{"id":"https://openalex.org/W2894708207","doi":"https://doi.org/10.1109/humanoids.2018.8624948","title":"Safe- to-Explore State Spaces: Ensuring Safe Exploration in Policy Search with Hierarchical Task Optimization","display_name":"Safe- to-Explore State Spaces: Ensuring Safe Exploration in Policy Search with Hierarchical Task Optimization","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2894708207","doi":"https://doi.org/10.1109/humanoids.2018.8624948","mag":"2894708207"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2018.8624948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2018.8624948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-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/A5064860545","display_name":"Jens Lundell","orcid":"https://orcid.org/0000-0003-2296-6685"},"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":true,"raw_author_name":"Jens Lundell","raw_affiliation_strings":["Department of Electrical Engineering and Automation, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Automation, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035020090","display_name":"Robert Krug","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Robert Krug","raw_affiliation_strings":["Robotics, KTH Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"Robotics, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024984249","display_name":"Erik Schaffernicht","orcid":"https://orcid.org/0000-0002-0804-8637"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Erik Schaffernicht","raw_affiliation_strings":["AASS Research Center, \u00d6rebro University, Sweden"],"affiliations":[{"raw_affiliation_string":"AASS Research Center, \u00d6rebro University, Sweden","institution_ids":["https://openalex.org/I26437253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044352907","display_name":"Todor Stoyanov","orcid":"https://orcid.org/0000-0002-6013-4874"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Todor Stoyanov","raw_affiliation_strings":["AASS Research Center, \u00d6rebro University, Sweden"],"affiliations":[{"raw_affiliation_string":"AASS Research Center, \u00d6rebro University, Sweden","institution_ids":["https://openalex.org/I26437253"]}]},{"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":["Department of Electrical Engineering and Automation, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Automation, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064860545"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.3679,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60972333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7857454419136047},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.7023570537567139},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6715620756149292},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.6570262908935547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6122897267341614},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.601539134979248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5357102155685425},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5341286659240723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4856361448764801},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46310991048812866},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.43311187624931335},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4276282787322998},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3970816731452942},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.3022933602333069},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1993257999420166},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.172098308801651},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12695544958114624},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09687662124633789}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7857454419136047},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.7023570537567139},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6715620756149292},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.6570262908935547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6122897267341614},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.601539134979248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357102155685425},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5341286659240723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4856361448764801},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46310991048812866},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.43311187624931335},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4276282787322998},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3970816731452942},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3022933602333069},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1993257999420166},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.172098308801651},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12695544958114624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09687662124633789},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids.2018.8624948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2018.8624948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W130216483","https://openalex.org/W1480376833","https://openalex.org/W1499669280","https://openalex.org/W1520597402","https://openalex.org/W1771410628","https://openalex.org/W1840625103","https://openalex.org/W1964941300","https://openalex.org/W1980602022","https://openalex.org/W2012392077","https://openalex.org/W2019606703","https://openalex.org/W2100235553","https://openalex.org/W2103120971","https://openalex.org/W2109169869","https://openalex.org/W2110304639","https://openalex.org/W2121138345","https://openalex.org/W2124605596","https://openalex.org/W2125612430","https://openalex.org/W2154847670","https://openalex.org/W2159459871","https://openalex.org/W2167117957","https://openalex.org/W2168921921","https://openalex.org/W2294174507","https://openalex.org/W2531377421","https://openalex.org/W2558381884","https://openalex.org/W2737943148","https://openalex.org/W2963293747","https://openalex.org/W3104013016","https://openalex.org/W4297799385","https://openalex.org/W6629881138","https://openalex.org/W6638018090","https://openalex.org/W6653435097","https://openalex.org/W6683149736"],"related_works":["https://openalex.org/W4317634134","https://openalex.org/W2889566344","https://openalex.org/W2981729160","https://openalex.org/W4388311650","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Policy":[0],"search":[1],"reinforcement":[2],"learning":[3,13,119,139],"allows":[4],"robots":[5],"to":[6,25,39,44,63,122],"acquire":[7],"skills":[8,75,150,156],"by":[9,59,72,117],"themselves.":[10],"However,":[11],"the":[12,19,27,30,42,46,49,56,61,127,143,163,166],"procedure":[14],"is":[15,115],"inherently":[16],"unsafe":[17],"as":[18,98],"robot":[20,47,161],"has":[21],"no":[22],"a-priori":[23],"way":[24],"predict":[26],"consequences":[28],"of":[29,131,142,165],"exploratory":[31],"actions":[32],"it":[33],"takes.":[34],"Therefore,":[35],"exploration":[36,62],"can":[37],"lead":[38],"collisions":[40],"with":[41,107],"potential":[43],"harm":[45],"and/or":[48],"environment.":[50],"In":[51],"this":[52],"work":[53],"we":[54],"address":[55],"safety":[57],"aspect":[58],"constraining":[60],"happen":[64],"in":[65,102,126,140,152],"safe-to-explore":[66],"state":[67],"spaces.":[68],"These":[69],"are":[70,96],"formed":[71],"decomposing":[73],"target":[74],"(e.g.,":[76,82,93],"grasping)":[77],"into":[78],"higher":[79,132],"ranked":[80,90,124,133],"sub-tasks":[81,125],"collision":[83],"avoidance,":[84],"joint":[85],"limit":[86],"avoidance)":[87],"and":[88,154],"lower":[89,123],"movement":[91],"tasks":[92],"reaching).":[94],"Sub-tasks":[95],"defined":[97],"concurrent":[99],"controllers":[100],"(policies)":[101],"different":[103],"operational":[104],"spaces":[105],"together":[106],"associated":[108],"Jacobians":[109],"representing":[110],"their":[111],"joint-space":[112],"mapping.":[113],"Safety":[114],"ensured":[116],"only":[118],"policies":[120],"corresponding":[121],"redundant":[128],"null":[129],"space":[130],"ones.":[134],"As":[135],"a":[136,159],"side":[137],"benefit,":[138],"sub-manifolds":[141],"state-space":[144],"also":[145],"facilitates":[146],"sample":[147],"efficiency.":[148],"Reaching":[149],"performed":[151,157],"simulation":[153],"grasping":[155],"on":[158],"real":[160],"validate":[162],"usefulness":[164],"proposed":[167],"approach.":[168]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}