{"id":"https://openalex.org/W3136025385","doi":"https://doi.org/10.1109/lra.2021.3065271","title":"Uncertainty-Aware Contact-Safe Model-Based Reinforcement Learning","display_name":"Uncertainty-Aware Contact-Safe Model-Based Reinforcement Learning","publication_year":2021,"publication_date":"2021-03-11","ids":{"openalex":"https://openalex.org/W3136025385","doi":"https://doi.org/10.1109/lra.2021.3065271","mag":"3136025385"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3065271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3065271","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/A5070668609","display_name":"Cheng-Yu Kuo","orcid":"https://orcid.org/0000-0002-3085-0343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-Yu Kuo","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3085-0343","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091016962","display_name":"Andreas Schaarschmidt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Schaarschmidt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5539-4260","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012730104","display_name":"Tamim Asfour","orcid":"https://orcid.org/0000-0003-4879-7680"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tamim Asfour","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4879-7680","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3545-4814","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9108,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87855765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"6","issue":"2","first_page":"3918","last_page":"3925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9954000115394592,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9952999949455261,"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":0.6620103716850281},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5646086931228638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5211241841316223},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3523867726325989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3283258378505707},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2830730676651001},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13311466574668884}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6620103716850281},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5646086931228638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5211241841316223},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3523867726325989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3283258378505707},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2830730676651001},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13311466574668884}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3065271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3065271","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W158164316","https://openalex.org/W164706946","https://openalex.org/W1520597402","https://openalex.org/W1595498733","https://openalex.org/W1657213141","https://openalex.org/W1663973292","https://openalex.org/W1978956894","https://openalex.org/W2009086942","https://openalex.org/W2012587148","https://openalex.org/W2100235553","https://openalex.org/W2118563516","https://openalex.org/W2126909264","https://openalex.org/W2140135625","https://openalex.org/W2167503371","https://openalex.org/W2172158418","https://openalex.org/W2321599906","https://openalex.org/W2334591577","https://openalex.org/W2418467170","https://openalex.org/W2480459371","https://openalex.org/W2700407638","https://openalex.org/W2781726626","https://openalex.org/W2922052901","https://openalex.org/W2963809569","https://openalex.org/W2982518621","https://openalex.org/W3003629310","https://openalex.org/W3026843233","https://openalex.org/W3028308378","https://openalex.org/W3029509103","https://openalex.org/W3039727005","https://openalex.org/W3047214858","https://openalex.org/W3088002337","https://openalex.org/W3088662645","https://openalex.org/W3091094690","https://openalex.org/W3091552533","https://openalex.org/W3094511556","https://openalex.org/W3100172161","https://openalex.org/W3115511323","https://openalex.org/W3129364384","https://openalex.org/W4205513846","https://openalex.org/W6677614981","https://openalex.org/W6680657880","https://openalex.org/W6740033195","https://openalex.org/W6747473740","https://openalex.org/W6765121789","https://openalex.org/W6770097079","https://openalex.org/W6783495412","https://openalex.org/W6784521679"],"related_works":["https://openalex.org/W4206669594","https://openalex.org/W3037422413","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W2909304650","https://openalex.org/W3111983280","https://openalex.org/W3164468573","https://openalex.org/W2185410470"],"abstract_inverted_index":{"This":[0],"letter":[1],"presents":[2],"contact-safe":[3,13,79],"Model-based":[4],"Reinforcement":[5],"Learning":[6],"(MBRL)":[7],"for":[8],"robot":[9,60,153],"applications":[10],"that":[11,81,96],"achieves":[12],"behaviors":[14],"in":[15,51],"the":[16,25,35,40,59,66,78,83,92,97],"learning":[17,41,107],"process.":[18],"In":[19],"typical":[20],"MBRL,":[21],"we":[22,76],"cannot":[23],"expect":[24],"data-driven":[26],"model":[27,93],"to":[28,34,44,58,106],"generate":[29],"accurate":[30],"and":[31,61,129,145],"reliable":[32],"policies":[33,50],"intended":[36],"robotic":[37],"tasks":[38,142,149],"during":[39],"process":[42],"due":[43],"sample":[45],"scarcity.":[46],"Operating":[47],"these":[48],"unreliable":[49],"a":[52,119,124,151],"contact-rich":[53,157],"environment":[54],"could":[55],"cause":[56],"damage":[57,70],"its":[62],"surroundings.":[63],"To":[64],"alleviate":[65],"risk":[67],"of":[68,100,156],"causing":[69],"through":[71,139],"unexpected":[72],"intensive":[73],"physical":[74],"contacts,":[75],"present":[77],"MBRL":[80],"associates":[82],"probabilistic":[84],"Model":[85],"Predictive":[86],"Control's":[87],"(pMPC)":[88],"control":[89,114],"limits":[90,115],"with":[91,111,143,150],"uncertainty":[94],"so":[95],"allowed":[98],"acceleration":[99],"controlled":[101],"behavior":[102],"is":[103,116,137],"adjusted":[104],"according":[105],"progress.":[108],"Control":[109],"planning":[110],"such":[112],"uncertainty-aware":[113],"formulated":[117],"as":[118,154],"deterministic":[120],"MPC":[121],"problem":[122],"using":[123],"computation-efficient":[125],"approximated":[126,131],"GP":[127],"dynamics":[128],"an":[130],"inference":[132],"technique.":[133],"Our":[134],"approach's":[135],"effectiveness":[136],"evaluated":[138],"bowl":[140],"mixing":[141],"simulated":[144],"real":[146,152],"robots,":[147],"scooping":[148],"examples":[155],"manipulation":[158],"skills.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}