{"id":"https://openalex.org/W4297505030","doi":"https://doi.org/10.3390/s22197382","title":"Computational Optimization of Image-Based Reinforcement Learning for Robotics","display_name":"Computational Optimization of Image-Based Reinforcement Learning for Robotics","publication_year":2022,"publication_date":"2022-09-28","ids":{"openalex":"https://openalex.org/W4297505030","doi":"https://doi.org/10.3390/s22197382","pmid":"https://pubmed.ncbi.nlm.nih.gov/36236477"},"language":"en","primary_location":{"id":"doi:10.3390/s22197382","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22197382","pdf_url":"https://www.mdpi.com/1424-8220/22/19/7382/pdf?version=1665203538","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/19/7382/pdf?version=1665203538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060542882","display_name":"Stefano Ferraro","orcid":"https://orcid.org/0000-0001-8193-4240"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Stefano Ferraro","raw_affiliation_strings":["IDLab, Ghent University, 25843 Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-8193-4240","affiliations":[{"raw_affiliation_string":"IDLab, Ghent University, 25843 Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062379167","display_name":"Toon Van de Maele","orcid":"https://orcid.org/0000-0001-7583-3291"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Toon Van de Maele","raw_affiliation_strings":["IDLab, Ghent University, 25843 Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab, Ghent University, 25843 Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008371078","display_name":"Pietro Mazzaglia","orcid":"https://orcid.org/0000-0003-3319-5986"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Pietro Mazzaglia","raw_affiliation_strings":["IDLab, Ghent University, 25843 Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0003-3319-5986","affiliations":[{"raw_affiliation_string":"IDLab, Ghent University, 25843 Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071221406","display_name":"Tim Verbelen","orcid":"https://orcid.org/0000-0003-2731-7262"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tim Verbelen","raw_affiliation_strings":["IDLab, Ghent University, 25843 Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0003-2731-7262","affiliations":[{"raw_affiliation_string":"IDLab, Ghent University, 25843 Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032558375","display_name":"Bart Dhoedt","orcid":"https://orcid.org/0000-0002-7271-7479"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bart Dhoedt","raw_affiliation_strings":["IDLab, Ghent University, 25843 Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab, Ghent University, 25843 Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060542882"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.6561,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74014305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"22","issue":"19","first_page":"7382","last_page":"7382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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/T11601","display_name":"Neuroscience and Neural Engineering","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.7942056059837341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7188270688056946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7074674367904663},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.680470883846283},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5685545206069946},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5124722123146057},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.49487632513046265},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49358904361724854},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.46594157814979553},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.44805973768234253},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.43009406328201294},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4182778000831604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3500678539276123},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16911691427230835},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10847970843315125},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.09245085716247559}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7942056059837341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7188270688056946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074674367904663},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.680470883846283},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5685545206069946},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5124722123146057},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.49487632513046265},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49358904361724854},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.46594157814979553},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.44805973768234253},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.43009406328201294},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4182778000831604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3500678539276123},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16911691427230835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10847970843315125},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.09245085716247559},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D018737","descriptor_name":"Hand