{"id":"https://openalex.org/W4388623195","doi":"https://doi.org/10.1109/ro-man57019.2023.10309604","title":"Probabilistic Policy Blending for Shared Autonomy using Deep Reinforcement Learning","display_name":"Probabilistic Policy Blending for Shared Autonomy using Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388623195","doi":"https://doi.org/10.1109/ro-man57019.2023.10309604"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5101461656","display_name":"Saurav Singh","orcid":"https://orcid.org/0000-0002-3250-425X"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saurav Singh","raw_affiliation_strings":["Rochester Institute of Technology,Rochester,NY,USA,14623"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology,Rochester,NY,USA,14623","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075542202","display_name":"Jamison Heard","orcid":"https://orcid.org/0000-0001-6860-0844"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamison Heard","raw_affiliation_strings":["Rochester Institute of Technology,Rochester,NY,USA,14623"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology,Rochester,NY,USA,14623","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101461656"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":0.23,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51928325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1537","last_page":"1544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.991599977016449,"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"}},"topics":[{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.991599977016449,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9789000153541565,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8228087425231934},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7647902369499207},{"id":"https://openalex.org/keywords/autonomy","display_name":"Autonomy","score":0.7165364027023315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6774296164512634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48833414912223816},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4332354962825775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3312745690345764},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32124143838882446},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16248437762260437},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11790350079536438},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.0752987265586853}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8228087425231934},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7647902369499207},{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.7165364027023315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6774296164512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48833414912223816},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4332354962825775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3312745690345764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32124143838882446},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16248437762260437},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11790350079536438},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0752987265586853},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1538807643","https://openalex.org/W1983885373","https://openalex.org/W2002966689","https://openalex.org/W2011475678","https://openalex.org/W2019526129","https://openalex.org/W2056797914","https://openalex.org/W2058543238","https://openalex.org/W2067474383","https://openalex.org/W2095714487","https://openalex.org/W2105925198","https://openalex.org/W2145339207","https://openalex.org/W2157289187","https://openalex.org/W2552912227","https://openalex.org/W2568343704","https://openalex.org/W2571352963","https://openalex.org/W2615097439","https://openalex.org/W2927819804","https://openalex.org/W2962776080","https://openalex.org/W2963507484","https://openalex.org/W2964022460","https://openalex.org/W3093766141","https://openalex.org/W3100107676","https://openalex.org/W3163332843","https://openalex.org/W3194407971","https://openalex.org/W4232476872","https://openalex.org/W4234505475","https://openalex.org/W4298857966","https://openalex.org/W6602271460","https://openalex.org/W6637967152"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Technologies":[0],"in":[1,12,23],"machine":[2],"learning":[3],"and":[4,15,25,43,58,85,130,145],"artificial":[5],"intelligence":[6],"have":[7,120],"come":[8],"a":[9,31,40,56,93],"long":[10],"way":[11],"decision":[13],"making":[14],"system":[16,57,129],"automation,":[17],"but":[18],"still":[19],"faces":[20],"difficult":[21],"challenges":[22],"semi-automation":[24],"human-in-the-loop":[26],"frameworks.":[27],"This":[28],"work":[29],"presents":[30],"probabilistic":[32],"policy":[33],"blending":[34],"approach":[35,49,90],"for":[36],"shared":[37],"control":[38,55],"between":[39,74,139],"human":[41,60,84,100,117,125],"operator":[42,61,101],"an":[44],"intelligent":[45],"agent.":[46],"The":[47,88],"proposed":[48,89],"assumes":[50],"that":[51,78],"the":[52,59,65,83,99,108,124,128,131,140],"agent":[53,132],"can":[54,91],"needs":[62],"to":[63,81,98],"communicate":[64],"system\u2019s":[66],"intended":[67],"goal.":[68],"A":[69,137],"comparative":[70],"study":[71],"is":[72],"presented":[73],"different":[75,134],"arbitration":[76,135,143],"functions":[77],"are":[79],"used":[80],"blend":[82],"agent\u2019s":[86],"actions.":[87],"achieve":[92],"variable":[94],"level":[95],"of":[96],"assistance":[97],"successfully":[102],"within":[103],"discrete":[104],"action":[105],"space":[106],"using":[107,133],"Lunar":[109],"Lander":[110],"game":[111],"environment":[112],"developed":[113],"by":[114],"OpenAI.":[115],"Furthermore,":[116],"physiological":[118,141],"data":[119],"been":[121],"analyzed":[122],"while":[123],"interacts":[126],"with":[127],"functions.":[136],"correlation":[138],"data,":[142],"level,":[144],"task":[146],"performance":[147],"was":[148],"observed.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}