{"id":"https://openalex.org/W4413925793","doi":"https://doi.org/10.1109/icra55743.2025.11128762","title":"World Model-Based Perception for Visual Legged Locomotion","display_name":"World Model-Based Perception for Visual Legged Locomotion","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925793","doi":"https://doi.org/10.1109/icra55743.2025.11128762"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5101789061","display_name":"Hang Lai","orcid":"https://orcid.org/0000-0003-1000-3232"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hang Lai","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015422529","display_name":"Jiahang Cao","orcid":"https://orcid.org/0000-0003-4338-4414"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahang Cao","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647351","display_name":"Jiafeng Xu","orcid":"https://orcid.org/0000-0002-0276-0180"},"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":"Jiafeng Xu","raw_affiliation_strings":["ByteDance Research,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Research,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101733307","display_name":"Hongtao Wu","orcid":"https://orcid.org/0009-0007-4863-5119"},"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":"Hongtao Wu","raw_affiliation_strings":["ByteDance Research,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Research,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078479308","display_name":"Yunfeng Lin","orcid":"https://orcid.org/0009-0004-8953-9244"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfeng Lin","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046716504","display_name":"Tao Kong","orcid":"https://orcid.org/0000-0002-6496-092X"},"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":"Tao Kong","raw_affiliation_strings":["ByteDance Research,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Research,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001571390","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-0281-8271"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102020195","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0001-5981-4752"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101789061"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":5.4715,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96092823,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11531","last_page":"11537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9973999857902527,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9973999857902527,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9591000080108643,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.6625096797943115},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6229807138442993},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46557968854904175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4508986175060272},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4426054358482361},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17120105028152466},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.10382074117660522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625096797943115},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6229807138442993},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46557968854904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4508986175060272},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4426054358482361},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17120105028152466},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.10382074117660522}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G177778633","display_name":null,"funder_award_id":"2022ZDO114804","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3554345598","display_name":null,"funder_award_id":"62076161","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2058330808","https://openalex.org/W2075312701","https://openalex.org/W2100941575","https://openalex.org/W2540093921","https://openalex.org/W2755486058","https://openalex.org/W2784198807","https://openalex.org/W2911087563","https://openalex.org/W2951360122","https://openalex.org/W2963184939","https://openalex.org/W2964198579","https://openalex.org/W3003647188","https://openalex.org/W3039737909","https://openalex.org/W3093922502","https://openalex.org/W3175254947","https://openalex.org/W3204973825","https://openalex.org/W4205430897","https://openalex.org/W4249244053","https://openalex.org/W4252189904","https://openalex.org/W4312900898","https://openalex.org/W4382365373","https://openalex.org/W4383108274","https://openalex.org/W4391259941","https://openalex.org/W4401413790","https://openalex.org/W4401415792","https://openalex.org/W4401416668","https://openalex.org/W4409975538"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Legged":[0],"locomotion":[1],"over":[2],"various":[3],"terrains":[4,100],"is":[5,29,91],"challenging":[6],"and":[7,14,20,32,52,135,172,183,186],"requires":[8],"precise":[9],"perception":[10],"of":[11,105,132,159],"the":[12,60,73,82,88,106,133,141,152,167],"robot":[13],"its":[15],"surroundings":[16],"from":[17,25,76],"both":[18],"proprioception":[19],"vision.":[21],"However,":[22],"learning":[23,89],"directly":[24],"high-dimensional":[26],"visual":[27,64],"input":[28],"often":[30],"data-inefficient":[31],"intricate.":[33],"To":[34],"address":[35],"this":[36,69,113],"issue,":[37],"traditional":[38],"methods":[39],"attempt":[40],"to":[41,48,58,81,97],"learn":[42,54,96],"a":[43,55,118,129,137],"teacher":[44],"policy":[45,57,75,138,168],"with":[46,63],"access":[47],"privileged":[49,109],"information":[50,83],"first":[51],"then":[53],"student":[56,74],"imitate":[59],"teacher's":[61],"behavior":[62],"input.":[65],"Despite":[66],"some":[67],"progress,":[68],"imitation":[70],"framework":[71],"prevents":[72],"achieving":[77],"optimal":[78],"performance":[79],"due":[80],"gap":[84],"between":[85],"inputs.":[86],"Furthermore,":[87],"process":[90],"unnatural":[92],"since":[93],"animals":[94],"intuitively":[95],"traverse":[98],"different":[99],"based":[101,139],"on":[102,140],"their":[103],"understanding":[104],"world":[107,130,142,153],"without":[108],"knowledge.":[110],"Inspired":[111],"by":[112],"natural":[114],"ability,":[115],"we":[116],"propose":[117],"simple":[119],"yet":[120],"effective":[121],"method,":[122],"World":[123],"Model-based":[124],"Perception":[125],"(WMP),":[126],"which":[127],"builds":[128],"model":[131,154],"environment":[134],"learns":[136],"model.":[143],"We":[144],"illustrate":[145],"that":[146,176],"though":[147],"completely":[148],"trained":[149],"in":[150,181],"simulation,":[151],"can":[155],"make":[156],"accurate":[157],"predictions":[158],"real-world":[160,173],"trajectories,":[161],"thus":[162],"providing":[163],"informative":[164],"signals":[165],"for":[166],"controller.":[169],"Extensive":[170],"simulated":[171],"experiments":[174],"demonstrate":[175],"WMP":[177],"outperforms":[178],"state-of-the-art":[179],"baselines":[180],"traversability":[182],"robustness.":[184],"Videos":[185],"Code":[187],"are":[188],"available":[189],"at:":[190],"https://wmp-loco.github.io/.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}