{"id":"https://openalex.org/W3201459714","doi":"https://doi.org/10.1109/icra46639.2022.9812122","title":"Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC","display_name":"Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3201459714","doi":"https://doi.org/10.1109/icra46639.2022.9812122","mag":"3201459714"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812122","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102712548","display_name":"Andrea Tagliabue","orcid":"https://orcid.org/0000-0003-3376-4114"},"institutions":[{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Tagliabue","raw_affiliation_strings":["MIT Department of Aeronautics and Astronautics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Department of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I46020346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033449275","display_name":"Dong Ki Kim","orcid":"https://orcid.org/0000-0002-5195-7852"},"institutions":[{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong-Ki Kim","raw_affiliation_strings":["MIT Department of Aeronautics and Astronautics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Department of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I46020346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064513857","display_name":"Michael Everett","orcid":"https://orcid.org/0000-0001-9377-6745"},"institutions":[{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Everett","raw_affiliation_strings":["MIT Department of Aeronautics and Astronautics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Department of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I46020346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["MIT Department of Aeronautics and Astronautics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Department of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I46020346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I46020346"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"462","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10409","display_name":"Fuel Cells and Related Materials","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.984000027179718,"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/computer-science","display_name":"Computer science","score":0.7467470765113831},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7290102243423462},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6153671145439148},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5545571446418762},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5450667142868042},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4883827567100525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44830361008644104},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4434446096420288},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.42138928174972534},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32432547211647034},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.28124773502349854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11479943990707397},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09428173303604126},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.08309638500213623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467470765113831},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7290102243423462},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6153671145439148},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5545571446418762},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5450667142868042},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4883827567100525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44830361008644104},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4434446096420288},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.42138928174972534},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32432547211647034},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.28124773502349854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11479943990707397},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09428173303604126},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.08309638500213623},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812122","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W195033972","https://openalex.org/W1522301498","https://openalex.org/W1923344279","https://openalex.org/W1931877416","https://openalex.org/W1980969546","https://openalex.org/W1981723834","https://openalex.org/W2104733512","https://openalex.org/W2105143952","https://openalex.org/W2121863487","https://openalex.org/W2167224731","https://openalex.org/W2290094632","https://openalex.org/W2342840547","https://openalex.org/W2396217537","https://openalex.org/W2410617946","https://openalex.org/W2559336140","https://openalex.org/W2595845486","https://openalex.org/W2749680651","https://openalex.org/W2767050701","https://openalex.org/W2774527530","https://openalex.org/W2794908222","https://openalex.org/W2806163172","https://openalex.org/W2903459254","https://openalex.org/W2925761457","https://openalex.org/W2952996256","https://openalex.org/W2962957031","https://openalex.org/W2962999504","https://openalex.org/W2964070888","https://openalex.org/W2964121744","https://openalex.org/W2968116426","https://openalex.org/W2972830116","https://openalex.org/W2972864268","https://openalex.org/W2982095652","https://openalex.org/W2991276239","https://openalex.org/W2994088087","https://openalex.org/W2994931756","https://openalex.org/W2997406364","https://openalex.org/W2999862950","https://openalex.org/W3003342008","https://openalex.org/W3033405912","https://openalex.org/W3038825904","https://openalex.org/W3039984786","https://openalex.org/W3097841467","https://openalex.org/W3100238596","https://openalex.org/W3101126850","https://openalex.org/W3101442004","https://openalex.org/W3102552342","https://openalex.org/W3105570727","https://openalex.org/W3138964531","https://openalex.org/W3149314533","https://openalex.org/W3158675508","https://openalex.org/W3181621367","https://openalex.org/W3205884165","https://openalex.org/W3206739224","https://openalex.org/W6607786297","https://openalex.org/W6631190155","https://openalex.org/W6640174482","https://openalex.org/W6675708744","https://openalex.org/W6675999342","https://openalex.org/W6704559304","https://openalex.org/W6712453370","https://openalex.org/W6734827232","https://openalex.org/W6747311492","https://openalex.org/W6751669119","https://openalex.org/W6770979763","https://openalex.org/W6784826119"],"related_works":["https://openalex.org/W2002388147","https://openalex.org/W3098928304","https://openalex.org/W2394883510","https://openalex.org/W2150958483","https://openalex.org/W2165013373","https://openalex.org/W2922503265","https://openalex.org/W2023324176","https://openalex.org/W2121097709","https://openalex.org/W3097920840","https://openalex.org/W196429367"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,7,15,22,32,48,75,80,85,88,91,95,107,112],"demonstration-efficient":[3],"strategy":[4],"to":[5,94,136],"compress":[6],"computationally":[8,17],"expensive":[9],"Model":[10],"Predictive":[11],"Controller":[12],"(MPC)":[13],"into":[14],"more":[16],"efficient":[18],"representation":[19],"based":[20],"on":[21,106],"deep":[23],"neural":[24],"network":[25],"and":[26,40,102,127,134],"Imitation":[27],"Learning":[28],"(IL).":[29],"By":[30],"generating":[31],"Robust":[33],"Tube":[34],"variant":[35],"(RTMPC)":[36],"of":[37,57,71,132],"the":[38,44,59,69],"MPC":[39,110],"leveraging":[41],"properties":[42],"from":[43,74],"tube,":[45],"we":[46],"introduce":[47],"data":[49],"augmentation":[50],"method":[51,117],"that":[52,115],"enables":[53],"high":[54],"demonstration-efficiency,":[55],"capable":[56],"compensating":[58],"distribution":[60],"shifts":[61],"typically":[62],"encountered":[63],"in":[64,79,90,122,130],"IL.":[65],"Our":[66],"approach":[67],"opens":[68],"possibility":[70],"zero-shot":[72],"transfer":[73],"single":[76],"demonstration":[77],"collected":[78],"nominal":[81],"domain,":[82],"such":[83,124],"as":[84,125],"simulation":[86],"or":[87],"robot":[89],"lab/controlled":[92],"environment,":[93],"domain":[96],"with":[97],"bounded":[98],"model":[99],"errors/perturbations.":[100],"Numerical":[101],"experimental":[103],"evaluations":[104],"performed":[105],"trajectory":[108],"tracking":[109],"for":[111],"multirotor":[113],"show":[114],"our":[116],"outperforms":[118],"strategies":[119],"commonly":[120],"employed":[121],"IL,":[123],"DAgger":[126],"Domain":[128],"Randomization,":[129],"terms":[131],"demonstration-efficiency":[133],"robustness":[135],"perturbations":[137],"unseen":[138],"during":[139],"training.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}