{"id":"https://openalex.org/W3199096322","doi":"https://doi.org/10.3390/robotics10030105","title":"Reinforcement Learning for Pick and Place Operations in Robotics: A Survey","display_name":"Reinforcement Learning for Pick and Place Operations in Robotics: A Survey","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3199096322","doi":"https://doi.org/10.3390/robotics10030105","mag":"3199096322"},"language":"en","primary_location":{"id":"doi:10.3390/robotics10030105","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics10030105","pdf_url":"https://www.mdpi.com/2218-6581/10/3/105/pdf?version=1631546868","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2218-6581/10/3/105/pdf?version=1631546868","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078163619","display_name":"Andrew Lobbezoo","orcid":"https://orcid.org/0000-0001-5159-277X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Andrew Lobbezoo","raw_affiliation_strings":["AI for Manufacturing Laboratory, Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5159-277X","affiliations":[{"raw_affiliation_string":"AI for Manufacturing Laboratory, Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000535038","display_name":"Yanjun Qian","orcid":"https://orcid.org/0000-0002-1581-0431"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yanjun Qian","raw_affiliation_strings":["AI for Manufacturing Laboratory, Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI for Manufacturing Laboratory, Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024242719","display_name":"Hyock\u2010Ju Kwon","orcid":"https://orcid.org/0000-0003-1354-0391"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hyock-Ju Kwon","raw_affiliation_strings":["AI for Manufacturing Laboratory, Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1354-0391","affiliations":[{"raw_affiliation_string":"AI for Manufacturing Laboratory, Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078163619"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":5.2729,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96092316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"10","issue":"3","first_page":"105","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9986000061035156,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.8549395799636841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.72147536277771},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6973644495010376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6093196272850037},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.5841053128242493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.576313316822052},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5692805051803589},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5196460485458374},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5079236626625061},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4506802260875702},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.4437218904495239},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4321235418319702},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4013468027114868},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3550386428833008},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22981008887290955},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.12728706002235413},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11520779132843018},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1090269684791565},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.09224194288253784}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8549395799636841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.72147536277771},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6973644495010376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6093196272850037},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.5841053128242493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.576313316822052},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5692805051803589},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5196460485458374},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5079236626625061},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4506802260875702},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.4437218904495239},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4321235418319702},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4013468027114868},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3550386428833008},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22981008887290955},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.12728706002235413},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11520779132843018},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1090269684791565},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.09224194288253784},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/robotics10030105","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics10030105","pdf_url":"https://www.mdpi.com/2218-6581/10/3/105/pdf?version=1631546868","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b60473660e284c11a7255d17ebff6cc4","is_oa":true,"landing_page_url":"https://doaj.org/article/b60473660e284c11a7255d17ebff6cc4","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics, Vol 10, Iss 3, p 105 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2218-6581/10/3/105/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/robotics10030105","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics; Volume 10; Issue 3; Pages: 105","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/robotics10030105","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics10030105","pdf_url":"https://www.mdpi.com/2218-6581/10/3/105/pdf?version=1631546868","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3199096322.pdf","grobid_xml":"https://content.openalex.org/works/W3199096322.