{"id":"https://openalex.org/W4415316236","doi":"https://doi.org/10.1109/icra57385.2026.11696699","title":"ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation","display_name":"ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W4415316236","doi":"https://doi.org/10.1109/icra57385.2026.11696699"},"language":"en","primary_location":{"id":"doi:10.1109/icra57385.2026.11696699","doi":"https://doi.org/10.1109/icra57385.2026.11696699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57385.2026.11696699","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.12618","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101807900","display_name":"Zekai Zhang","orcid":"https://orcid.org/0009-0007-6496-1969","observed_orcids":["https://orcid.org/0009-0007-6496-1969"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekai Zhang","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112845340","display_name":"Weiye Zhu","orcid":"https://orcid.org/0009-0002-4392-2753","observed_orcids":["https://orcid.org/0009-0002-4392-2753"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiye Zhu","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hewei Pan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hewei Pan","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085460482","display_name":"Xiangchen Wang","orcid":"https://orcid.org/0009-0002-0857-4378","observed_orcids":["https://orcid.org/0009-0002-0857-4378"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangchen Wang","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038918940","display_name":"Rongtao Xu","orcid":"https://orcid.org/0000-0003-4619-9679","observed_orcids":["https://orcid.org/0000-0003-4619-9679"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongtao Xu","raw_affiliation_strings":["Spatialtemporal AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spatialtemporal AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110060989","display_name":"Xing Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Sun","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":null,"display_name":"Feng Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zheng","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.2212,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98269912,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12611","last_page":"12618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9672999978065491,"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":0.9672999978065491,"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":0.022600000724196434,"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":0.0012000000569969416,"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":0.9890000224113464},{"id":"https://openalex.org/keywords/active-exploration","display_name":"active exploration","score":0.8299999833106995},{"id":"https://openalex.org/keywords/multi-turn-reinforcement-learning","display_name":"multi-turn reinforcement learning","score":0.9869999885559082},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.625},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.6119999885559082},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.4909999966621399},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.6800000071525574},{"id":"https://openalex.org/keywords/natural-language-instructions","display_name":"natural language instructions","score":0.6660000085830688},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6019999980926514},{"id":"https://openalex.org/keywords/covariate-shift","display_name":"covariate shift","score":0.6890000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878000140190125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6841999888420105},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4449000060558319},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40950000286102295},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3901999890804291},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2554999887943268}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra57385.2026.11696699","doi":"https://doi.org/10.1109/icra57385.2026.11696699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57385.2026.11696699","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.12618","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12618","pdf_url":"https://arxiv.org/pdf/2509.12618","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.2509.12618","doi":"https://doi.org/10.48550/arxiv.2509.12618","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12618","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:2509.12618","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12618","pdf_url":"https://arxiv.org/pdf/2509.12618","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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4405022959","https://openalex.org/W3106641651","https://openalex.org/W7169063566","https://openalex.org/W4402957713","https://openalex.org/W4393300392","https://openalex.org/W7123355754","https://openalex.org/W4311189605","https://openalex.org/W7222921121","https://openalex.org/W4389524290","https://openalex.org/W4414987633"],"abstract_inverted_index":{"The":[0],"Vision-and-Language":[1],"Navigation":[2],"(VLN)":[3],"task":[4],"requires":[5],"an":[6],"agent":[7,135],"to":[8,34,87,126,164,189],"follow":[9],"natural":[10],"language":[11],"instructions":[12],"and":[13,28,46,67,90,138,145,192,210],"navigate":[14],"through":[15,109],"complex":[16],"environments.":[17],"Existing":[18],"MLLM-based":[19],"VLN":[20,58,102],"methods":[21,60],"primarily":[22],"rely":[23],"on":[24,69],"imitation":[25],"learning":[26,50],"(IL)":[27],"often":[29],"use":[30],"DAgger":[31],"for":[32,72,124],"post-training":[33,195],"mitigate":[35],"covariate":[36],"shift.":[37],"While":[38],"effective,":[39],"these":[40,96],"approaches":[41,203],"incur":[42],"substantial":[43],"data":[44,211],"collection":[45],"training":[47],"costs.":[48],"Reinforcement":[49],"(RL)":[51],"offers":[52],"a":[53,101,116,160,206],"promising":[54],"alternative.":[55],"However,":[56],"prior":[57,193],"RL":[59,156],"lack":[61],"dynamic":[62,161],"interaction":[63],"with":[64,172,201],"the":[65,84,113,128,131,134,150,181],"environment":[66],"depend":[68],"expert":[70,120],"trajectories":[71,121],"reward":[73],"shaping,":[74],"rather":[75],"than":[76],"engaging":[77],"in":[78],"open-ended":[79],"active":[80,107],"exploration.":[81],"This":[82],"restricts":[83],"agent's":[85],"ability":[86],"discover":[88],"diverse":[89,143],"plausible":[91],"navigation":[92],"routes.":[93],"To":[94,153],"address":[95],"limitations,":[97],"we":[98,158],"propose":[99],"ActiveVLN,":[100],"framework":[103],"that":[104,178],"explicitly":[105],"enables":[106],"exploration":[108],"multi-turn":[110],"RL.":[111],"In":[112,130],"first":[114],"stage,":[115,133],"small":[117],"fraction":[118],"of":[119],"is":[122],"used":[123],"IL":[125,186],"bootstrap":[127],"agent.":[129],"second":[132],"iteratively":[136],"predicts":[137],"executes":[139],"actions,":[140],"automatically":[141],"collects":[142],"trajectories,":[144,170],"optimizes":[146],"multiple":[147],"rollouts":[148],"via":[149],"GRPO":[151],"objective.":[152],"further":[154],"improve":[155],"efficiency,":[157],"introduce":[159],"early-stopping":[162],"strategy":[163],"prune":[165],"long-tail":[166],"or":[167],"likely":[168],"failed":[169],"along":[171],"additional":[173],"engineering":[174],"optimizations.":[175],"Experiments":[176],"show":[177],"ActiveVLN":[179],"achieves":[180],"largest":[182],"performance":[183,200],"gains":[184],"over":[185],"baselines":[187],"compared":[188],"both":[190],"DAgger-based":[191],"RL-based":[194],"methods,":[196],"while":[197],"reaching":[198],"competitive":[199],"state-of-the-art":[202],"despite":[204],"using":[205],"smaller":[207],"model.":[208],"Code":[209],"will":[212],"be":[213],"released":[214],"soon.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2025-10-18T00:00:00"}