{"id":"https://openalex.org/W3134537774","doi":"https://doi.org/10.1109/iros51168.2021.9635857","title":"Learning to Fly\u2014a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","display_name":"Learning to Fly\u2014a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3134537774","doi":"https://doi.org/10.1109/iros51168.2021.9635857","mag":"3134537774"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9635857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.02142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038164962","display_name":"Jacopo Panerati","orcid":"https://orcid.org/0000-0003-2994-5422"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I3143791293","display_name":"Institute for Christian Studies","ror":"https://ror.org/054dn2d35","country_code":"CA","type":"education","lineage":["https://openalex.org/I3143791293"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jacopo Panerati","raw_affiliation_strings":["Institute for Aerospace Studies, University of Toronto, Canada","Vector Institute for Artificial Intelligence in Toronto","1 and 2"],"affiliations":[{"raw_affiliation_string":"Institute for Aerospace Studies, University of Toronto, Canada","institution_ids":["https://openalex.org/I3143791293","https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence in Toronto","institution_ids":["https://openalex.org/I4210127509"]},{"raw_affiliation_string":"1 and 2","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006008705","display_name":"Hehui Zheng","orcid":"https://orcid.org/0000-0002-4977-0220"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hehui Zheng","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom","Univ. of Cambridge"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Univ. of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048199386","display_name":"Siqi Zhou","orcid":"https://orcid.org/0000-0001-7240-546X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I3143791293","display_name":"Institute for Christian Studies","ror":"https://ror.org/054dn2d35","country_code":"CA","type":"education","lineage":["https://openalex.org/I3143791293"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"SiQi Zhou","raw_affiliation_strings":["Institute for Aerospace Studies, University of Toronto, Canada","Vector Institute for Artificial Intelligence in Toronto","1 and 2"],"affiliations":[{"raw_affiliation_string":"Institute for Aerospace Studies, University of Toronto, Canada","institution_ids":["https://openalex.org/I3143791293","https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence in Toronto","institution_ids":["https://openalex.org/I4210127509"]},{"raw_affiliation_string":"1 and 2","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109061634","display_name":"James Y. Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I3143791293","display_name":"Institute for Christian Studies","ror":"https://ror.org/054dn2d35","country_code":"CA","type":"education","lineage":["https://openalex.org/I3143791293"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James Xu","raw_affiliation_strings":["Institute for Aerospace Studies, University of Toronto, Canada","University of Toronto, Institute for Aerospace Studies"],"affiliations":[{"raw_affiliation_string":"Institute for Aerospace Studies, University of Toronto, Canada","institution_ids":["https://openalex.org/I3143791293","https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Institute for Aerospace Studies","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066624177","display_name":"Amanda Prorok","orcid":"https://orcid.org/0000-0001-7313-5983"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amanda Prorok","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom","Univ. of Cambridge"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Univ. of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052147335","display_name":"Angela P. Schoellig","orcid":"https://orcid.org/0000-0003-4012-4668"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I3143791293","display_name":"Institute for Christian Studies","ror":"https://ror.org/054dn2d35","country_code":"CA","type":"education","lineage":["https://openalex.org/I3143791293"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Angela P. Schoellig","raw_affiliation_strings":["Institute for Aerospace Studies, University of Toronto, Canada","Vector Institute for Artificial Intelligence in Toronto","University of Toronto, Institute for Aerospace Studies"],"affiliations":[{"raw_affiliation_string":"Institute for Aerospace Studies, University of Toronto, Canada","institution_ids":["https://openalex.org/I3143791293","https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence in Toronto","institution_ids":["https://openalex.org/I4210127509"]},{"raw_affiliation_string":"University of Toronto, Institute for Aerospace Studies","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5038164962"],"corresponding_institution_ids":["https://openalex.org/I185261750","https://openalex.org/I3143791293","https://openalex.org/I4210127509"],"apc_list":null,"apc_paid":null,"fwci":1.6496,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.86637095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7512","last_page":"7519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9883000254631042,"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/T10524","display_name":"Traffic control and management","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.864810585975647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6185632944107056},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.5044959783554077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4939799904823303},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.448154091835022},{"id":"https://openalex.org/keywords/physics-engine","display_name":"Physics