{"id":"https://openalex.org/W7213397307","doi":"https://doi.org/10.48550/arxiv.2609.16737","title":"Visual Cue Guided Video Planning for Generalizable Robot Navigation","display_name":"Visual Cue Guided Video Planning for Generalizable Robot Navigation","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213397307","doi":"https://doi.org/10.48550/arxiv.2609.16737"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.16737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16737","pdf_url":"https://arxiv.org/pdf/2609.16737","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/2609.16737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100726313","display_name":"Hojin Lee","orcid":"https://orcid.org/0000-0002-2044-7470","observed_orcids":["https://orcid.org/0000-0002-2044-7470"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lee, Hojin","raw_affiliation_strings":["Munich Institute of Robotics and Machine Intelligence (MIRMI) , Tech- nical University of Munich , 80797 Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Munich Institute of Robotics and Machine Intelligence (MIRMI) , Tech- nical University of Munich , 80797 Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104046409","display_name":"Sizhe Li","orcid":"https://orcid.org/0009-0000-1857-1520","observed_orcids":["https://orcid.org/0009-0000-1857-1520"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Sizhe Lester","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL) , Mas- sachusetts Institute of Technology , Cambridge , MA 02139 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL) , Mas- sachusetts Institute of Technology , Cambridge , MA 02139 , USA","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068850140","display_name":"Maximilian Hilger","orcid":"https://orcid.org/0009-0006-1747-8491","observed_orcids":["https://orcid.org/0009-0006-1747-8491"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hilger, Maximilian","raw_affiliation_strings":["Munich Institute of Robotics and Machine Intelligence (MIRMI) , Tech- nical University of Munich , 80797 Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Munich Institute of Robotics and Machine Intelligence (MIRMI) , Tech- nical University of Munich , 80797 Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151878710","display_name":"Susie Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu, Susie","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL) , Mas- sachusetts Institute of Technology , Cambridge , MA 02139 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL) , Mas- sachusetts Institute of Technology , Cambridge , MA 02139 , USA","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088586617","display_name":"Achim J. Lilienthal","orcid":"https://orcid.org/0000-0003-0217-9326","observed_orcids":["https://orcid.org/0000-0003-0217-9326"]},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","SE"],"is_corresponding":false,"raw_author_name":"Lilienthal, Achim J.","raw_affiliation_strings":["Centre for Applied Autonomous Sensor Systems (AASS) , \u00d6rebro Uni- versity , 72081 \u00d6rebro , Sweden","Munich Institute of Robotics and Machine Intelligence (MIRMI) , Tech- nical University of Munich , 80797 Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Applied Autonomous Sensor Systems (AASS) , \u00d6rebro Uni- versity , 72081 \u00d6rebro , Sweden","institution_ids":["https://openalex.org/I26437253"]},{"raw_affiliation_string":"Munich Institute of Robotics and Machine Intelligence (MIRMI) , Tech- nical University of Munich , 80797 Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016061808","display_name":"Vincent Sitzmann","orcid":"https://orcid.org/0000-0002-0107-5704","observed_orcids":["https://orcid.org/0000-0002-0107-5704"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sitzmann, Vincent","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL) , Mas- sachusetts Institute of Technology , Cambridge , MA 02139 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL) , Mas- sachusetts Institute of Technology , Cambridge , MA 02139 , USA","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064280336","display_name":"Daniel Andre Duecker","orcid":"https://orcid.org/0000-0001-7256-6984","observed_orcids":["https://orcid.org/0000-0001-7256-6984"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Duecker, Daniel A.","raw_affiliation_strings":["Munich Institute of Robotics and Machine Intelligence (MIRMI) , Tech- nical University of Munich , 80797 Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Munich Institute of Robotics and Machine Intelligence (MIRMI) , Tech- nical University of Munich , 80797 Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.8622999787330627,"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":0.8622999787330627,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0649000033736229,"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":0.01940000057220459,"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/robot-navigation","display_name":"robot navigation","score":0.8970000147819519},{"id":"https://openalex.org/keywords/video-planning","display_name":"video planning","score":0.8550000190734863},{"id":"https://openalex.org/keywords/visual-cues","display_name":"visual