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W947069083","https://openalex.org/W1536323281","https://openalex.org/W1560270123","https://openalex.org/W1570792896","https://openalex.org/W1578592924","https://openalex.org/W1777239053","https://openalex.org/W1977655452","https://openalex.org/W1999874108","https://openalex.org/W2005824379","https://openalex.org/W2012587148","https://openalex.org/W2018855542","https://openalex.org/W2036637075","https://openalex.org/W2079247031","https://openalex.org/W2086113803","https://openalex.org/W2107726111","https://openalex.org/W2109163007","https://openalex.org/W2117629901","https://openalex.org/W2123435073","https://openalex.org/W2159880874","https://openalex.org/W2198041288","https://openalex.org/W2260756217","https://openalex.org/W2290104316","https://openalex.org/W2585959050","https://openalex.org/W2605102758","https://openalex.org/W2773721443","https://openalex.org/W2808278571","https://openalex.org/W2894931878","https://openalex.org/W2901563868","https://openalex.org/W2914159285","https://openalex.org/W2935588605","https://openalex.org/W2943634310","https://openalex.org/W2962746398","https://openalex.org/W2963033241","https://openalex.org/W2963166883","https://openalex.org/W2963277051","https://openalex.org/W2963280855","https://openalex.org/W2963654160","https://openalex.org/W2967349569","https://openalex.org/W2978612180","https://openalex.org/W2995986219","https://openalex.org/W3003266338","https://openalex.org/W3004003541","https://openalex.org/W3004091482","https://openalex.org/W3013419527","https://openalex.org/W3034321388","https://openalex.org/W3086270667","https://openalex.org/W3088158297","https://openalex.org/W3090299930","https://openalex.org/W3091277626","https://openalex.org/W3092253994","https://openalex.org/W3101780148","https://openalex.org/W3107710873","https://openalex.org/W3112422759","https://openalex.org/W3118516347","https://openalex.org/W3126384422","https://openalex.org/W3127556163","https://openalex.org/W3137655987","https://openalex.org/W3138680551","https://openalex.org/W3200879008","https://openalex.org/W3202764408","https://openalex.org/W3205206576","https://openalex.org/W4200292174","https://openalex.org/W6629910019","https://openalex.org/W6653548176","https://openalex.org/W6675999342","https://openalex.org/W6684205842","https://openalex.org/W6718092244","https://openalex.org/W6732350924","https://openalex.org/W6790013788","https://openalex.org/W6801742604"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2163296013"],"abstract_inverted_index":{"The":[0,133,157],"field":[1,130,154],"of":[2,27,34,66,72,108,122,137,149,161,168],"robotics":[3,55],"has":[4,22],"been":[5,23],"rapidly":[6],"developing":[7],"in":[8,128],"recent":[9],"years,":[10],"and":[11,69,79,100,111,135,144,165,177],"the":[12,32,64,89,106,109,129,147,153,162,166],"work":[13],"related":[14],"to":[15,49,131,152],"training":[16],"robotic":[17],"agents":[18],"with":[19],"reinforcement":[20,35,67,115],"learning":[21,36,68],"a":[24,40,43,54],"major":[25],"focus":[26],"research.":[28,186],"This":[29],"survey":[30],"reviews":[31],"application":[33],"for":[37,114],"pick-and-place":[38,90],"operations,":[39],"task":[41],"that":[42,172,183],"logistics":[44],"robot":[45],"can":[46],"be":[47],"trained":[48],"complete":[50],"without":[51],"support":[52],"from":[53,140],"engineer.":[56],"To":[57],"introduce":[58],"this":[59],"topic,":[60],"we":[61,117],"first":[62],"review":[63,107,121],"fundamentals":[65,110],"various":[70],"methods":[71,124],"policy":[73,80],"optimization,":[74],"such":[75,92],"as":[76,93],"value":[77],"iteration":[78],"search.":[81],"Next,":[82],"factors":[83,113],"which":[84],"have":[85],"an":[86,119],"impact":[87],"on":[88],"task,":[91],"reward":[94],"shaping,":[95],"imitation":[96],"learning,":[97,116],"pose":[98,179],"estimation,":[99],"simulation":[101],"environment":[102],"are":[103,142,155,181],"examined.":[104],"Following":[105],"key":[112],"present":[118],"extensive":[120],"all":[123],"implemented":[125],"by":[126],"researchers":[127],"date.":[132],"strengths":[134],"weaknesses":[136],"each":[138,150],"method":[139],"literature":[141],"discussed,":[143],"details":[145],"about":[146],"contribution":[148],"manuscript":[151],"reviewed.":[156],"concluding":[158],"critical":[159],"discussion":[160],"available":[163],"literature,":[164],"summary":[167],"open":[169],"problems":[170],"indicates":[171],"experiment":[173],"validation,":[174],"model":[175],"generalization,":[176],"grasp":[178],"selection":[180],"topics":[182],"require":[184],"additional":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}