{"id":"https://openalex.org/W4389665598","doi":"https://doi.org/10.1109/iros55552.2023.10341941","title":"Comparing Quadrotor Control Policies for Zero-Shot Reinforcement Learning under Uncertainty and Partial Observability","display_name":"Comparing Quadrotor Control Policies for Zero-Shot Reinforcement Learning under Uncertainty and Partial Observability","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665598","doi":"https://doi.org/10.1109/iros55552.2023.10341941"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5020980906","display_name":"Sven Gronauer","orcid":"https://orcid.org/0000-0002-0047-5116"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sven Gronauer","raw_affiliation_strings":["TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093479807","display_name":"Daniel St\u00fcmke","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel St\u00fcmke","raw_affiliation_strings":["TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074346065","display_name":"Klaus Diepold","orcid":"https://orcid.org/0000-0003-0439-7511"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Diepold","raw_affiliation_strings":["TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020980906"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67370964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7508","last_page":"7514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9887999892234802,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.7909538745880127},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7129224538803101},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7030845880508423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6912263035774231},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5247226357460022},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.48985549807548523},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.44133320450782776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42013463377952576},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.417896568775177},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3868347108364105},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.36275404691696167},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3248445987701416},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2555726170539856},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20180538296699524}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7909538745880127},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7129224538803101},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7030845880508423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912263035774231},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5247226357460022},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.48985549807548523},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.44133320450782776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42013463377952576},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.417896568775177},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3868347108364105},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36275404691696167},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3248445987701416},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2555726170539856},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20180538296699524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.47999998927116394,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2418817242","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2754517384","https://openalex.org/W2902907165","https://openalex.org/W2982095652","https://openalex.org/W3003669699","https://openalex.org/W3010884024","https://openalex.org/W3038194455","https://openalex.org/W3102552342","https://openalex.org/W3121342653","https://openalex.org/W3136542217","https://openalex.org/W3189225861","https://openalex.org/W3202883604","https://openalex.org/W4200630212","https://openalex.org/W4225492787","https://openalex.org/W4285102199","https://openalex.org/W4312992339","https://openalex.org/W4383109238","https://openalex.org/W4396910019","https://openalex.org/W6627932998","https://openalex.org/W6757184387","https://openalex.org/W6775089412","https://openalex.org/W6782364735","https://openalex.org/W6802227391"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990","https://openalex.org/W2615757685"],"abstract_inverted_index":{"To":[0],"alleviate":[1],"the":[2,20,37,72,79],"sample":[3],"complexity":[4],"of":[5,74],"reinforcement":[6],"learning":[7],"algorithms,":[8],"simulations":[9],"are":[10,178,186],"a":[11,23,27,53,57,105,118,131],"common":[12],"approach":[13],"to":[14,39,52],"train":[15,40],"control":[16,70,117,140],"policies":[17,42,67,88,141,149],"before":[18],"deploying":[19],"policy":[21],"on":[22,104,121,152],"real-world":[24,106],"robot.":[25],"However,":[26],"gap":[28],"between":[29],"simulation":[30,45],"and":[31,98,102,145],"reality":[32],"generally":[33],"persists,":[34],"which":[35],"endorses":[36],"aim":[38],"robust":[41],"already":[43],"in":[44,71,84],"such":[46,183],"that":[47,138,175],"those":[48],"can":[49,116],"be":[50],"transferred":[51],"real":[54],"robot":[55],"at":[56],"high":[58],"success":[59,164],"rate.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,109],"investigate":[65],"history-dependent":[66],"for":[68,166],"drone":[69],"context":[73],"zero-shot":[75],"transfer":[76,168],"learning,":[77],"where":[78],"training":[80],"is":[81],"conducted":[82],"exclusively":[83],"simulation.":[85],"We":[86,172],"compare":[87],"represented":[89],"by":[90],"feed-forward":[91,148,170],"neural":[92,96],"networks":[93,97,161],"with":[94],"recurrent":[95,139,160,176],"assess":[99],"both":[100],"performance":[101,144],"robustness":[103,146],"quadrotor.":[107],"Furthermore,":[108],"study":[110],"if":[111],"an":[112],"end-to-end":[113],"learned":[114],"representation":[115],"quadrotor":[119],"based":[120],"raw":[122,156],"onboard-sensor":[123],"information":[124],"only,":[125],"rendering":[126],"accurate":[127],"state":[128,153],"estimation":[129],"from":[130],"Kalman":[132],"filter":[133],"obsolete.":[134],"Our":[135],"results":[136],"show":[137],"achieve":[142],"similar":[143],"as":[147,184],"when":[150,180],"acting":[151],"estimates.":[154],"With":[155],"sensory":[157],"data,":[158],"however,":[159],"offer":[162],"higher":[163],"rates":[165],"sim-to-real":[167],"than":[169],"networks.":[171],"also":[173],"find":[174],"architectures":[177],"advantageous":[179],"system":[181],"parameters":[182],"latency":[185],"uncertain.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}