{"id":"https://openalex.org/W4285233190","doi":"https://doi.org/10.1109/lra.2022.3177294","title":"SafeAPT: Safe Simulation-to-Real Robot Learning Using Diverse Policies Learned in Simulation","display_name":"SafeAPT: Safe Simulation-to-Real Robot Learning Using Diverse Policies Learned in Simulation","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285233190","doi":"https://doi.org/10.1109/lra.2022.3177294"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3177294","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3177294","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/7339444/09780237.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/7083369/7339444/09780237.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072492839","display_name":"Rituraj Kaushik","orcid":"https://orcid.org/0000-0003-2598-8804"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Rituraj Kaushik","raw_affiliation_strings":["Intelligent Robotics Group, Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0003-2598-8804","affiliations":[{"raw_affiliation_string":"Intelligent Robotics Group, Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003059336","display_name":"Karol Arndt","orcid":"https://orcid.org/0000-0001-9596-6585"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Karol Arndt","raw_affiliation_strings":["Intelligent Robotics Group, Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-9596-6585","affiliations":[{"raw_affiliation_string":"Intelligent Robotics Group, Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080940147","display_name":"Ville Kyrki","orcid":"https://orcid.org/0000-0002-5230-5549"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Kyrki","raw_affiliation_strings":["Intelligent Robotics Group, Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-5230-5549","affiliations":[{"raw_affiliation_string":"Intelligent Robotics Group, Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":1.31,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83189267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"7","issue":"3","first_page":"6838","last_page":"6845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9819999933242798,"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"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.6849466562271118},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6664564609527588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5817108750343323},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.535552978515625},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5282767415046692},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48438793420791626},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4655829966068268},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.44144418835639954},{"id":"https://openalex.org/keywords/repertoire","display_name":"Repertoire","score":0.435001015663147},{"id":"https://openalex.org/keywords/harm","display_name":"Harm","score":0.41984909772872925},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4180074632167816},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16329634189605713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6849466562271118},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6664564609527588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5817108750343323},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.535552978515625},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5282767415046692},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48438793420791626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4655829966068268},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.44144418835639954},{"id":"https://openalex.org/C2778473898","wikidata":"https://www.wikidata.org/wiki/Q2145110","display_name":"Repertoire","level":2,"score":0.435001015663147},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.41984909772872925},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4180074632167816},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16329634189605713},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lra.2022.3177294","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3177294","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/7339444/09780237.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/120620","is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/120620","pdf_url":"https://aaltodoc.aalto.fi/bitstreams/74a17c3c-a57d-4be3-af05-a8d9ce7848e3/download","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"G5 Artikkeliv\u00e4it\u00f6skirja"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/115881","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/aebd07e0-ed1b-4218-b353-88f462d1bf3e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/lra.2022.3177294","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3177294","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/7339444/09780237.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285233190.pdf","grobid_xml":"https://content.openalex.org/works/W4285233190.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W202805564","https://openalex.org/W758372786","https://openalex.org/W1738827650","https://openalex.org/W2015630562","https://openalex.org/W2091568354","https://openalex.org/W2099201756","https://openalex.org/W2158782408","https://openalex.org/W2192203593","https://openalex.org/W2604883922","https://openalex.org/W2619551236","https://openalex.org/W2726187156","https://openalex.org/W2727901370","https://openalex.org/W2962687375","https://openalex.org/W2962899390","https://openalex.org/W2963525569","https://openalex.org/W2963575966","https://openalex.org/W2995736683","https://openalex.org/W3001500946","https://openalex.org/W3035611392","https://openalex.org/W3090612618","https://openalex.org/W3097464790","https://openalex.org/W3105252106","https://openalex.org/W3112009288","https://openalex.org/W3138863790","https://openalex.org/W3175352502","https://openalex.org/W6608206471","https://openalex.org/W6622219343","https://openalex.org/W6675200109","https://openalex.org/W6677959772","https://openalex.org/W6730100995","https://openalex.org/W6740222838","https://openalex.org/W6753051720","https://openalex.org/W6771329031","https://openalex.org/W6779756738","https://openalex.org/W6784643869","https://openalex.org/W6784754777"],"related_works":["https://openalex.org/W3120300186","https://openalex.org/W2084831119","https://openalex.org/W4255048859","https://openalex.org/W2278124082","https://openalex.org/W2055491483","https://openalex.org/W4378635687","https://openalex.org/W2019758535","https://openalex.org/W2093107729","https://openalex.org/W2026305825","https://openalex.org/W4293754511"],"abstract_inverted_index":{"The":[0],"framework":[1],"of":[2,18,96,171,178,208],"sim-to-real":[3],"learning,":[4],"i.e.,":[5],"training":[6],"policies":[7,97,179,203],"in":[8,26,45,65,99,181,191],"simulation":[9,37,47,100],"and":[10,38,101,123,193,197],"transferring":[11],"them":[12],"to":[13,30,77,108,139,165,167],"real-world":[14,127,209],"systems,":[15],"is":[16],"one":[17],"the":[19,31,36,39,46,56,66,69,103,109,141,145,148,153,158,175,182,216],"most":[20,104],"promising":[21,105],"approaches":[22],"towards":[23],"data-efficient":[24],"learning":[25,89],"robotics.":[27],"However,":[28],"due":[29],"inevitable":[32],"reality":[33],"gap":[34],"between":[35],"real":[40,57,67,110,194],"world,":[41,68],"a":[42,52,60,86,93,163,168,205],"policy":[43,63,107,143],"learned":[44],"may":[48,71],"not":[49],"always":[50],"generate":[51],"safe":[53,106],"behaviour":[54],"on":[55],"robot.":[58],"As":[59],"result,":[61],"during":[62,215],"adaptation":[64],"robot":[70,88,111,164],"damage":[72],"itself":[73],"or":[74],"cause":[75],"harm":[76],"its":[78],"surroundings.":[79],"In":[80],"this":[81],"work,":[82],"we":[83],"introduce":[84],"SafeAPT,":[85],"multi-goal":[87],"algorithm":[90],"that":[91,199],"leverages":[92],"diverse":[94],"repertoire":[95,146,177],"evolved":[98,180],"transfers":[102],"through":[112],"episodic":[113],"interaction.":[114],"To":[115],"achieve":[116],"this,":[117],"SafeAPT":[118,161,186,200],"iteratively":[119],"learns":[120],"probabilistic":[121],"reward":[122,149],"safety":[124,155,159,213],"models":[125],"from":[126,144],"observations":[128],"using":[129,157],"simulated":[130,192],"experiences":[131],"as":[132],"priors.":[133],"Then,":[134],"it":[135],"performs":[136],"Bayesian":[137],"optimization":[138],"select":[140],"best":[142],"with":[147,174,187],"model,":[150],"while":[151,211],"maintaining":[152],"specified":[154],"constraint":[156],"model.":[160],"allows":[162],"adapt":[166],"wide":[169],"range":[170],"goals":[172],"safely":[173],"same":[176],"simulation.":[183],"We":[184],"compare":[185],"several":[188],"baselines,":[189],"both":[190],"robotic":[195],"experiments,":[196],"show":[198],"finds":[201],"high-performing":[202],"within":[204],"few":[206],"minutes":[207],"operation":[210],"minimizing":[212],"violations":[214],"interactions.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
