed_orcids":["https://orcid.org/0000-0002-1037-1361"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qi","raw_affiliation_strings":["Defense Innovation Institute , Academy of Military Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute , Academy of Military Sciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153416451","display_name":"Yue Gao","orcid":null,"observed_orcids":[]},"institutions":[{"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":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Yue","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence and AI Institute , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence and AI Institute , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153405625","display_name":"Xiang Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiang","raw_affiliation_strings":["Defense Innovation Institute , Academy of Military Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute , Academy of Military Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5684000253677368,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5684000253677368,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1160999983549118,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.1096000000834465,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/vision-and-language-navigation","display_name":"vision-and-language navigation","score":0.9779999852180481},{"id":"https://openalex.org/keywords/post-training","display_name":"post-training","score":0.5740000009536743},{"id":"https://openalex.org/keywords/embodied-agents","display_name":"embodied agents","score":0.5709999799728394}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.8930000066757202},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8616999983787537},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.7935000061988831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372000217437744},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5546000003814697},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4307999908924103},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.35839998722076416},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C9354725","wikidata":"https://www.wikidata.org/wiki/Q286017","display_name":"Operationalization","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32292","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32292","pdf_url":"https://arxiv.org/pdf/2609.32292","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,"listed_in":[],"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.2609.32292","doi":"https://doi.org/10.48550/arxiv.2609.32292","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32292","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.32292","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32292","pdf_url":"https://arxiv.org/pdf/2609.32292","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214754129.pdf","grobid_xml":"https://content.openalex.org/works/W7214754129.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4402353981","https://openalex.org/W4412795922","https://openalex.org/W4413847149","https://openalex.org/W4413926193","https://openalex.org/W4415913019","https://openalex.org/W4416258180","https://openalex.org/W7114792256","https://openalex.org/W7128774487","https://openalex.org/W7135194298","https://openalex.org/W7158641555","https://openalex.org/W7164895536"],"related_works":["https://openalex.org/W7138855241","https://openalex.org/W7161819231","https://openalex.org/W7164175522","https://openalex.org/W7222997415","https://openalex.org/W4415934885","https://openalex.org/W7164010433","https://openalex.org/W7202145315","https://openalex.org/W4385965455","https://openalex.org/W4416748461","https://openalex.org/W7162546573"],"abstract_inverted_index":{"Vision-and-language":[0],"navigation":[1],"increasingly":[2],"relies":[3],"on":[4,85,133],"general-purpose":[5],"semantic":[6,63,91,173],"planners,":[7],"yet":[8],"translating":[9],"correct":[10],"high-level":[11],"intent":[12,174],"into":[13,73,123],"reliable":[14,66,176],"physical":[15,94],"execution":[16,57],"remains":[17],"difficult":[18],"in":[19,162],"spatially":[20],"constrained":[21],"transitions.":[22],"Reaching":[23],"a":[24,54,74],"staircase,":[25],"doorway,":[26],"or":[27,110],"narrow":[28],"passage":[29],"does":[30],"not":[31],"ensure":[32],"traversal;":[33],"the":[34,134,142,166],"agent":[35],"must":[36],"identify":[37],"an":[38],"executable":[39],"affordance":[40,78],"pose":[41,79],"and":[42,80,129,139,150,175],"recover":[43],"from":[44,146,151],"accumulated":[45],"action":[46,83],"errors.":[47],"We":[48,96,120],"propose":[49],"PACE":[50,69,99,122],"(Preference-refined":[51],"Affordance-Conditioned":[52],"Execution),":[53],"supervised":[55],"local":[56],"module":[58],"that":[59,107],"augments":[60],"frozen":[61],"zero-shot":[62,126],"planners":[64],"for":[65],"cross-floor":[67,135],"navigation.":[68],"grounds":[70],"transition-related":[71],"semantics":[72],"long-horizon,":[75],"agent-centric":[76],"traversable":[77,169],"conditions":[81],"short-horizon":[82],"generation":[84],"this":[86],"spatial":[87],"target,":[88],"thereby":[89,116],"aligning":[90],"goals":[92],"with":[93,113],"execution.":[95],"further":[97,158],"post-train":[98],"through":[100],"failure-aware":[101],"preference":[102],"refinement":[103],"using":[104],"rollout-derived":[105],"pairs":[106],"contrast":[108],"normal":[109],"recovery":[111],"behaviors":[112],"deviation-amplifying":[114],"behaviors,":[115],"improving":[117],"closed-loop":[118],"correction.":[119],"integrate":[121],"six":[124],"open-source":[125],"VLN":[127],"navigators":[128],"demonstrate":[130,159],"consistent":[131],"improvements":[132],"subsets":[136],"of":[137,168],"R2R-CE":[138],"RxR-CE,":[140],"increasing":[141],"average":[143],"success":[144],"rate":[145],"16.35%":[147],"to":[148,153,171],"27.65%":[149],"4.76%":[152],"12.06%,":[154],"respectively.":[155],"Real-world":[156],"experiments":[157],"PACE's":[160],"applicability":[161],"unseen":[163],"environments,":[164],"highlighting":[165],"potential":[167],"affordances":[170],"bridge":[172],"embodied":[177],"behavior.":[178]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}