engine","score":0.44334858655929565},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4155423641204834},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.39628171920776367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3204120993614197},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.11698734760284424}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.864810585975647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6185632944107056},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.5044959783554077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4939799904823303},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.448154091835022},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.44334858655929565},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4155423641204834},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.39628171920776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3204120993614197},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.11698734760284424},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros51168.2021.9635857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.02142","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02142","pdf_url":"https://arxiv.org/pdf/2103.02142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"mag:3134537774","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2103.02142","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.02142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.02142","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.02142","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02142","pdf_url":"https://arxiv.org/pdf/2103.02142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G3969759488","display_name":null,"funder_award_id":"program","funder_id":"https://openalex.org/F4320322675","funder_display_name":"Mitacs"},{"id":"https://openalex.org/G5904765876","display_name":null,"funder_award_id":"Elevate","funder_id":"https://openalex.org/F4320322675","funder_display_name":"Mitacs"}],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"},{"id":"https://openalex.org/F4320332453","display_name":"General Dynamics Land Systems","ror":"https://ror.org/05pyq8e17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134537774.pdf","grobid_xml":"https://content.openalex.org/works/W3134537774.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W80180111","https://openalex.org/W2115579991","https://openalex.org/W2158782408","https://openalex.org/W2162991084","https://openalex.org/W2465948386","https://openalex.org/W2511710936","https://openalex.org/W2615547864","https://openalex.org/W2822752092","https://openalex.org/W2901402208","https://openalex.org/W2948013437","https://openalex.org/W2954048160","https://openalex.org/W2962890638","https://openalex.org/W2963094322","https://openalex.org/W2963120839","https://openalex.org/W3003669699","https://openalex.org/W3013146177","https://openalex.org/W3013618273","https://openalex.org/W3034956653","https://openalex.org/W3037207827","https://openalex.org/W3106152188","https://openalex.org/W3141505394","https://openalex.org/W3155747680","https://openalex.org/W6725478704","https://openalex.org/W6744123322","https://openalex.org/W6752963931","https://openalex.org/W6762919599","https://openalex.org/W6775522024","https://openalex.org/W6780559895","https://openalex.org/W6782364735","https://openalex.org/W6910476156","https://openalex.org/W7070460818"],"related_works":["https://openalex.org/W3083092137","https://openalex.org/W3212211932","https://openalex.org/W2890803796","https://openalex.org/W2120569901","https://openalex.org/W3119387236","https://openalex.org/W3101926919","https://openalex.org/W2076745239","https://openalex.org/W2135765924","https://openalex.org/W2114882146","https://openalex.org/W2964227158","https://openalex.org/W2899455822","https://openalex.org/W3100944043","https://openalex.org/W2575705757","https://openalex.org/W1520597402","https://openalex.org/W2952695043","https://openalex.org/W2973019294","https://openalex.org/W3203679646","https://openalex.org/W3205292911","https://openalex.org/W2262174858","https://openalex.org/W3008009191"],"abstract_inverted_index":{"Robotic":[0],"simulators":[1,47],"are":[2],"crucial":[3],"for":[4,61,106,154],"academic":[5],"research":[6,178],"and":[7,51,77,92,117,130,170,183],"education":[8],"as":[9,11,122,124],"well":[10,123],"the":[12,28,38,83,111,125,136],"development":[13,39],"of":[14,30,42,127,138,143],"safety-critical":[15],"applications.":[16],"Reinforcement":[17],"learning":[18,43,57,76,94,120,168],"environments\u2014":[19],"simple":[20],"simulations":[21],"coupled":[22],"with":[23,158,163],"a":[24,31,141],"problem":[25],"specification":[26],"in":[27,65],"form":[29],"reward":[32],"function\u2014are":[33],"also":[34],"important":[35],"to":[36,86,135,175],"standardize":[37],"(and":[40],"benchmarking)":[41],"algorithms.":[44],"Yet,":[45],"full-scale":[46],"typically":[48],"lack":[49,82],"portability":[50],"paral-lelizability.":[52],"Vice":[53],"versa,":[54],"many":[55],"reinforcement":[56,93,119,167],"environments":[58],"trade-off":[59],"realism":[60],"high":[62],"sample":[63],"throughputs":[64],"toy-like":[66],"problems.":[67],"While":[68],"public":[69],"data":[70],"sets":[71],"have":[72],"greatly":[73],"benefited":[74],"deep":[75],"computer":[78],"vision,":[79],"we":[80,99],"still":[81],"software":[84],"tools":[85],"simultaneously":[87],"develop\u2014and":[88],"fairly":[89],"compare\u2014control":[90],"theory":[91,182],"approaches.":[95],"In":[96],"this":[97],"paper,":[98],"propose":[100],"an":[101],"open-source":[102],"OpenAI":[103],"Gym-like":[104],"environment":[105],"multiple":[107],"quadcopters":[108],"based":[109],"on":[110],"Bullet":[112],"physics":[113],"engine.":[114],"Its":[115],"multi-agent":[116,171],"vision-based":[118],"interfaces,":[121],"support":[126],"realistic":[128],"collisions":[129],"aerodynamic":[131],"effects,":[132],"make":[133],"it,":[134],"best":[137],"our":[139],"knowledge,":[140],"first":[142],"its":[144,148],"kind.":[145],"We":[146],"demonstrate":[147],"use":[149],"through":[150],"several":[151],"examples,":[152],"either":[153],"control":[155,181],"(trajectory":[156],"tracking":[157],"PID":[159],"control,":[160],"multi-robot":[161],"flight":[162],"downwash,":[164],"etc.)":[165],"or":[166],"(single":[169],"stabilization":[172],"tasks),":[173],"hoping":[174],"inspire":[176],"future":[177],"that":[179],"combines":[180],"machine":[184],"learning.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}