{"id":"https://openalex.org/W3001693108","doi":"https://doi.org/10.1109/robio49542.2019.8961517","title":"Robot Control in Human Environment using Deep Reinforcement Learning and Convolutional Neural Network","display_name":"Robot Control in Human Environment using Deep Reinforcement Learning and Convolutional Neural Network","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3001693108","doi":"https://doi.org/10.1109/robio49542.2019.8961517","mag":"3001693108"},"language":"en","primary_location":{"id":"doi:10.1109/robio49542.2019.8961517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5100418540","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1131-4913"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075221193","display_name":"Hsieh-Yu Li","orcid":"https://orcid.org/0000-0003-2651-917X"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hsieh-Yu Li","raw_affiliation_strings":["Singapore University of Technology of Design,Pillar of Engineering Product Development,Singapore","Pillar of Engineering Product Development, Singapore University of Technology of Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology of Design,Pillar of Engineering Product Development,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Pillar of Engineering Product Development, Singapore University of Technology of Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078874206","display_name":"Audelia G. Dharmawan","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Audelia G. Dharmawan","raw_affiliation_strings":["Singapore University of Technology of Design,Pillar of Engineering Product Development,Singapore","Pillar of Engineering Product Development, Singapore University of Technology of Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology of Design,Pillar of Engineering Product Development,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Pillar of Engineering Product Development, Singapore University of Technology of Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001434671","display_name":"Khairuldanial Ismail","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Khairuldanial Ismail","raw_affiliation_strings":["Singapore University of Technology of Design,Pillar of Engineering Product Development,Singapore","Pillar of Engineering Product Development, Singapore University of Technology of Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology of Design,Pillar of Engineering Product Development,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Pillar of Engineering Product Development, Singapore University of Technology of Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408608","display_name":"Xiang Liu","orcid":"https://orcid.org/0000-0002-4822-2396"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023142347","display_name":"U-Xuan Tan","orcid":"https://orcid.org/0000-0002-5757-1379"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"U-Xuan Tan","raw_affiliation_strings":["Singapore University of Technology of Design,Pillar of Engineering Product Development,Singapore","Pillar of Engineering Product Development, Singapore University of Technology of Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology of Design,Pillar of Engineering Product Development,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Pillar of Engineering Product Development, Singapore University of Technology of Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100418540"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67592896,"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":"1121","last_page":"1126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9918000102043152,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9894999861717224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8098917007446289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7610023617744446},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6904488205909729},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6774498224258423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6751692295074463},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5192549228668213},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47617143392562866},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45007258653640747},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4394485056400299},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4156368672847748},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32970255613327026}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8098917007446289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610023617744446},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6904488205909729},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6774498224258423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6751692295074463},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5192549228668213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47617143392562866},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45007258653640747},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4394485056400299},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4156368672847748},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32970255613327026},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio49542.2019.8961517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1587009522","https://openalex.org/W2042882799","https://openalex.org/W2094801294","https://openalex.org/W2100235553","https://openalex.org/W2121615981","https://openalex.org/W2139053308","https://openalex.org/W2168945912","https://openalex.org/W2194966727","https://openalex.org/W2257979135","https://openalex.org/W2522340145","https://openalex.org/W2605102758","https://openalex.org/W2766614170","https://openalex.org/W2767050701","https://openalex.org/W2788781499","https://openalex.org/W2792855406","https://openalex.org/W2952629144","https://openalex.org/W2962887844","https://openalex.org/W2963276406","https://openalex.org/W2964198579","https://openalex.org/W3101442004","https://openalex.org/W4293864724","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6637967152","https://openalex.org/W6678317597","https://openalex.org/W6728925229","https://openalex.org/W6736179038","https://openalex.org/W6737327832","https://openalex.org/W6740801417","https://openalex.org/W6748523217"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Deep":[0,136],"reinforcement":[1],"learning":[2],"(DRL)":[3],"has":[4],"been":[5],"employed":[6,143],"in":[7,17,109,121,165,176,188,203],"numerous":[8],"applications":[9],"where":[10],"complex":[11,215],"decision-making":[12],"is":[13,21,49,91,103,142,158,186],"needed.":[14],"Robot":[15],"control":[16],"a":[18,40,88,114,135,151,183],"human":[19,45,89,190],"environment":[20,90],"an":[22],"example.":[23],"Such":[24],"algorithm":[25,140,156],"offers":[26],"possibilities":[27],"to":[28,65,72,85,117,126,128,144,160],"achieve":[29,118],"end-to-end":[30,119],"training":[31,38,61,120,175],"which":[32],"learns":[33],"from":[34,83],"image":[35],"directly.":[36],"However,":[37],"on":[39],"physical":[41,66],"robotic":[42],"system":[43],"under":[44,213],"environments":[46],"using":[47],"DRL":[48,74,115,174],"inefficient":[50],"and":[51,95,172,193,199],"even":[52],"dangerous.":[53],"Several":[54],"recent":[55],"works":[56],"have":[57,209],"used":[58,159],"simulators":[59],"for":[60,80,106,147,197],"models":[62],"before":[63],"implementing":[64],"robots.":[67],"Although":[68],"simulation":[69,84,101,177],"provides":[70,169],"efficiency":[71],"obtain":[73],"trained":[75,99],"models,":[76],"it":[77],"poses":[78],"challenges":[79],"the":[81,97,163,170,204],"transformation":[82],"reality.":[86,107],"Since":[87],"often":[92],"cluttered,":[93],"dynamic":[94,189],"complex,":[96],"policy":[98,146],"with":[100],"images":[102],"not":[104],"applicable":[105],"Therefore,":[108],"this":[110],"paper,":[111],"we":[112],"propose":[113],"method":[116],"simulation,":[122],"as":[123,125],"well":[124],"adapt":[127],"reality":[129],"without":[130],"any":[131],"further":[132],"finetune.":[133],"Firstly,":[134],"Deterministic":[137],"Policy":[138],"Gradient":[139],"(DDPG)":[141],"learn":[145],"robot":[148,185],"control.":[149],"Secondly,":[150],"pre-trained":[152],"Convolutional":[153],"Neural":[154],"Network":[155],"(CNN)":[157],"visually":[161],"track":[162],"target":[164],"image.":[166],"This":[167],"technique":[168],"efficient":[171],"safe":[173],"while":[178],"offering":[179],"robust":[180],"application":[181],"when":[182],"real":[184],"placed":[187],"environment.":[191],"Simulation":[192],"experiment":[194],"are":[195],"conducted":[196],"validation":[198],"can":[200],"be":[201],"seen":[202],"attached":[205],"video.":[206],"The":[207],"results":[208],"shown":[210],"successful":[211],"demonstration":[212],"various":[214],"environments.":[216]},"counts_by_year":[{"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"}