{"id":"https://openalex.org/W3178845376","doi":"https://doi.org/10.1007/s10994-021-06006-6","title":"Air Learning: a deep reinforcement learning gym for autonomous aerial robot visual navigation","display_name":"Air Learning: a deep reinforcement learning gym for autonomous aerial robot visual navigation","publication_year":2021,"publication_date":"2021-07-07","ids":{"openalex":"https://openalex.org/W3178845376","doi":"https://doi.org/10.1007/s10994-021-06006-6","mag":"3178845376"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-021-06006-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06006-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06006-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06006-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058825852","display_name":"Srivatsan Krishnan","orcid":"https://orcid.org/0000-0002-7148-5389"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Srivatsan Krishnan","raw_affiliation_strings":["Harvard University, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089709128","display_name":"Behzad Boroujerdian","orcid":"https://orcid.org/0000-0003-3655-266X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Behzad Boroujerdian","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013339756","display_name":"William Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Fu","raw_affiliation_strings":["Harvard University, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002971435","display_name":"Aleksandra Faust","orcid":"https://orcid.org/0000-0002-3268-8685"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aleksandra Faust","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000635267","display_name":"Vijay Janapa Reddi","orcid":"https://orcid.org/0000-0002-5259-7721"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Janapa Reddi","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058825852"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":3.9432,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.946351,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"110","issue":"9","first_page":"2501","last_page":"2540"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9972000122070312,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7289388179779053},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7283897399902344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6009485721588135},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5113314986228943},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4754997193813324},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4527081847190857},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.4101758897304535},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3662516474723816},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3598710596561432},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3575156033039093},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.11751312017440796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289388179779053},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7283897399902344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6009485721588135},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5113314986228943},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4754997193813324},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4527081847190857},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.4101758897304535},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3662516474723816},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3598710596561432},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3575156033039093},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.11751312017440796},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-021-06006-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06006-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06006-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-021-06006-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06006-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06006-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320309622","display_name":"Harvard University","ror":"https://ror.org/03vek6s52"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3178845376.pdf","grobid_xml":"https://content.openalex.org/works/W3178845376.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W40338364","https://openalex.org/W158183001","https://openalex.org/W190583841","https://openalex.org/W589244474","https://openalex.org/W1480527676","https://openalex.org/W1757796397","https://openalex.org/W1820232481","https://openalex.org/W1849277567","https://openalex.org/W1969161726","https://openalex.org/W2024591926","https://openalex.org/W2081329272","https://openalex.org/W2089087399","https://openalex.org/W2096533821","https://openalex.org/W2158782408","https://openalex.org/W2159570978","https://openalex.org/W2167340365","https://openalex.org/W2296073425","https://openalex.org/W2296673577","https://openalex.org/W2342840547","https://openalex.org/W2410630689","https://openalex.org/W2467042364","https://openalex.org/W2529573675","https://openalex.org/W2529658650","https://openalex.org/W2575705757","https://openalex.org