{"id":"https://openalex.org/W4414632003","doi":"https://doi.org/10.48550/arxiv.2504.15643","title":"Multimodal Perception for Goal-oriented Navigation: A Survey","display_name":"Multimodal Perception for Goal-oriented Navigation: A Survey","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4414632003","doi":"https://doi.org/10.48550/arxiv.2504.15643"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.15643","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15643","pdf_url":"https://arxiv.org/pdf/2504.15643","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/2504.15643","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119771106","display_name":"I-Tak Ieong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ieong, I-Tak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101745105","display_name":"Hao Tang A","orcid":"https://orcid.org/0000-0002-6197-0874","observed_orcids":["https://orcid.org/0000-0002-6197-0874"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Hao","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":true,"cited_by_count":5,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.5580999851226807,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.5580999851226807,"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":0.1574999988079071,"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":0.07259999960660934,"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/goal-directed-navigation","display_name":"goal-directed navigation","score":0.9879999756813049},{"id":"https://openalex.org/keywords/multisensory-perception","display_name":"multisensory perception","score":0.9929999709129333},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.7080000042915344},{"id":"https://openalex.org/keywords/visual-perception","display_name":"visual perception","score":0.6869999766349792},{"id":"https://openalex.org/keywords/linguistic-perception","display_name":"linguistic perception","score":0.7580000162124634},{"id":"https://openalex.org/keywords/acoustic-perception","display_name":"acoustic perception","score":0.9869999885559082},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"sensor fusion","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5404000282287598},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4661000072956085},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3497999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.15643","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15643","pdf_url":"https://arxiv.org/pdf/2504.15643","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.2504.15643","doi":"https://doi.org/10.48550/arxiv.2504.15643","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.15643","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:2504.15643","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15643","pdf_url":"https://arxiv.org/pdf/2504.15643","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/W4414632003.pdf","grobid_xml":"https://content.openalex.org/works/W4414632003.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W2260756217","https://openalex.org/W2519887557","https://openalex.org/W2567015638","https://openalex.org/W2616729100","https://openalex.org/W2736601468","https://openalex.org/W2776202271","https://openalex.org/W2786472725","https://openalex.org/W2794752562","https://openalex.org/W2884565639","https://openalex.org/W2896457183","https://openalex.org/W2949830259","https://openalex.org/W2950635152","https://openalex.org/W2962812366","https://openalex.org/W2964339842","https://openalex.org/W3001975179","https://openalex.org/W3011144238","https://openalex.org/W3036497058","https://openalex.org/W3081567831","https://openalex.org/W3094502228","https://openalex.org/W3110257065","https://openalex.org/W3121780787","https://openalex.org/W3126809086","https://openalex.org/W3176468608","https://openalex.org/W3200063923","https://openalex.org/W3207872317","https://openalex.org/W4226399820","https://openalex.org/W4226538240","https://openalex.org/W4287265459","https://openalex.org/W4297808394","https://openalex.org/W4298187450","https://openalex.org/W4312046386","https://openalex.org/W4327525106","https://openalex.org/W4327810158","https://openalex.org/W4361229539","https://openalex.org/W4366850747","https://openalex.org/W4382322597","https://openalex.org/W4385416186","https://openalex.org/W4385431115","https://openalex.org/W4387210650","https://openalex.org/W4387226145","https://openalex.org/W4390690152","https://openalex.org/W4392019697","https://openalex.org/W4401042437","https://openalex.org/W4401413869","https://openalex.org/W4402354030","https://openalex.org/W4404341559","https://openalex.org/W4405785171","https://openalex.org/W4410746275","https://openalex.org/W4413925833","https://openalex.org/W4415798988"],"related_works":["https://openalex.org/W4400258109","https://openalex.org/W4413925802","https://openalex.org/W4392939491","https://openalex.org/W7143606032","https://openalex.org/W4386066968","https://openalex.org/W7138073044","https://openalex.org/W4416050970","https://openalex.org/W4402726789","https://openalex.org/W3195049861","https://openalex.org/W3102804550"],"abstract_inverted_index":{"Goal-oriented":[0],"navigation":[1,27,56,80,90,104],"presents":[2],"a":[3,22],"fundamental":[4],"challenge":[5],"for":[6],"autonomous":[7],"systems,":[8],"requiring":[9],"agents":[10,38],"to":[11,15,102,114],"navigate":[12,43],"complex":[13],"environments":[14,44],"reach":[16],"designated":[17],"targets.":[18],"This":[19],"survey":[20],"offers":[21],"comprehensive":[23],"analysis":[24],"of":[25,33,99,119],"multimodal":[26,100],"approaches":[28,77],"through":[29],"the":[30,94,120],"unifying":[31],"perspective":[32],"inference":[34,66],"domains,":[35],"exploring":[36],"how":[37,70],"perceive,":[39],"reason":[40],"about,":[41],"and":[42,48,85,92,97],"using":[45],"visual,":[46],"linguistic,":[47],"acoustic":[49],"information.":[50],"Our":[51],"key":[52],"contributions":[53],"include":[54],"organizing":[55],"methods":[57],"based":[58],"on":[59],"their":[60],"primary":[61],"environmental":[62],"reasoning":[63],"mechanisms":[64],"across":[65,78,88],"domains;":[67],"systematically":[68],"analyzing":[69],"shared":[71],"computational":[72],"foundations":[73],"support":[74],"seemingly":[75],"disparate":[76],"different":[79],"tasks;":[81],"identifying":[82],"recurring":[83],"patterns":[84],"distinctive":[86],"strengths":[87],"various":[89],"paradigms;":[91],"examining":[93],"integration":[95],"challenges":[96],"opportunities":[98],"perception":[101],"enhance":[103],"capabilities.":[105],"In":[106],"addition,":[107],"we":[108],"review":[109],"approximately":[110],"200":[111],"relevant":[112],"articles":[113],"provide":[115],"an":[116],"in-depth":[117],"understanding":[118],"current":[121],"landscape.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}