{"id":"https://openalex.org/W7166732169","doi":"https://doi.org/10.48550/arxiv.2606.29934","title":"RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation","display_name":"RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166732169","doi":"https://doi.org/10.48550/arxiv.2606.29934"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29934","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.29934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139632910","display_name":"Zixuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139684148","display_name":"Yuqi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112625169","display_name":"Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139707580","display_name":"Siyuan Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Siyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025164031","display_name":"\u6f58\u52c7\u821f","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Yongzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139661545","display_name":"Beichen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Beichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139677825","display_name":"Mir Feroskhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feroskhan, Mir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.31450000405311584,"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":0.31450000405311584,"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":0.1664000004529953,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11110000312328339,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7049000263214111},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6464999914169312},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5932999849319458},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5734999775886536},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5394999980926514},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4307999908924103},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.40220001339912415}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7049000263214111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6848999857902527},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6464999914169312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.609499990940094},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29934","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.29934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29934","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image-goal":[0],"navigation":[1,53,115],"is":[2],"a":[3,14,19,51,78],"key":[4],"challenge":[5],"in":[6,98],"embodied":[7],"robotics,":[8],"where":[9],"an":[10],"agent":[11],"must":[12],"reach":[13],"target":[15],"specified":[16],"solely":[17],"by":[18],"goal":[20],"image.":[21],"While":[22],"existing":[23],"reinforcement":[24,90],"learning":[25,91],"approaches":[26],"map":[27],"perceptual":[28],"observations":[29],"directly":[30],"to":[31,35,41,58],"actions,":[32],"they":[33],"struggle":[34],"model":[36],"long-horizon":[37],"dependencies,":[38],"often":[39],"leading":[40],"suboptimal":[42],"trajectories.":[43],"To":[44],"address":[45],"this":[46],"limitation,":[47],"we":[48],"propose":[49],"RoamFlow,":[50],"generative":[52],"framework":[54],"that":[55,82,107],"leverages":[56],"MeanFlow":[57],"predict":[59],"the":[60],"average":[61],"velocity":[62],"field":[63],"for":[64,86,92],"trajectory":[65],"synthesis,":[66],"enabling":[67],"efficient":[68,110],"few-step":[69],"generation":[70],"and":[71,102],"reducing":[72],"inference":[73,111],"latency.":[74],"We":[75],"further":[76],"adopt":[77],"two-stage":[79],"training":[80],"strategy":[81],"combines":[83],"expert":[84],"imitation":[85],"stable":[87],"initialization":[88],"with":[89],"task-specific":[93],"policy":[94],"refinement.":[95],"Extensive":[96],"experiments":[97],"both":[99],"Habitat":[100],"simulation":[101],"real-world":[103],"robotic":[104],"platforms":[105],"demonstrate":[106],"RoamFlow":[108],"achieves":[109],"while":[112],"maintaining":[113],"strong":[114],"performance":[116],"under":[117],"real-time":[118],"constraints.":[119]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-01T00:00:00"}