{"id":"https://openalex.org/W7203606965","doi":"https://doi.org/10.1038/s41598-026-62543-x","title":"Trans-Percept: robust perceptive locomotion in the wild via spatiotemporal causal transformers","display_name":"Trans-Percept: robust perceptive locomotion in the wild via spatiotemporal causal transformers","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7203606965","doi":"https://doi.org/10.1038/s41598-026-62543-x"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-62543-x","doi":"https://doi.org/10.1038/s41598-026-62543-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-62543-x","pdf_url":"https://www.nature.com/articles/s41598-026-62543-x_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-62543-x_reference.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088624952","display_name":"Zukun Zhang","orcid":"https://orcid.org/0009-0005-9477-9573","observed_orcids":["https://orcid.org/0009-0005-9477-9573"]},"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":"Zukun Zhang","raw_affiliation_strings":["The University of Hong Kong, 999077, Pokfulam, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, 999077, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111267280","display_name":"Mingqiao Mo","orcid":"https://orcid.org/0009-0006-6345-7990","observed_orcids":["https://orcid.org/0009-0006-6345-7990"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqiao Mo","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, 101408, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114633771","display_name":"Kai Shu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Shu","raw_affiliation_strings":["Alibaba Inc, HangZhou, 311121, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Inc, HangZhou, 311121, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114633771"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50613984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9731000065803528,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9731000065803528,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.02329999953508377,"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":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/legged-robot-locomotion","display_name":"legged robot locomotion","score":0.972000002861023},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.6449999809265137},{"id":"https://openalex.org/keywords/teacher-student-training","display_name":"teacher-student training","score":0.8259999752044678},{"id":"https://openalex.org/keywords/unitree-go2","display_name":"Unitree Go2","score":0.7950000166893005},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716000080108643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5005999803543091},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.4611000120639801},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4205000102519989},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37299999594688416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34709998965263367},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3411000072956085},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3260999917984009},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C171790689","wikidata":"https://www.wikidata.org/wiki/Q1129066","display_name":"Proprioception","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s41598-026-62543-x","doi":"https://doi.org/10.1038/s41598-026-62543-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-62543-x","pdf_url":"https://www.nature.com/articles/s41598-026-62543-x_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-62543-x","doi":"https://doi.org/10.1038/s41598-026-62543-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-62543-x","pdf_url":"https://www.nature.com/articles/s41598-026-62543-x_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203606965.pdf","grobid_xml":"https://content.openalex.org/works/W7203606965.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3178099496","https://openalex.org/W4205430897","https://openalex.org/W4413925793","https://openalex.org/W7155203484","https://openalex.org/W4401416668","https://openalex.org/W7203696652","https://openalex.org/W7204640368","https://openalex.org/W7165915325","https://openalex.org/W3204240397","https://openalex.org/W4309137642"],"abstract_inverted_index":{"The":[0,192],"integration":[1],"of":[2,87,99],"exteroceptive":[3],"perception":[4],"with":[5],"proprioceptive":[6,103],"control":[7],"has":[8],"revolutionized":[9],"legged":[10],"robot":[11],"locomotion,":[12],"enabling":[13],"navigation":[14],"through":[15],"complex,":[16],"non-flat":[17],"terrains.":[18],"Miki":[19],"et":[20,141],"al.":[21],"(2022)":[22],"established":[23],"a":[24,67,84,109,207],"seminal":[25],"paradigm":[26],"by":[27,172,189],"fusing":[28],"vision":[29],"and":[30,37,51,147,158,181,202],"proprioception":[31],"using":[32],"Recurrent":[33,137,170],"Neural":[34],"Networks":[35],"(RNNs)":[36],"Belief":[38,138],"States.":[39],"However,":[40],"RNN-based":[41],"architectures":[42],"suffer":[43],"from":[44,185],"inherent":[45],"limitations":[46],"in":[47,57,105,155,174],"modeling":[48],"long-horizon":[49],"dependencies":[50],"reacting":[52],"to":[53,94],"high-frequency":[54],"burst":[55],"noise":[56],"sensor":[58,122],"data.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"Trans-Percept":[65,82,166],",":[66],"novel":[68],"end-to-end":[69],"reinforcement":[70],"learning":[71],"architecture":[72],"based":[73],"on":[74,159,177],"Causal":[75],"Spatiotemporal":[76],"Transformers.":[77],"Unlike":[78],"recursive":[79],"belief":[80],"updates,":[81],"processes":[83],"sliding":[85],"window":[86],"raw":[88],"multimodal":[89],"history,":[90],"utilizing":[91],"self-attention":[92],"mechanisms":[93],"dynamically":[95],"weigh":[96],"the":[97,160,168,196],"reliability":[98],"visual":[100,204],"data":[101],"against":[102,128],"feedback":[104],"real-time.":[106],"We":[107,124],"introduce":[108],"\u201cModality":[110],"Confidence\u201d":[111],"masking":[112],"strategy":[113],"during":[114,121],"teacher-student":[115],"training":[116],"that":[117,165],"enforces":[118],"robust":[119],"behavior":[120],"occlusion.":[123],"benchmark":[125],"our":[126],"method":[127,194],"four":[129],"distinct":[130],"baselines:":[131],"(1)":[132],"Blind":[133],"Locomotion":[134],"(RMA),":[135],"(2)":[136],"State":[139],"(Miki":[140],"al.),":[142],"(3)":[143],"Conventional":[144],"Elevation":[145],"Mapping,":[146],"(4)":[148],"A":[149],"Naive":[150],"Vision":[151],"Transformer.":[152],"Extensive":[153],"experiments":[154],"high-fidelity":[156],"simulation":[157],"Unitree":[161],"Go2":[162],"quadruped":[163],"demonstrate":[164],"outperforms":[167],"state-of-the-art":[169],"baseline":[171],"18.4%":[173],"success":[175],"rate":[176],"\u201cvisually":[178],"deceptive\u201d":[179],"terrains":[180],"reduces":[182],"recovery":[183],"time":[184],"unexpected":[186],"external":[187],"perturbations":[188],"0.5s":[190],".":[191],"proposed":[193],"bridges":[195],"gap":[197],"between":[198],"reactive":[199],"blind":[200],"walking":[201],"predictive":[203],"planning,":[205],"offering":[206],"unified":[208],"solution":[209],"for":[210],"wild":[211],"environments.":[212]},"counts_by_year":[],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2026-08-18T00:00:00"}