{"id":"https://openalex.org/W3113139432","doi":"https://doi.org/10.1109/smc42975.2020.9282951","title":"Learning Continuous Control Actions for Robotic Grasping with Reinforcement Learning","display_name":"Learning Continuous Control Actions for Robotic Grasping with Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-11","ids":{"openalex":"https://openalex.org/W3113139432","doi":"https://doi.org/10.1109/smc42975.2020.9282951","mag":"3113139432"},"language":"en","primary_location":{"id":"doi:10.1109/smc42975.2020.9282951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9282951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003810719","display_name":"Asad Ali Shahid","orcid":"https://orcid.org/0009-0001-0312-9657"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Asad Ali Shahid","raw_affiliation_strings":["Politecnico di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086291668","display_name":"Loris Roveda","orcid":"https://orcid.org/0000-0002-4427-536X"},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Loris Roveda","raw_affiliation_strings":["Istituto Dalle Molle di studi sull\u2019Intelligenza Artificiale (IDSIA) Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Universit\u00e0 della Svizzera Italiana (USI) IDSIA-SUPSI, Lugano, Switzerland","Istituto Dalle Molle di studi sull'Intelligenza Artificiale (IDSIA) Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Universit\u00e0 della Svizzera Italiana (USI) IDSIA-SUPSI, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Dalle Molle di studi sull\u2019Intelligenza Artificiale (IDSIA) Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Universit\u00e0 della Svizzera Italiana (USI) IDSIA-SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"raw_affiliation_string":"Istituto Dalle Molle di studi sull'Intelligenza Artificiale (IDSIA) Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Universit\u00e0 della Svizzera Italiana (USI) IDSIA-SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046585507","display_name":"Dario Piga","orcid":"https://orcid.org/0000-0001-7691-4886"},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dario Piga","raw_affiliation_strings":["Istituto Dalle Molle di studi sull\u2019Intelligenza Artificiale (IDSIA) Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Universit\u00e0 della Svizzera Italiana (USI) IDSIA-SUPSI, Lugano, Switzerland","Istituto Dalle Molle di studi sull'Intelligenza Artificiale (IDSIA) Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Universit\u00e0 della Svizzera Italiana (USI) IDSIA-SUPSI, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Dalle Molle di studi sull\u2019Intelligenza Artificiale (IDSIA) Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Universit\u00e0 della Svizzera Italiana (USI) IDSIA-SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"raw_affiliation_string":"Istituto Dalle Molle di studi sull'Intelligenza Artificiale (IDSIA) Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Universit\u00e0 della Svizzera Italiana (USI) IDSIA-SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050750282","display_name":"Francesco Braghin","orcid":"https://orcid.org/0000-0002-0476-4118"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Braghin","raw_affiliation_strings":["Politecnico di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4066","last_page":"4072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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":0.9763000011444092,"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":0.8457257151603699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7194123268127441},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.7018966674804688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6831303238868713},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.654069185256958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6469926834106445},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6028144359588623},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.5432114005088806},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5040292143821716},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4414665400981903},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4326373040676117},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41244766116142273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31855762004852295},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.21908318996429443},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14359909296035767}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8457257151603699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194123268127441},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7018966674804688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6831303238868713},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.654069185256958},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6469926834106445},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6028144359588623},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.5432114005088806},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5040292143821716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4414665400981903},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4326373040676117},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