{"id":"https://openalex.org/W4416748461","doi":"https://doi.org/10.1109/iros60139.2025.11246147","title":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation","display_name":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748461","doi":"https://doi.org/10.1109/iros60139.2025.11246147"},"language":"en","primary_location":{"id":"doi:10.1109/iros60139.2025.11246147","doi":"https://doi.org/10.1109/iros60139.2025.11246147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246147","pdf_url":null,"source":{"id":"https://openalex.org/S4393918188","display_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":"2153-0858","issn":["2153-0858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101261295","display_name":"Xiangyu Shi","orcid":"https://orcid.org/0009-0009-3929-1443","observed_orcids":["https://orcid.org/0009-0009-3929-1443"]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiangyu Shi","raw_affiliation_strings":["Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037611974","display_name":"Zerui Li","orcid":"https://orcid.org/0000-0001-7831-3785","observed_orcids":["https://orcid.org/0000-0001-7831-3785"]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zerui Li","raw_affiliation_strings":["Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113277401","display_name":"Wenqi Lyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenqi Lyu","raw_affiliation_strings":["Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiatong Xia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiatong Xia","raw_affiliation_strings":["Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091323624","display_name":"Feras Dayoub","orcid":"https://orcid.org/0000-0002-4234-7374","observed_orcids":["https://orcid.org/0000-0002-4234-7374"]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feras Dayoub","raw_affiliation_strings":["Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049868894","display_name":"Yanyuan Qiao","orcid":"https://orcid.org/0000-0002-5606-0702","observed_orcids":["https://orcid.org/0000-0002-5606-0702"]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yanyuan Qiao","raw_affiliation_strings":["Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021603002","display_name":"Qi Wu","orcid":"https://orcid.org/0009-0006-1175-1258","observed_orcids":["https://orcid.org/0009-0006-1175-1258"]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":9.2133,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.98111798,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"16923","last_page":"16930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7675999999046326,"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":0.7675999999046326,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0731000006198883,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.058800000697374344,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/vision-and-language-navigation","display_name":"vision-and-language navigation","score":0.9909999966621399},{"id":"https://openalex.org/keywords/continuous-environments","display_name":"continuous environments","score":0.7829999923706055},{"id":"https://openalex.org/keywords/waypoint-prediction","display_name":"waypoint prediction","score":0.8640000224113464},{"id":"https://openalex.org/keywords/backtracking","display_name":"backtracking","score":0.921999990940094},{"id":"https://openalex.org/keywords/zero-shot-navigation","display_name":"zero-shot navigation","score":0.7059999704360962},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9079999923706055},{"id":"https://openalex.org/keywords/adaptive-path-planning","display_name":"adaptive path planning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/natural-language-instructions","display_name":"natural language instructions","score":0.6100000143051147}],"concepts":[{"id":"https://openalex.org/C2781271823","wikidata":"https://www.wikidata.org/wiki/Q138081","display_name":"Waypoint","level":2,"score":0.9836000204086304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067000269889832},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6897000074386597},{"id":"https://openalex.org/C156884757","wikidata":"https://www.wikidata.org/wiki/Q798554","display_name":"Backtracking","level":2,"score":0.678600013256073},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4672999978065491},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3677999973297119},{"id":"https://openalex.org/C3018142793","wikidata":"https://www.wikidata.org/wiki/Q7448134","display_name":"Self limiting","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C96522737","wikidata":"https://www.wikidata.org/wiki/Q17148345","display_name":"Path integration","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros60139.2025.11246147","doi":"https://doi.org/10.1109/iros60139.2025.11246147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246147","pdf_url":null,"source":{"id":"https://openalex.org/S4393918188","display_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":"2153-0858","issn":["2153-0858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2503.10069","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10069","pdf_url":"https://arxiv.org/pdf/2503.10069","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.2503.10069","doi":"https://doi.org/10.48550/arxiv.2503.10069","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10069","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:2503.10069","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10069","pdf_url":"https://arxiv.org/pdf/2503.10069","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416748461.pdf","grobid_xml":"https://content.openalex.org/works/W4416748461.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2770387316","https://openalex.org/W2929928372","https://openalex.org/W2964339842","https://openalex.org/W2970231061","https://openalex.org/W3014266552","https://openalex.org/W3034578524","https://openalex.org/W3100923070","https://openalex.org/W4226052928","https://openalex.org/W4312253995","https://openalex.org/W4390871755","https://openalex.org/W4390872429","https://openalex.org/W4390873167","https://openalex.org/W4393154152","https://openalex.org/W4393160097","https://openalex.org/W4394627367","https://openalex.org/W4401042755","https://openalex.org/W4401417232","https://openalex.org/W4402353981","https://openalex.org/W4402703032","https://openalex.org/W4413918509","https://openalex.org/W4413925269"],"related_works":["https://openalex.org/W4416433475","https://openalex.org/W4414787818","https://openalex.org/W7212013948","https://openalex.org/W4412795922","https://openalex.org/W4417173786","https://openalex.org/W7161831566","https://openalex.org/W7164171039","https://openalex.org/W7138863807","https://openalex.org/W4402979664","https://openalex.org/W4415087953"],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"in":[3,119],"continuous":[4],"environments":[5],"requires":[6],"agents":[7],"to":[8,29,35,126],"interpret":[9],"natural":[10],"language":[11],"instructions":[12],"while":[13,46],"navigating":[14],"unconstrained":[15],"3D":[16],"spaces.":[17],"Existing":[18],"VLN-CE":[19,60],"frameworks":[20],"rely":[21],"on":[22,107,132],"a":[23,26,33,58,68,78],"two-stage":[24],"approach:":[25],"waypoint":[27,40,65,91],"predictor":[28,66,76],"generate":[30],"waypoints":[31],"and":[32,51,85,98,109],"navigator":[34,94],"execute":[36],"movements.":[37],"However,":[38],"current":[39],"predictors":[41],"struggle":[42],"with":[43,67,102],"spatial":[44],"awareness,":[45],"navigators":[47],"lack":[48],"historical":[49],"reasoning":[50,97],"backtracking":[52],"capabilities,":[53],"limiting":[54],"adaptability.":[55,138],"We":[56],"propose":[57],"zero-shot":[59,120],"framework":[61],"integrating":[62],"an":[63,86],"enhanced":[64],"Multi-modal":[69],"Large":[70],"Language":[71],"Model":[72],"(MLLM)-based":[73],"navigator.":[74],"Our":[75],"employs":[77],"stronger":[79],"vision":[80],"encoder,":[81],"masked":[82],"cross-attention":[83],"fusion,":[84],"occupancy-aware":[87],"loss":[88],"for":[89],"better":[90],"quality.":[92],"The":[93],"incorporates":[95],"history-aware":[96],"adaptive":[99],"path":[100],"planning":[101],"backtracking,":[103],"improving":[104],"robustness.":[105],"Experiments":[106],"R2R-CE":[108],"MP3D":[110],"benchmarks":[111],"show":[112],"our":[113],"method":[114],"achieves":[115],"state-of-the-art":[116],"(SOTA)":[117],"performance":[118],"settings,":[121],"demonstrating":[122],"competitive":[123],"results":[124],"compared":[125],"fully":[127],"supervised":[128],"methods.":[129],"Real-world":[130],"validation":[131],"Turtlebot":[133],"4":[134],"further":[135],"highlights":[136],"its":[137]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2025-11-28T00:00:00"}