cues","score":0.6940000057220459},{"id":"https://openalex.org/keywords/bird-s-eye-view","display_name":"bird's-eye view","score":0.7680000066757202},{"id":"https://openalex.org/keywords/inverse-dynamics-model","display_name":"inverse dynamics model","score":0.9520000219345093},{"id":"https://openalex.org/keywords/flow-field","display_name":"flow field","score":0.5329999923706055},{"id":"https://openalex.org/keywords/long-horizon-planning","display_name":"long-horizon planning","score":0.7760000228881836},{"id":"https://openalex.org/keywords/generative-video-models","display_name":"generative video models","score":0.8130000233650208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044000029563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6574000120162964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6355000138282776},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.5508999824523926},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.546500027179718},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3921000063419342},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3700000047683716},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.2782000005245209},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2778761605","wikidata":"https://www.wikidata.org/wiki/Q3565782","display_name":"Navigational aid","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.16737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16737","pdf_url":"https://arxiv.org/pdf/2609.16737","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.2609.16737","doi":"https://doi.org/10.48550/arxiv.2609.16737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.16737","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:2609.16737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16737","pdf_url":"https://arxiv.org/pdf/2609.16737","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":[{"id":"https://openalex.org/G3344764105","display_name":"Center: NSF Engineering Research Center for Human AugmentatioN via Dexterity (HAND)","funder_award_id":"2330040","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213397307.pdf","grobid_xml":"https://content.openalex.org/works/W7213397307.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7134236056","https://openalex.org/W7128631038","https://openalex.org/W4413147084","https://openalex.org/W7160839365","https://openalex.org/W7223062605","https://openalex.org/W7160326296","https://openalex.org/W7162685497","https://openalex.org/W7166710426","https://openalex.org/W7117102118","https://openalex.org/W4417292834"],"abstract_inverted_index":{"Generative":[0],"video":[1,17,23,48,56,98,110,173,185],"models":[2],"can":[3],"serve":[4],"as":[5,16],"a":[6,47,69,150,195],"promising":[7],"backbone":[8],"for":[9,199],"robot":[10,84,113,177],"navigation":[11,50,131,145,167,197],"by":[12],"predicting":[13],"future":[14],"observations":[15],"plans.":[18],"Recent":[19],"approaches":[20],"often":[21],"condition":[22],"planning":[24,37,57,133,186,201],"on":[25,211],"short-horizon":[26],"guidance":[27],"and":[28,38,79,168,202,207],"recover":[29],"geometric":[30],"waypoints":[31],"through":[32],"scene":[33],"reconstruction,":[34],"leaving":[35],"longer-horizon":[36,200],"precise":[39,144],"video-to-action":[40],"translation":[41],"less":[42],"explored.":[43],"We":[44,162],"present":[45],"CueNav,":[46],"model-based":[49],"framework":[51,198],"combining":[52],"visual":[53,65,117,183],"cue":[54,118],"guided":[55],"with":[58,140,146,187],"an":[59],"embodiment-specific":[60,188],"Inverse-Dynamics":[61],"Model":[62],"(IDM).":[63],"As":[64],"cues,":[66],"we":[67],"use":[68],"Bird's-Eye":[70],"View":[71],"(BEV)":[72],"map":[73],"to":[74,90,158],"convey":[75],"global":[76,120],"task":[77,121],"context":[78],"retain":[80],"part":[81],"of":[82,170],"the":[83,87,97,101,109,116,135,141,160,171,192],"body":[85],"in":[86,129,149],"egocentric":[88],"observation":[89],"expose":[91],"embodiment":[92],"context.":[93],"These":[94],"cues":[95],"guide":[96],"planner,":[99],"while":[100],"IDM":[102,142],"translates":[103],"dense":[104],"flow":[105],"fields":[106],"extracted":[107],"from":[108],"plan":[111],"into":[112],"actions.":[114],"With":[115],"encoding":[119],"context,":[122],"CueNav":[123],"achieves":[124],"nearly":[125],"2x":[126],"higher":[127],"success":[128,148],"maze":[130],"than":[132],"without":[134],"cue.":[136],"The":[137],"body-aware":[138],"view":[139],"enables":[143],"70%":[147],"narrow":[151],"passage":[152],"where":[153],"comparison":[154],"methods":[155],"largely":[156],"fail":[157],"complete":[159],"task.":[161],"further":[163],"demonstrate":[164],"zero-shot":[165],"semantic-conditioned":[166],"deployment":[169],"same":[172],"planner":[174],"across":[175],"different":[176],"platforms.":[178],"Our":[179],"results":[180,206],"show":[181],"that":[182],"cue-guided":[184],"action":[189],"grounding":[190],"paves":[191],"way":[193],"toward":[194],"generalizable":[196],"embodiment-aware":[203],"control.":[204],"Additional":[205],"code":[208],"are":[209],"available":[210],"our":[212],"project":[213],"website:":[214],"https://cuenav.github.io.":[215]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-17T00:00:00"}