Strength","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018737","descriptor_name":"Hand Strength","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018737","descriptor_name":"Hand Strength","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.3390/s22197382","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22197382","pdf_url":"https://www.mdpi.com/1424-8220/22/19/7382/pdf?version=1665203538","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},{"id":"pmid:36236477","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36236477","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:archive.ugent.be:8771317","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8771317","pdf_url":"https://biblio.ugent.be/publication/8771317/file/8771319.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 1424-8220","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:70b46f99982a42d6befbf3f7cc79fc49","is_oa":true,"landing_page_url":"https://doaj.org/article/70b46f99982a42d6befbf3f7cc79fc49","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 22, Iss 19, p 7382 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/19/7382/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22197382","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":"Sensors; Volume 22; Issue 19; Pages: 7382","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9571553","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9571553","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22197382","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22197382","pdf_url":"https://www.mdpi.com/1424-8220/22/19/7382/pdf?version=1665203538","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297505030.pdf","grobid_xml":"https://content.openalex.org/works/W4297505030.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1993383995","https://openalex.org/W2082511574","https://openalex.org/W2120284346","https://openalex.org/W2145339207","https://openalex.org/W2736506089","https://openalex.org/W2895268904","https://openalex.org/W2919115771","https://openalex.org/W2940669070","https://openalex.org/W2960833983","https://openalex.org/W2962793652","https://openalex.org/W2962962024","https://openalex.org/W2963446712","https://openalex.org/W2966086598","https://openalex.org/W2970352191","https://openalex.org/W2970971581","https://openalex.org/W2989777804","https://openalex.org/W3007935348","https://openalex.org/W3088310808","https://openalex.org/W3120778962","https://openalex.org/W3132082252","https://openalex.org/W3134399927","https://openalex.org/W3174982021"],"related_works":["https://openalex.org/W2557924869","https://openalex.org/W4380075502","https://openalex.org/W2888481972","https://openalex.org/W2907945115","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W2767518918","https://openalex.org/W4364306694","https://openalex.org/W3111283311"],"abstract_inverted_index":{"The":[0],"robotics":[1],"field":[2],"has":[3,18],"been":[4,19],"deeply":[5],"influenced":[6],"by":[7,21,111,118,156,174],"the":[8,22,37,51,71,75,94,106,113,120,127,132,150,165,171,182,186],"advent":[9],"of":[10,24,74,115,185],"deep":[11],"learning.":[12],"In":[13,62,188],"recent":[14],"years,":[15],"this":[16,63],"trend":[17],"characterized":[20],"adoption":[23],"large,":[25,46],"pretrained":[26],"models":[27,49,77],"for":[28,57,69],"robotic":[29,42],"use":[30],"cases,":[31],"which":[32,54],"are":[33],"not":[34],"compatible":[35],"with":[36],"computational":[38,72,133,172],"hardware":[39],"available":[40],"in":[41,79,109,153],"systems.":[43,61],"Moreover,":[44],"such":[45],"computationally":[47],"intensive":[48],"impede":[50],"low-latency":[52],"execution":[53],"is":[55],"required":[56],"many":[58],"closed-loop":[59,192],"control":[60,193],"work,":[64],"we":[65,87,104,124,136,141,190],"propose":[66],"different":[67],"strategies":[68,167],"improving":[70,181],"efficiency":[73,173],"deep-learning":[76],"adopted":[78],"reinforcement-learning":[80],"(RL)":[81],"scenarios.":[82],"As":[83,99],"a":[84,100,158,196,203],"use-case":[85],"project,":[86],"consider":[88,125],"an":[89],"image-based":[90],"RL":[91],"method":[92],"on":[93,195,202],"synergy":[95],"between":[96],"push-and-grasp":[97],"actions.":[98],"first":[101],"optimization":[102,155,166],"step,":[103],"reduce":[105,131],"model":[107],"architecture":[108,121],"complexity,":[110],"decreasing":[112],"number":[114],"layers":[116],"and":[117,145],"altering":[119],"structure.":[122],"Second,":[123],"downscaling":[126],"input":[128],"resolution":[129],"to":[130],"load.":[134],"Finally,":[135],"perform":[137],"weight":[138],"quantization,":[139],"where":[140],"compare":[142],"post-training":[143],"quantization":[144],"quantized-aware":[146],"training.":[147],"We":[148,162],"benchmark":[149],"improvements":[151],"introduced":[152,168],"each":[154],"running":[157],"standard":[159],"testing":[160],"routine.":[161],"show":[163],"that":[164],"can":[169],"improve":[170],"around":[175],"300":[176],"times,":[177],"while":[178,199],"also":[179],"slightly":[180],"functional":[183],"performance":[184],"system.":[187],"addition,":[189],"demonstrate":[191],"behaviour":[194],"real-world":[197],"robot,":[198],"processing":[200],"everything":[201],"Jetson":[204],"Xavier":[205],"NX":[206],"edge":[207],"device.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}