{"id":"https://openalex.org/W4281717241","doi":"https://doi.org/10.1109/icra46639.2022.9812368","title":"Narrowing the coordinate-frame gap in behavior prediction models: Distillation for efficient and accurate scene-centric motion forecasting","display_name":"Narrowing the coordinate-frame gap in behavior prediction models: Distillation for efficient and accurate scene-centric motion forecasting","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4281717241","doi":"https://doi.org/10.1109/icra46639.2022.9812368"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812368","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041890767","display_name":"DiJia Su","orcid":"https://orcid.org/0000-0001-9369-4715"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DiJia Andy Su","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022459396","display_name":"Bertrand Douillard","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bertrand Douillard","raw_affiliation_strings":["Waymo LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025234902","display_name":"Rami Al\u2010Rfou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rami Al-Rfou","raw_affiliation_strings":["Waymo LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077092452","display_name":"Cheol Woo Park","orcid":"https://orcid.org/0000-0002-3650-1558"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cheol Park","raw_affiliation_strings":["Waymo LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014258241","display_name":"Benjamin Sapp","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Sapp","raw_affiliation_strings":["Waymo LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0559,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93490287,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10370","display_name":"Traffic and Road Safety","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7567704916000366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6595554947853088},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5461493730545044},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5017507076263428},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4476161599159241},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.4323587417602539},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4316312074661255},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4181002676486969},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3514634370803833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567704916000366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6595554947853088},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5461493730545044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5017507076263428},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4476161599159241},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.4323587417602539},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4316312074661255},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4181002676486969},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3514634370803833},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812368","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W1821462560","https://openalex.org/W2424778531","https://openalex.org/W2607296803","https://openalex.org/W2894978157","https://openalex.org/W2898900571","https://openalex.org/W2905173465","https://openalex.org/W2940129212","https://openalex.org/W2945289329","https://openalex.org/W2955189650","https://openalex.org/W2955425717","https://openalex.org/W2962101532","https://openalex.org/W2963001155","https://openalex.org/W2963736842","https://openalex.org/W2963759562","https://openalex.org/W2968296999","https://openalex.org/W2980087597","https://openalex.org/W2982745079","https://openalex.org/W2986406093","https://openalex.org/W2995999067","https://openalex.org/W3000520642","https://openalex.org/W3012478636","https://openalex.org/W3028769608","https://openalex.org/W3034223443","https://openalex.org/W3034722190","https://openalex.org/W3035574168","https://openalex.org/W3035671534","https://openalex.org/W3062588417","https://openalex.org/W3090166818","https://openalex.org/W3090789587","https://openalex.org/W3108486966","https://openalex.org/W3116651890","https://openalex.org/W3125605478","https://openalex.org/W3156216502","https://openalex.org/W3169575318","https://openalex.org/W3171077607","https://openalex.org/W3180491419","https://openalex.org/W4287685696","https://openalex.org/W6638523607","https://openalex.org/W6754877132","https://openalex.org/W6755864109","https://openalex.org/W6756871163","https://openalex.org/W6762718338","https://openalex.org/W6762811270","https://openalex.org/W6766065261","https://openalex.org/W6767342764","https://openalex.org/W6768870957","https://openalex.org/W6769043036","https://openalex.org/W6769921281","https://openalex.org/W6773443883","https://openalex.org/W6779371077","https://openalex.org/W6781231738","https://openalex.org/W6782088249","https://openalex.org/W6782468546","https://openalex.org/W6796929002"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Behavior":[0],"prediction":[1],"models":[2,62,72,100,136,210],"have":[3,137],"proliferated":[4],"in":[5,9,68,174,213,229],"recent":[6],"years,":[7],"especially":[8],"the":[10,20,39,92,113,130,172,189],"popular":[11],"real-world":[12],"robotics":[13],"application":[14],"of":[15,25,41,58,94,115,132],"autonomous":[16],"driving,":[17],"where":[18],"representing":[19],"distribution":[21],"over":[22],"possible":[23],"futures":[24],"moving":[26],"agents":[27,95],"is":[28],"essential":[29],"for":[30],"safe":[31],"and":[32,47,65,78,96,143,148,166,178,198,216],"comfortable":[33],"motion":[34,163],"planning.":[35],"In":[36,153],"these":[37,135,168],"models,":[38,165],"choice":[40],"coordinate":[42,104],"frames":[43],"to":[44,76,106,138,141,170,200,219],"represent":[45],"inputs":[46,64],"outputs":[48],"has":[49],"crucial":[50],"trade":[51],"offs":[52],"which":[53,126],"broadly":[54],"fall":[55],"into":[56],"one":[57],"two":[59],"categories.":[60],"Agent-centric":[61],"transform":[63],"perform":[66],"inference":[67,124],"agent-centric":[69,151,177,226],"coordinates.":[70],"These":[71,207],"are":[73,83,217],"intrinsically":[74],"invari-ant":[75],"translation":[77,142],"rotation":[79,144],"between":[80,145,161,176],"scene":[81,97,146],"elements,":[82,147],"best-performing":[84],"on":[85,188,194,202],"public":[86,190,214],"leaderboards,":[87],"but":[88],"scale":[89],"quadratically":[90],"with":[91,129],"number":[93,131],"elements.":[98],"Scene-centric":[99],"use":[101],"a":[102,203],"fixed":[103],"system":[105],"process":[107],"all":[108,119],"agents.":[109,133],"This":[110,181],"gives":[111],"them":[112],"advantage":[114],"sharing":[116],"representations":[117],"among":[118],"agents,":[120],"offering":[121],"efficient":[122,223],"amortized":[123],"computation":[125],"scales":[127],"linearly":[128],"However,":[134],"learn":[139],"invariance":[140],"typically":[149],"underperform":[150],"models.":[152,180],"this":[154],"work,":[155],"we":[156],"develop":[157],"knowledge":[158],"distillation":[159],"techniques":[160,169],"probabilistic":[162],"forecasting":[164],"apply":[167],"close":[171],"gap":[173],"performance":[175,185],"scene-centric":[179,183,209],"improves":[182],"model":[184],"by":[186],"13.2%":[187],"Argoverse":[191],"benchmark,":[192],"7.8%":[193],"Waymo":[195],"Open":[196],"Dataset":[197],"up":[199,218],"9.4%":[201],"large":[204],"In-House":[205],"dataset.":[206],"improved":[208],"rank":[211],"highly":[212],"leaderboards":[215],"15":[220],"times":[221],"more":[222],"than":[224],"their":[225],"teacher":[227],"counterparts":[228],"busy":[230],"scenes.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}