41244766116142273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31855762004852295},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.21908318996429443},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14359909296035767},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/smc42975.2020.9282951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9282951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1163438","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/9282951","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W2012204020","https://openalex.org/W2012587148","https://openalex.org/W2016765487","https://openalex.org/W2070665593","https://openalex.org/W2100235553","https://openalex.org/W2109102709","https://openalex.org/W2121103318","https://openalex.org/W2121863487","https://openalex.org/W2126909264","https://openalex.org/W2133068870","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2156737235","https://openalex.org/W2158782408","https://openalex.org/W2169209873","https://openalex.org/W2172158418","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2342662072","https://openalex.org/W2529601334","https://openalex.org/W2605102758","https://openalex.org/W2725320964","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2785962646","https://openalex.org/W2810785043","https://openalex.org/W2899059606","https://openalex.org/W2962736495","https://openalex.org/W2962746398","https://openalex.org/W2963394817","https://openalex.org/W2963641140","https://openalex.org/W2963713397","https://openalex.org/W2963864421","https://openalex.org/W2964157221","https://openalex.org/W2964161785","https://openalex.org/W2981030070","https://openalex.org/W3003629310","https://openalex.org/W4297818513","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6675894441","https://openalex.org/W6678367057","https://openalex.org/W6679958247","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6683195989","https://openalex.org/W6684921986","https://openalex.org/W6685331716","https://openalex.org/W6704571135","https://openalex.org/W6740023956","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6753243525","https://openalex.org/W6755421158"],"related_works":["https://openalex.org/W4250003534","https://openalex.org/W2134294860","https://openalex.org/W1973668536","https://openalex.org/W2911965264","https://openalex.org/W2724299411","https://openalex.org/W2030895127","https://openalex.org/W1965774354","https://openalex.org/W4316038512","https://openalex.org/W2110346561","https://openalex.org/W4365788246"],"abstract_inverted_index":{"Robots":[0],"are":[1,77],"nowadays":[2],"increasingly":[3],"required":[4],"to":[5,17,21,79,101,137,180,188,207,222],"deal":[6],"with":[7,81],"(partially)":[8],"unknown":[9],"tasks":[10],"and":[11,118,194,214,224],"situations.":[12],"The":[13,109,144,183,201],"robot":[14,187,220],"has,":[15],"therefore,":[16],"adapt":[18],"its":[19],"behavior":[20],"the":[22,64,135,153,162,177,186,190,198,219,226],"specific":[23],"working":[24],"conditions.":[25],"Classical":[26],"control":[27,70,87,110],"methods":[28],"in":[29,42,150],"robotics":[30],"require":[31],"manually":[32],"programming":[33],"all":[34],"actions":[35],"of":[36,54,66,141,161],"a":[37,92,115,168],"robot.":[38],"While":[39],"very":[40],"effective":[41],"fixed":[43],"conditions,":[44],"such":[45],"model-based":[46],"approaches":[47,76],"cannot":[48],"handle":[49],"variations,":[50],"demanding":[51],"tedious":[52],"tuning":[53],"parameters":[55],"for":[56,85,134],"every":[57],"new":[58,69],"task.":[59,163,228],"Reinforcement":[60],"learning":[61,68,80,140],"(RL)":[62],"holds":[63],"promise":[65],"autonomously":[67],"policies":[71],"through":[72,107],"trial-and-error.":[73],"However,":[74],"RL":[75],"prone":[78],"high":[82],"samples,":[83],"particularly":[84],"continuous":[86],"problems.":[88],"In":[89],"this":[90],"paper,":[91],"learning-based":[93],"method":[94],"is":[95,112,147],"presented":[96],"that":[97],"leverages":[98],"simulation":[99,151],"data":[100],"learn":[102,223],"an":[103,142],"object":[104,212],"manipulation":[105],"task":[106,136,166,179,184],"RL.":[108],"policy":[111],"parameterized":[113],"by":[114],"neural":[116],"network":[117],"learned":[119],"using":[120],"modern":[121],"Proximal":[122],"Policy":[123],"Optimization":[124],"(PPO)":[125],"algorithm.":[126],"A":[127,164],"dense":[128],"reward":[129],"function":[130],"has":[131,173,204],"been":[132,174,205],"designed":[133],"enable":[138],"efficient":[139],"agent.":[143],"proposed":[145,202],"approach":[146,203],"trained":[148],"entirely":[149],"(exploiting":[152],"MuJoCo":[154],"environment)":[155],"from":[156],"scratch":[157],"without":[158],"any":[159],"demonstrations":[160],"grasping":[165],"involving":[167],"Franka":[169],"Emika":[170],"Panda":[171],"manipulator":[172],"considered":[175],"as":[176],"reference":[178],"be":[181,208],"learned.":[182],"requires":[185],"reach":[189],"part,":[191],"grasp":[192],"it,":[193],"lift":[195],"it":[196],"off":[197],"contact":[199],"surface.":[200],"demonstrated":[206],"generalizable":[209],"across":[210],"multiple":[211],"geometries":[213],"initial":[215],"robot/parts":[216],"configurations,":[217],"having":[218],"able":[221],"re-execute":[225],"target":[227]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":10}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}