{"id":"https://openalex.org/W4415536279","doi":"https://doi.org/10.1145/3746027.3758180","title":"AirScape: An Aerial Generative World Model with Motion Controllability","display_name":"AirScape: An Aerial Generative World Model with Motion Controllability","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536279","doi":"https://doi.org/10.1145/3746027.3758180"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758180","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758180","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758180","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043924969","display_name":"Baining Zhao","orcid":"https://orcid.org/0000-0002-9653-3316"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baining Zhao","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9653-3316","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rongze Tang","orcid":"https://orcid.org/0009-0004-4625-2315"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongze Tang","raw_affiliation_strings":["School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-4625-2315","affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112482415","display_name":"Mingyuan Jia","orcid":null},"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":"Mingyuan Jia","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-4890-7794","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073471363","display_name":"Ziyou Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152629","display_name":"Eastern University","ror":"https://ror.org/05e2ncr14","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210152629"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Ziyou Wang","raw_affiliation_strings":["Computer and Communication Engineering College, Northeastern University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0005-2297-1830","affiliations":[{"raw_affiliation_string":"Computer and Communication Engineering College, Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I4210152629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026025438","display_name":"Fanhang Man","orcid":"https://orcid.org/0000-0002-5830-0685"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Fanhang Man","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5830-0685","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042093698","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0002-2506-7370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Manifold AI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2506-7370","affiliations":[{"raw_affiliation_string":"Manifold AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060571629","display_name":"Yu Shang","orcid":"https://orcid.org/0009-0005-9049-8483"},"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":"Yu Shang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-9049-8483","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024468450","display_name":"Weichen Zhang","orcid":"https://orcid.org/0009-0008-8892-9389"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weichen Zhang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-8892-9389","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101584040","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0001-5757-4476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["Manifold AI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5757-4476","affiliations":[{"raw_affiliation_string":"Manifold AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078622343","display_name":"Chen Gao","orcid":"https://orcid.org/0000-0002-7561-5646"},"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":"Chen Gao","raw_affiliation_strings":["BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7561-5646","affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016095713","display_name":"Xinlei Chen","orcid":"https://orcid.org/0000-0001-8271-5023"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Xinlei Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8271-5023","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355277","display_name":"Yong Li","orcid":"https://orcid.org/0000-0001-5617-1659"},"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":"Yong Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5617-1659","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12519","last_page":"12528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9959999918937683,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9959999918937683,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.972599983215332,"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/motion","display_name":"Motion (physics)","score":0.7584999799728394},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6794000267982483},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6608999967575073},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5898000001907349},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.5572999715805054},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42879998683929443},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.42829999327659607},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4196999967098236}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7584999799728394},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6794000267982483},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6608999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6431000232696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122000217437744},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3880000114440918},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758180","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758180","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758180","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758180","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2996880115","https://openalex.org/W2999156928","https://openalex.org/W3035574168","https://openalex.org/W3109908659","https://openalex.org/W3175099349","https://openalex.org/W4214745154","https://openalex.org/W4312287126","https://openalex.org/W4312913021","https://openalex.org/W4313307856","https://openalex.org/W4360884927","https://openalex.org/W4386075779","https://openalex.org/W4388224702","https://openalex.org/W4390872297","https://openalex.org/W4391468387","https://openalex.org/W4392866731","https://openalex.org/W4394862905","https://openalex.org/W4399324146","https://openalex.org/W4402660110","https://openalex.org/W4402727415","https://openalex.org/W4402727699","https://openalex.org/W4403338712","https://openalex.org/W4404965692","https://openalex.org/W4405013818","https://openalex.org/W4406793847","https://openalex.org/W4409356457","https://openalex.org/W4410068177","https://openalex.org/W4412889658","https://openalex.org/W4413146238"],"related_works":[],"abstract_inverted_index":{"How":[0],"to":[1,4,104,125],"enable":[2],"agents":[3],"predict":[5],"the":[6,33,94],"outcomes":[7],"of":[8,69,86,110],"their":[9],"own":[10],"motion":[11,53,96,121,153],"intentions":[12,122],"in":[13,21,139,150],"three-dimensional":[14],"space":[15],"has":[16],"been":[17],"a":[18,58,83,101,106,114,147],"fundamental":[19],"problem":[20],"embodied":[22,111],"intelligence.":[23],"To":[24],"explore":[25],"general":[26],"spatial":[27,112,141],"imagination":[28,142],"capability,":[29],"we":[30,56,99],"present":[31],"AirScape,":[32],"first":[34],"world":[35,62,115],"model":[36,63,116],"designed":[37],"for":[38,60],"six-degree-of-freedom":[39],"aerial":[40,61],"agents.":[41],"AirScape":[42,133],"predicts":[43],"future":[44],"observation":[45],"sequences":[46],"based":[47],"on":[48],"current":[49],"visual":[50],"inputs":[51],"and":[52,65,123],"intentions.":[54,97],"Specifically,":[55],"construct":[57],"dataset":[59,74],"training":[64],"testing,":[66],"which":[67],"consists":[68],"11k":[70],"video-intention":[71],"pairs.":[72],"This":[73],"includes":[75],"first-person-view":[76],"videos":[77],"capturing":[78],"diverse":[79],"drone":[80],"actions":[81],"across":[82],"wide":[84],"range":[85],"scenarios,":[87],"with":[88,145],"over":[89,146],"1,000":[90],"hours":[91],"spent":[92],"annotating":[93],"corresponding":[95],"Then":[98],"develop":[100],"two-phase":[102],"schedule":[103],"train":[105],"foundation":[107,137],"model-initially":[108],"devoid":[109],"knowledge-into":[113],"that":[117,132],"is":[118,157],"controllable":[119],"by":[120],"adheres":[124],"physical":[126],"spatio-temporal":[127],"constraints.":[128],"Experimental":[129],"results":[130],"demonstrate":[131],"significantly":[134],"outperforms":[135],"existing":[136],"models":[138],"3D":[140],"capabilities,":[143],"especially":[144],"50%":[148],"improvement":[149],"metrics":[151],"reflecting":[152],"alignment.":[154],"The":[155],"project":[156],"available":[158],"at:":[159],"https://embodiedcity.github.io/AirScape/.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}