{"id":"https://openalex.org/W4405785215","doi":"https://doi.org/10.1109/iros58592.2024.10801689","title":"MG-VLN: Benchmarking Multi-Goal and Long-Horizon Vision-Language Navigation with Language Enhanced Memory Map","display_name":"MG-VLN: Benchmarking Multi-Goal and Long-Horizon Vision-Language Navigation with Language Enhanced Memory Map","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785215","doi":"https://doi.org/10.1109/iros58592.2024.10801689"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Tsinghua University,Institute for Interdisciplinary Information Sciences"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for Interdisciplinary Information Sciences","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006570986","display_name":"Kaisheng Ma","orcid":"https://orcid.org/0000-0001-9226-3366"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaisheng Ma","raw_affiliation_strings":["Tsinghua University,Institute for Interdisciplinary Information Sciences"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for Interdisciplinary Information Sciences","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100778479"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5065,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67930845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7750","last_page":"7757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9914000034332275,"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":0.9914000034332275,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9545999765396118,"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/T12031","display_name":"Speech and dialogue systems","score":0.9435999989509583,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426406741142273},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7096495032310486},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.6150733828544617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49630433320999146},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4303074777126312},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38183730840682983},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37243229150772095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426406741142273},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7096495032310486},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.6150733828544617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49630433320999146},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4303074777126312},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38183730840682983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37243229150772095},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2896457183","https://openalex.org/W2926977875","https://openalex.org/W2951973805","https://openalex.org/W2962744691","https://openalex.org/W2962789679","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2979727876","https://openalex.org/W3009928773","https://openalex.org/W3034578524","https://openalex.org/W3035232877","https://openalex.org/W3100923070","https://openalex.org/W3109097593","https://openalex.org/W3134025030","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3174887918","https://openalex.org/W3176495323","https://openalex.org/W3176974620","https://openalex.org/W3182243998","https://openalex.org/W3192009892","https://openalex.org/W3195026654","https://openalex.org/W3205276578","https://openalex.org/W4214879935","https://openalex.org/W4226052928","https://openalex.org/W4312434279","https://openalex.org/W4312501707","https://openalex.org/W4312581490","https://openalex.org/W4312729859","https://openalex.org/W4312924260","https://openalex.org/W4312938887","https://openalex.org/W4313591672","https://openalex.org/W4364353501","https://openalex.org/W4382240275","https://openalex.org/W4383109211","https://openalex.org/W4386065508","https://openalex.org/W4386065870","https://openalex.org/W4386066594","https://openalex.org/W4386072289","https://openalex.org/W4386075539","https://openalex.org/W4386075653","https://openalex.org/W4386076252","https://openalex.org/W4390873167","https://openalex.org/W4390874160","https://openalex.org/W4402354030","https://openalex.org/W6726873649","https://openalex.org/W6751885507","https://openalex.org/W6758824984","https://openalex.org/W6765108809","https://openalex.org/W6765527290","https://openalex.org/W6766904570","https://openalex.org/W6774815639","https://openalex.org/W6780451406","https://openalex.org/W6784287907","https://openalex.org/W6785121346","https://openalex.org/W6791353385","https://openalex.org/W6800673378","https://openalex.org/W6802382269","https://openalex.org/W6803039797","https://openalex.org/W6810151762","https://openalex.org/W6846113813","https://openalex.org/W6846137956","https://openalex.org/W6847021064","https://openalex.org/W6847646427","https://openalex.org/W6849177959","https://openalex.org/W6852960723","https://openalex.org/W6854602269","https://openalex.org/W6860803839"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"Vision-Language":[0,57],"Navigation":[1,58],"(VLN)":[2],"with":[3,71,143,189],"high-level":[4,74,190],"language":[5],"instructions":[6,24],"is":[7,181],"a":[8,50,81],"crucial":[9],"task":[10,77],"in":[11,98,111,169],"robotics.":[12],"Existing":[13],"VLN":[14],"benchmarks,":[15],"such":[16,146],"as":[17,147],"the":[18,33,61,86,96,106,126,140,160,182],"REVERIE":[19,62],"challenge":[20],"which":[21],"has":[22],"single-goal":[23],"and":[25,42,55,67,90,152,171,178],"limited":[26],"navigation":[27,37,69,92,113,167],"steps,":[28],"do":[29],"not":[30],"fully":[31],"encapsulate":[32],"complexity":[34],"of":[35,73,88,108,128],"real-world":[36],"that":[38,130],"often":[39],"require":[40],"multi-objective":[41,66],"long-horizon":[43,68,91,172],"navigation.":[44],"To":[45,94],"address":[46],"this,":[47],"we":[48,103,124,138],"propose":[49],"new":[51],"benchmark":[52,63,83],"task:":[53],"Multi-Goal":[54],"Long-Horizon":[56],"(MG-VLN),":[59],"extending":[60],"to":[64,79,84],"encompass":[65],"scenarios":[70],"sequences":[72],"instructions.":[75,191],"This":[76],"aims":[78],"provide":[80],"simulation":[82],"guide":[85],"design":[87],"lifelong":[89],"robots.":[93],"initiate":[95],"exploration":[97],"this":[99,134],"newly":[100],"proposed":[101],"task,":[102],"first":[104],"investigate":[105],"role":[107],"long-term":[109,135,162],"memory":[110,163],"improving":[112],"performance":[114,168],"by":[115],"leveraging":[116],"environmental":[117,187],"information":[118,180],"gathered":[119],"during":[120],"previous":[121],"sub-goals.":[122],"Additionally,":[123],"examine":[125],"types":[127],"knowledge":[129,145],"most":[131,183],"effectively":[132],"enrich":[133],"memory.":[136],"Specifically,":[137],"integrate":[139],"visual":[141,150],"contents":[142],"linguistic":[144],"object":[148,153,176],"categories,":[149],"captions,":[151],"attributes/relationships.":[154],"Our":[155],"findings":[156],"indicate":[157],"that:":[158],"1)":[159],"explicit":[161],"map":[164],"significantly":[165],"enhances":[166],"multi-goal":[170],"scenarios;":[173],"2)":[174],"incorporating":[175],"attributes":[177],"relationships":[179],"advantageous":[184],"for":[185],"aligning":[186],"cues":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}