{"id":"https://openalex.org/W2020455387","doi":"https://doi.org/10.1109/iros.2013.6696349","title":"Ensuring safety of policies learned by reinforcement: Reaching objects in the presence of obstacles with the iCub","display_name":"Ensuring safety of policies learned by reinforcement: Reaching objects in the presence of obstacles with the iCub","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2020455387","doi":"https://doi.org/10.1109/iros.2013.6696349","mag":"2020455387"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2013.6696349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5075926868","display_name":"Shashank Pathak","orcid":"https://orcid.org/0000-0002-2888-6750"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Shashank Pathak","raw_affiliation_strings":["Robotics, Brain and Cognitive Sciences (RBCS), Istituto Italiano di Tecnologia (IIT), Genova, Italy","Robot., Brain & Cognitive Sci. (RBCS), Ist. Italiano di Tecnol. (IIT), Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics, Brain and Cognitive Sciences (RBCS), Istituto Italiano di Tecnologia (IIT), Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Robot., Brain & Cognitive Sci. (RBCS), Ist. Italiano di Tecnol. (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004587018","display_name":"Luca Pulina","orcid":"https://orcid.org/0000-0003-0258-3222"},"institutions":[{"id":"https://openalex.org/I159650629","display_name":"University of Sassari","ror":"https://ror.org/01bnjbv91","country_code":"IT","type":"education","lineage":["https://openalex.org/I159650629"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Pulina","raw_affiliation_strings":["POLCOMING, Universita degli Studi di Sassari, Sassari, Italy","POLCOMING, Univ. degli Studi di Sassari, Sassari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POLCOMING, Universita degli Studi di Sassari, Sassari, Italy","institution_ids":["https://openalex.org/I159650629"]},{"raw_affiliation_string":"POLCOMING, Univ. degli Studi di Sassari, Sassari, Italy","institution_ids":["https://openalex.org/I159650629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090032106","display_name":"Giorgio Metta","orcid":"https://orcid.org/0000-0003-0459-4769"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giorgio Metta","raw_affiliation_strings":["Robotics, Brain and Cognitive Sciences (RBCS), Istituto Italiano di Tecnologia (IIT), Genova, Italy","Robot., Brain & Cognitive Sci. (RBCS), Ist. Italiano di Tecnol. (IIT), Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics, Brain and Cognitive Sciences (RBCS), Istituto Italiano di Tecnologia (IIT), Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Robot., Brain & Cognitive Sci. (RBCS), Ist. Italiano di Tecnol. (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067087113","display_name":"Armando Tacchella","orcid":"https://orcid.org/0000-0001-9487-331X"},"institutions":[{"id":"https://openalex.org/I4210139705","display_name":"Ingegneria dei Sistemi (Italy)","ror":"https://ror.org/03spsm219","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210139705"]},{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Armando Tacchella","raw_affiliation_strings":["Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS), Universita degli Studi di Genova, Genova, Italy","Dipt. di Inf., Bioingegneria, Robot. e Ing. dei Sist. (DIBRIS), Univ. degli Studi di Genova, Genova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS), Universita degli Studi di Genova, Genova, Italy","institution_ids":["https://openalex.org/I4210139705","https://openalex.org/I83816512"]},{"raw_affiliation_string":"Dipt. di Inf., Bioingegneria, Robot. e Ing. dei Sist. (DIBRIS), Univ. degli Studi di Genova, Genova, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.517,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90713264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"170","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9879999756813049,"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":0.9879999756813049,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9779000282287598,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/icub","display_name":"iCub","score":0.9868953227996826},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6225413084030151},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.567359447479248},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4581446349620819},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.430942565202713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24078696966171265},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22643333673477173},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.1855459213256836},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.17466583847999573},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.12166351079940796}],"concepts":[{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.9868953227996826},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6225413084030151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.567359447479248},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4581446349620819},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.430942565202713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24078696966171265},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22643333673477173},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.1855459213256836},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.17466583847999573},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.12166351079940796}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2013.6696349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unige.it:11567/785811","is_oa":false,"landing_page_url":"http://hdl.handle.net/11567/785811","pdf_url":null,"source":{"id":"https://openalex.org/S4377196291","display_name":"CINECA IRIS Institutial Research Information System (University of Genoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83816512","host_organization_name":"University of Genoa","host_organization_lineage":["https://openalex.org/I83816512"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W309749295","https://openalex.org/W1513873158","https://openalex.org/W1516256348","https://openalex.org/W1585575029","https://openalex.org/W1593428110","https://openalex.org/W1963790880","https://openalex.org/W1982948368","https://openalex.org/W1999354872","https://openalex.org/W2001737341","https://openalex.org/W2050963907","https://openalex.org/W2101075098","https://openalex.org/W2117189826","https://openalex.org/W2121863487","https://openalex.org/W2154284891","https://openalex.org/W2161222115","https://openalex.org/W2164479831","https://openalex.org/W2407524210","https://openalex.org/W3106238320","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4230735704","https://openalex.org/W6713785089"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2130280438","https://openalex.org/W2079582948","https://openalex.org/W4235148364","https://openalex.org/W1999531358","https://openalex.org/W2122050160","https://openalex.org/W4237651640","https://openalex.org/W2499388093","https://openalex.org/W2110525007","https://openalex.org/W2135835174"],"abstract_inverted_index":{"Given":[0],"a":[1,17,42,52,63],"stochastic":[2],"policy":[3,64],"learned":[4],"by":[5],"reinforcement,":[6],"we":[7,67],"wish":[8],"to":[9,32,38,54,75],"ensure":[10],"that":[11],"it":[12,69,90],"can":[13,91],"be":[14,92],"deployed":[15],"on":[16],"robot":[18],"with":[19,70,95],"demonstrably":[20],"low":[21,44],"probability":[22,115],"of":[23,104,116],"unsafe":[24,80,117],"behavior.":[25],"Our":[26],"case":[27],"study":[28],"is":[29,48,65,85,106],"about":[30],"learning":[31],"reach":[33],"target":[34],"objects":[35],"positioned":[36],"close":[37],"obstacles,":[39],"and":[40,77,109],"ensuring":[41],"reasonably":[43],"collision":[45],"probability.":[46],"Learning":[47],"carried":[49],"out":[50],"in":[51,58,88,112],"simulator":[53],"avoid":[55],"physical":[56],"damage":[57],"the":[59,114],"trial-and-error":[60],"phase.":[61],"Once":[62],"learned,":[66],"analyze":[68],"probabilistic":[71],"model":[72],"checking":[73],"tools":[74],"identify":[76],"correct":[78],"potential":[79],"behaviors.":[81,118],"The":[82],"whole":[83],"process":[84],"automated":[86,102],"and,":[87],"principle,":[89],"integrated":[93],"step-by-step":[94],"routine":[96],"task-learning.":[97],"As":[98],"our":[99],"results":[100],"demonstrate,":[101],"fixing":[103],"policies":[105],"both":[107],"feasible":[108],"highly":[110],"effective":[111],"bounding":[113]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
