{"id":"https://openalex.org/W4405710362","doi":"https://doi.org/10.1109/lra.2024.3520894","title":"Multi-Task Reinforcement Learning for Quadrotors","display_name":"Multi-Task Reinforcement Learning for Quadrotors","publication_year":2024,"publication_date":"2024-12-23","ids":{"openalex":"https://openalex.org/W4405710362","doi":"https://doi.org/10.1109/lra.2024.3520894"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3520894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3520894","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":["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/A5031291897","display_name":"Jiaxu Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jiaxu Xing","raw_affiliation_strings":["Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092418578","display_name":"Ismail Geles","orcid":"https://orcid.org/0009-0006-2940-0675"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ismail Geles","raw_affiliation_strings":["Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085971429","display_name":"Yunlong Song","orcid":"https://orcid.org/0000-0002-6352-3744"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yunlong Song","raw_affiliation_strings":["Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065108843","display_name":"Elie Aljalbout","orcid":"https://orcid.org/0000-0003-0590-0043"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Elie Aljalbout","raw_affiliation_strings":["Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057116316","display_name":"Davide Scaramuzza","orcid":"https://orcid.org/0000-0002-3831-6778"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Davide Scaramuzza","raw_affiliation_strings":["Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031291897"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":null,"apc_paid":null,"fwci":3.6026,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.93927543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":"3","first_page":"2112","last_page":"2119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9552000164985657,"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":0.9552000164985657,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9229999780654907,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9154000282287598,"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":0.7911726236343384},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7067691087722778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5982874035835266},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5581679940223694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3691420555114746},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3479771018028259},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20238882303237915},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17322048544883728},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07049143314361572},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.04945647716522217}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7911726236343384},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7067691087722778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5982874035835266},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5581679940223694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3691420555114746},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3479771018028259},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20238882303237915},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17322048544883728},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07049143314361572},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.04945647716522217}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3520894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3520894","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2733312032","https://openalex.org/W2949924544","https://openalex.org/W2962957005","https://openalex.org/W2963796870","https://openalex.org/W2995481444","https://openalex.org/W3206200647","https://openalex.org/W4206742276","https://openalex.org/W4239261738","https://openalex.org/W4283262038","https://openalex.org/W4285102199","https://openalex.org/W4386285856","https://openalex.org/W4386718967","https://openalex.org/W4389667799","https://openalex.org/W4396542455","https://openalex.org/W4400229167","https://openalex.org/W4401416687","https://openalex.org/W4401417288","https://openalex.org/W4402354032","https://openalex.org/W6741002519","https://openalex.org/W6769596995","https://openalex.org/W6775647304","https://openalex.org/W6779282036","https://openalex.org/W6782364735","https://openalex.org/W6801111356","https://openalex.org/W6803156713","https://openalex.org/W6803699115","https://openalex.org/W6863354946","https://openalex.org/W6872193574"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,50],"(RL)":[2],"has":[3],"shown":[4],"great":[5],"effectiveness":[6],"in":[7,18,109,121],"quadrotor":[8,55],"control,":[9,56],"enabling":[10,88],"specialized":[11,23],"policies":[12,24],"to":[13,65,92],"develop":[14],"even":[15],"human-champion-level":[16],"performance":[17],"single-task":[19],"scenarios.":[20],"However,":[21],"these":[22],"often":[25],"struggle":[26],"with":[27],"novel":[28,47],"tasks,":[29,87],"requiring":[30],"a":[31,46,74,89],"complete":[32],"retraining":[33],"of":[34,62,123],"the":[35,58,63],"policy":[36,91],"from":[37],"scratch.":[38],"To":[39],"address":[40],"this":[41,43],"limitation,":[42],"paper":[44],"presents":[45],"multi-task":[48],"reinforcement":[49],"(MTRL)":[51],"framework":[52,82,117],"tailored":[53],"for":[54],"leveraging":[57],"shared":[59,78],"physical":[60],"dynamics":[61],"platform":[64],"enhance":[66],"sample":[67,124],"efficiency":[68,125],"and":[69,77,101,111,126],"task":[70,79,128],"performance.":[71,129],"By":[72],"employing":[73],"multi-critic":[75],"architecture":[76],"encoders,":[80],"our":[81,116],"facilitates":[83],"knowledge":[84],"transfer":[85],"across":[86],"single":[90],"execute":[93],"diverse":[94],"maneuvers,":[95],"including":[96],"high-speed":[97],"stabilization,":[98],"velocity":[99],"tracking,":[100],"autonomous":[102],"racing.":[103],"Our":[104],"experimental":[105],"results,":[106],"validated":[107],"both":[108],"simulation":[110],"real-world":[112],"scenarios,":[113],"demonstrate":[114],"that":[115],"outperforms":[118],"baseline":[119],"approaches":[120],"terms":[122],"overall":[127],"Video":[130],"is":[131],"available":[132],"at":[133],"<uri":[134],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://youtu.be/HfK9UT1OVnY</uri>.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}