{"id":"https://openalex.org/W4415318125","doi":"https://doi.org/10.1109/lra.2026.3703584","title":"DPL: Depth-Only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction","display_name":"DPL: Depth-Only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W4415318125","doi":"https://doi.org/10.1109/lra.2026.3703584"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2026.3703584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3703584","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.07152","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049574394","display_name":"Jingkai Sun","orcid":"https://orcid.org/0000-0002-1032-2957"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkai Sun","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-9377-5834","affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100899705","display_name":"Gang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Han","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046892904","display_name":"Pihai Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pihai Sun","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8637-1511","affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111526799","display_name":"Wen Zhao","orcid":"https://orcid.org/0009-0002-9728-3950"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Zhao","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"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/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahang Cao","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-4338-4414","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101468620","display_name":"Jiaxu Wang","orcid":"https://orcid.org/0000-0003-1277-6896"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaxu Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015738855","display_name":"Qiang Zhang","orcid":"https://orcid.org/0000-0003-0078-8232"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-8277-1898","affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100572173","display_name":"Yijie Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijie Guo","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7333-3736","affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7596,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89218678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"11","issue":"8","first_page":"9407","last_page":"9414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12740","display_name":"Gait Recognition and Analysis","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/terrain","display_name":"Terrain","score":0.7494999766349792},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6018999814987183},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5034999847412109},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4564000070095062},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4185999929904938},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4156999886035919},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.3797999918460846},{"id":"https://openalex.org/keywords/elevation","display_name":"Elevation (ballistics)","score":0.36980000138282776}],"concepts":[{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.7494999766349792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707099974155426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6725999712944031},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6226999759674072},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6018999814987183},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C37054046","wikidata":"https://www.wikidata.org/wiki/Q641888","display_name":"Elevation (ballistics)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C181843262","wikidata":"https://www.wikidata.org/wiki/Q640492","display_name":"Digital elevation model","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C116108083","wikidata":"https://www.wikidata.org/wiki/Q1940131","display_name":"Ray casting","level":4,"score":0.30869999527931213},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C99695388","wikidata":"https://www.wikidata.org/wiki/Q350514","display_name":"Raised-relief map","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lra.2026.3703584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3703584","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2510.07152","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.07152","pdf_url":"https://arxiv.org/pdf/2510.07152","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.07152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07152","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.07152","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.07152","pdf_url":"https://arxiv.org/pdf/2510.07152","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415318125.pdf","grobid_xml":"https://content.openalex.org/works/W4415318125.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,41,57,135],"legged":[3],"robot":[4],"perceptive":[5],"locomotion":[6,14,172],"have":[7],"shown":[8],"promising":[9],"progress.":[10],"However,":[11],"terrain-aware":[12],"humanoid":[13,166],"remains":[15],"largely":[16],"constrained":[17],"to":[18,91,126],"two":[19],"paradigms:":[20],"depth":[21,42,110,129],"image-based":[22],"end-to-end":[23],"learning":[24,94],"and":[25,36,53,59,123,148,170,175],"elevation":[26,88],"map-based":[27,89],"methods.":[28],"The":[29],"former":[30],"suffers":[31],"from":[32,108],"limited":[33,146],"training":[34,144],"efficiency":[35],"a":[37,68,82,164],"significant":[38],"sim-to-real":[39],"gap":[40],"perception,":[43],"while":[44,151],"the":[45],"latter":[46],"depends":[47],"heavily":[48],"on":[49,163],"multiple":[50],"vision":[51],"sensors":[52],"localization":[54],"systems,":[55],"resulting":[56],"latency":[58],"reduced":[60],"robustness.":[61],"To":[62],"overcome":[63],"these":[64],"challenges,":[65],"we":[66],"propose":[67],"novel":[69],"framework":[70,162],"that":[71],"tightly":[72],"integrates":[73],"three":[74],"key":[75],"components:":[76],"(1)":[77],"Terrain-Aware":[78],"Locomotion":[79],"Policy":[80],"with":[81,95,145],"Blind":[83],"Backbone,":[84],"which":[85,103,118],"leverages":[86],"pre-trained":[87],"perception":[90],"guide":[92],"reinforcement":[93],"minimal":[96],"visual":[97],"input;":[98],"(2)":[99],"Multi-Modality":[100],"Cross-Attention":[101],"Transformer,":[102],"reconstructs":[104],"structured":[105],"terrain":[106,136,154],"representations":[107],"noisy":[109],"images;":[111],"(3)":[112],"Realistic":[113],"Depth":[114],"Images":[115],"Synthetic":[116],"Method,":[117],"employs":[119],"self-occlusion-aware":[120],"ray":[121],"casting":[122],"noise-aware":[124],"modeling":[125],"synthesize":[127],"realistic":[128],"observations,":[130],"achieving":[131],"over":[132],"30%":[133],"reduction":[134],"reconstruction":[137],"error.":[138],"This":[139],"combination":[140],"enables":[141],"efficient":[142],"policy":[143],"data":[147],"hardware":[149],"resources,":[150],"preserving":[152],"critical":[153],"features":[155],"essential":[156],"for":[157],"generalization.":[158],"We":[159],"validate":[160],"our":[161],"full-sized":[165],"robot,":[167],"demonstrating":[168],"agile":[169],"adaptive":[171],"across":[173],"diverse":[174],"challenging":[176],"terrains.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-18T00:00:00"}
