{"id":"https://openalex.org/W2901099638","doi":"https://doi.org/10.1109/iisr.2018.8535886","title":"Deep Reinforcement Learning Algorithm for Object Placement Tasks with Manipulator","display_name":"Deep Reinforcement Learning Algorithm for Object Placement Tasks with Manipulator","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2901099638","doi":"https://doi.org/10.1109/iisr.2018.8535886","mag":"2901099638"},"language":"en","primary_location":{"id":"doi:10.1109/iisr.2018.8535886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iisr.2018.8535886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Intelligence and Safety for Robotics (ISR)","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/A5100648538","display_name":"Wei Guo","orcid":"https://orcid.org/0000-0001-8616-0221"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Guo","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101940143","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-0343-3982"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007636779","display_name":"Yu Fu","orcid":"https://orcid.org/0000-0003-4972-0626"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Fu","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008850130","display_name":"Fusheng Zha","orcid":"https://orcid.org/0000-0001-9695-1940"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fusheng Zha","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7493,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7365407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"608","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9994000196456909,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.8611577749252319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8077771663665771},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7012007832527161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6645783185958862},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5964689254760742},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47774213552474976},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4670286178588867},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4607352614402771},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.44910547137260437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4276397228240967},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.422539085149765},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41160160303115845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3901708126068115},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.18416595458984375}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8611577749252319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077771663665771},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7012007832527161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6645783185958862},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5964689254760742},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47774213552474976},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4670286178588867},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4607352614402771},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.44910547137260437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4276397228240967},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.422539085149765},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41160160303115845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3901708126068115},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.18416595458984375},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iisr.2018.8535886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iisr.2018.8535886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Intelligence and Safety for Robotics (ISR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1977655452","https://openalex.org/W1992989752","https://openalex.org/W2033819227","https://openalex.org/W2034052310","https://openalex.org/W2087617385","https://openalex.org/W2126909264","https://openalex.org/W2140135625","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2528734395","https://openalex.org/W2739274579","https://openalex.org/W2745990901","https://openalex.org/W2963403593","https://openalex.org/W2963689319","https://openalex.org/W2964161785","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6680657880","https://openalex.org/W6682849425"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2930863966","https://openalex.org/W3127551068"],"abstract_inverted_index":{"To":[0],"settle":[1],"the":[2,5,11,41,50,65,76,85,89,96,102],"problem":[3],"that":[4],"household":[6],"robot":[7,38,66],"needs":[8],"to":[9,63,68],"have":[10],"flexibility":[12,100],"of":[13,92,101],"object":[14,21,46],"types":[15,47],"and":[16,54,88,99],"target":[17,70],"poses":[18],"when":[19],"performing":[20,73],"placement":[22,42,77],"tasks,":[23,75],"a":[24,55],"deep":[25,103],"reinforcement":[26,104],"learning":[27,97,105],"algorithm":[28,37,106],"is":[29,61,107],"utilized":[30],"in":[31],"this":[32,36],"paper.":[33],"By":[34],"using":[35],"can":[39,79],"learn":[40],"method":[43,87],"for":[44],"different":[45,69],"autonomously":[48],"under":[49],"policy":[51,60],"search":[52],"part,":[53],"convolutional":[56],"neural":[57],"network":[58],"(CNN)":[59],"trained":[62],"make":[64],"adapt":[67],"poses.":[71],"When":[72],"these":[74],"error":[78],"also":[80],"be":[81],"reduced":[82],"by":[83,109],"modifying":[84],"sampling":[86],"weight":[90],"form":[91],"cost":[93],"function.":[94],"Finally,":[95],"ability":[98],"tested":[108],"simulation.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}