/W2604185556","https://openalex.org/W2605102758","https://openalex.org/W2609009256","https://openalex.org/W2609239033","https://openalex.org/W2610925780","https://openalex.org/W2615547864","https://openalex.org/W2733312032","https://openalex.org/W2736373118","https://openalex.org/W2736601468","https://openalex.org/W2738612236","https://openalex.org/W2767621168","https://openalex.org/W2769434793","https://openalex.org/W2788842776","https://openalex.org/W2792036039","https://openalex.org/W2810785043","https://openalex.org/W2888235455","https://openalex.org/W2890803796","https://openalex.org/W2891230768","https://openalex.org/W2899733099","https://openalex.org/W2907258563","https://openalex.org/W2912063360","https://openalex.org/W2950268955","https://openalex.org/W2952186574","https://openalex.org/W2952509347","https://openalex.org/W2952768114","https://openalex.org/W2962759351","https://openalex.org/W2962890638","https://openalex.org/W2962957005","https://openalex.org/W2963252944","https://openalex.org/W2964081807","https://openalex.org/W2975673761","https://openalex.org/W2999905431","https://openalex.org/W3012012823","https://openalex.org/W3029539653","https://openalex.org/W3037207827","https://openalex.org/W3104173699","https://openalex.org/W3106462682","https://openalex.org/W4365799919","https://openalex.org/W6617386103","https://openalex.org/W6628627537","https://openalex.org/W6674304311","https://openalex.org/W6704559304","https://openalex.org/W6741002519","https://openalex.org/W6745851918","https://openalex.org/W6745935785","https://openalex.org/W6767997047","https://openalex.org/W6780559895","https://openalex.org/W7025024117"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2897743049","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4226140413","https://openalex.org/W4391331176","https://openalex.org/W2031695474"],"abstract_inverted_index":{"Abstract":[0],"We":[1,38,92,152,243],"introduce":[2],"Air":[3,25,62,135,224,262],"Learning,":[4],"an":[5,98,192],"open-source":[6],"simulator,":[7],"and":[8,51,56,79,231],"a":[9,28,32,89,108,148,155,265],"gym":[10],"environment":[11],"for":[12],"deep":[13,269],"reinforcement":[14],"learning":[15],"research":[16,271],"on":[17,84,97,107,147,171,177,255,272],"resource-constrained":[18,85],"aerial":[19,178,240],"robots.":[20],"Equipped":[21],"with":[22,42,202,226],"domain":[23],"randomization,":[24],"Learning":[26,63,136,225,263],"exposes":[27,232],"UAV":[29],"agent":[30],"to":[31,115,137,143,162,207,221,248],"diverse":[33],"set":[34],"of":[35,123,130,167,252,268],"challenging":[36],"scenarios.":[37],"seed":[39],"the":[40,65,75,80,95,124,128,160,164,169,172,185,196,200,209,214,234,239,250,256],"toolset":[41],"point-to-point":[43],"obstacle":[44],"avoidance":[45],"tasks":[46],"in":[47,113,121,213],"three":[48],"different":[49,103],"environments":[50],"Deep":[52],"Q":[53],"Networks":[54],"(DQN)":[55],"Proximal":[57],"Policy":[58],"Optimization":[59],"(PPO)":[60],"trainers.":[61],"assesses":[64],"policies\u2019":[66],"performance":[67,142],"under":[68],"various":[69],"quality-of-flight":[70],"(QoF)":[71],"metrics,":[72],"such":[73,131],"as":[74,191],"energy":[76],"consumed,":[77],"endurance,":[78],"average":[81],"trajectory":[82],"length,":[83],"embedded":[86,99,150],"platforms":[87],"like":[88],"Raspberry":[90],"Pi.":[91],"find":[93],"that":[94,158],"trajectories":[96,120],"Ras-Pi":[100],"are":[101],"vastly":[102],"from":[104,184,219],"those":[105,229],"predicted":[106],"high-end":[109,140],"desktop":[110,141],"system,":[111],"resulting":[112],"up":[114],"$$40\\%$$":[116],"<mml:math":[117],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mn>40</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math>":[118],"longer":[119],"one":[122],"environments.":[125],"To":[126],"understand":[127],"source":[129,275],"discrepancies,":[132],"we":[133],"use":[134],"artificially":[138],"degrade":[139],"mimic":[144],"what":[145],"happens":[146],"low-end":[149],"system.":[151],"then":[153,189],"propose":[154],"mitigation":[156],"technique":[157],"uses":[159],"hardware-in-the-loop":[161,227],"determine":[163],"latency":[165,183,186],"distribution":[166,187],"running":[168],"policy":[170,201],"target":[173],"platform":[174],"(onboard":[175],"compute":[176],"robot).":[179],"A":[180],"randomly":[181],"sampled":[182],"is":[188,277],"added":[190],"artificial":[193,203],"delay":[194],"within":[195],"training":[197],"loop.":[198],"Training":[199],"delays":[204],"allows":[205],"us":[206],"minimize":[208],"hardware":[210],"gap":[211],"(discrepancy":[212],"flight":[215],"time":[216],"metric":[217],"reduced":[218],"37.73%":[220],"0.5%).":[222],"Thus,":[223],"characterizes":[228],"differences":[230],"how":[233],"onboard":[235],"compute\u2019s":[236],"choice":[237],"affects":[238],"robot\u2019s":[241],"performance.":[242],"also":[244],"conduct":[245],"reliability":[246],"studies":[247],"assess":[249],"effect":[251],"sensor":[253],"failures":[254],"learned":[257],"policies.":[258],"All":[259],"put":[260],"together,":[261],"enables":[264],"broad":[266],"class":[267],"RL":[270],"UAVs.":[273],"The":[274],"code":[276],"available":[278],"at:":[279],"https://github.com/harvard-edge/AirLearning":[280],".":[281]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}