{"id":"https://openalex.org/W2914358862","doi":"https://doi.org/10.1109/lra.2019.2896467","title":"Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning","display_name":"Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-01-30","ids":{"openalex":"https://openalex.org/W2914358862","doi":"https://doi.org/10.1109/lra.2019.2896467","mag":"2914358862"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2019.2896467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2019.2896467","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11850/322242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003429397","display_name":"Michel Breyer","orcid":"https://orcid.org/0000-0002-9470-0643"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michel Breyer","raw_affiliation_strings":["Autonomous Systems Lab, ETH, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-9470-0643","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076445011","display_name":"Fadri Furrer","orcid":"https://orcid.org/0000-0002-6070-1760"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fadri Furrer","raw_affiliation_strings":["Autonomous Systems Lab, ETH, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6070-1760","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007761314","display_name":"Ton\u010di Novkovi\u0107","orcid":"https://orcid.org/0000-0003-0209-5915"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tonci Novkovic","raw_affiliation_strings":["Autonomous Systems Lab, ETH, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-0209-5915","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083003222","display_name":"Roland Siegwart","orcid":"https://orcid.org/0000-0002-2760-7983"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roland Siegwart","raw_affiliation_strings":["Autonomous Systems Lab, ETH, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-2760-7983","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059792297","display_name":"Juan Nieto","orcid":"https://orcid.org/0000-0003-4808-0831"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Juan Nieto","raw_affiliation_strings":["Autonomous Systems Lab, ETH, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4808-0831","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5525,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.94970107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"4","issue":"2","first_page":"1549","last_page":"1556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973999857902527,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8010527491569519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7377648949623108},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6740276217460632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6198540329933167},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6078468561172485},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5918107628822327},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.556142270565033},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.536472737789154},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5137975811958313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40721437335014343},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32369130849838257},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09817478060722351},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.0840209424495697}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8010527491569519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7377648949623108},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6740276217460632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6198540329933167},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6078468561172485},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5918107628822327},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.556142270565033},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.536472737789154},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5137975811958313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40721437335014343},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32369130849838257},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09817478060722351},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0840209424495697},{"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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lra.2019.2896467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2019.2896467","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:research-collection.ethz.ch:20.500.11850/322242","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/322242","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"info:eu-repo/semantics/workingPaper"},{"id":"doi:10.3929/ethz-b-000322242","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000322242","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:research-collection.ethz.ch:20.500.11850/322242","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/322242","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"info:eu-repo/semantics/workingPaper"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1515851193","https://openalex.org/W1522301498","https://openalex.org/W1771410628","https://openalex.org/W1978580730","https://openalex.org/W1999156278","https://openalex.org/W2036637075","https://openalex.org/W2060914855","https://openalex.org/W2085261163","https://openalex.org/W2107726111","https://openalex.org/W2125612430","https://openalex.org/W2140173255","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2201912979","https://openalex.org/W2257979135","https://openalex.org/W2285664202","https://openalex.org/W2296073425","https://openalex.org/W2342662072","https://openalex.org/W2485911221","https://openalex.org/W2534269850","https://openalex.org/W2575705757","https://openalex.org/W2600030077","https://openalex.org/W2601066903","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2610395436","https://openalex.org/W2616430965","https://openalex.org/W2617317556","https://openalex.org/W2626073992","https://openalex.org/W2758237641","https://openalex.org/W2773721443","https://openalex.org/W2798273187","https://openalex.org/W2804992755","https://openalex.org/W2810785043","https://openalex.org/W2952629144","https://openalex.org/W2962759351","https://openalex.org/W2962787403","https://openalex.org/W2962899390","https://openalex.org/W2963129648","https://openalex.org/W2963184939","https://openalex.org/W2963293881","https://openalex.org/W2963311874","https://openalex.org/W2963411833","https://openalex.org/W2963484919","https://openalex.org/W2963641140","https://openalex.org/W2963649664","https://openalex.org/W2963654160","https://openalex.org/W2963684914","https://openalex.org/W2963864421","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2972758308","https://openalex.org/W3101442004","https://openalex.org/W3112422759","https://openalex.org/W4293864724","https://openalex.org/W4297818513","https://openalex.org/W6621543089","https://openalex.org/W6638018090","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6695998386","https://openalex.org/W6704571135","https://openalex.org/W6728925229","https://openalex.org/W6735544697","https://openalex.org/W6735677848","https://openalex.org/W6737327832","https://openalex.org/W6737937804","https://openalex.org/W6739378191","https://openalex.org/W6740023956","https://openalex.org/W6740421855","https://openalex.org/W6741302124","https://openalex.org/W6746713385","https://openalex.org/W6780559895","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W2130674020","https://openalex.org/W2093748878","https://openalex.org/W2333771223","https://openalex.org/W2120056845","https://openalex.org/W1981531423","https://openalex.org/W4394861761","https://openalex.org/W1977371217","https://openalex.org/W2035264131","https://openalex.org/W1679012645","https://openalex.org/W1925461966"],"abstract_inverted_index":{"Enabling":[0],"autonomous":[1],"robots":[2],"to":[3,48,55,78,98,133,147,166,172,187],"interact":[4],"in":[5,92,129],"unstructured":[6],"environments":[7],"with":[8,17,36,73,110,122,151,189],"dynamic":[9],"objects":[10,193],"requires":[11],"manipulation":[12],"capabilities":[13],"that":[14,104,162],"can":[15,115],"deal":[16],"clutter,":[18],"changes,":[19],"and":[20,51,65,85,94],"objects'":[21],"variability.":[22],"This":[23],"letter":[24],"presents":[25],"a":[26,37,67,71,74,99,111,123,164,183],"comparison":[27],"of":[28,155],"different":[29,53],"reinforcement":[30],"learning-based":[31],"approaches":[32,54],"for":[33],"object":[34],"picking":[35],"robotic":[38],"manipulator.":[39],"We":[40,102,141,160],"learn":[41],"closed-loop":[42],"policies":[43,97,108,127,146,178],"mapping":[44],"depth":[45,157],"camera":[46],"inputs":[47],"motion":[49],"commands":[50],"compare":[52],"keep":[56],"the":[57,80,96,134,138,148,156,168,177],"problem":[58],"tractable,":[59],"including":[60],"reward":[61,113],"shaping,":[62],"curriculum":[63,106,184],"learning,":[64,107],"using":[66,105,163,182],"policy":[68,135],"pre-trained":[69],"on":[70,137],"task":[72],"reduced":[75],"action":[76],"set":[77],"warm-start":[79,167],"full":[81],"problem.":[82],"For":[83],"efficient":[84],"more":[86],"flexible":[87],"data":[88],"collection,":[89],"we":[90],"train":[91],"simulation":[93],"transfer":[95,144],"real":[100,149],"robot.":[101],"show":[103],"learned":[109,185],"sparse":[112],"formulation":[114],"be":[116],"trained":[117,179],"at":[118],"similar":[119],"rates":[120,131],"as":[121],"shaped":[124],"reward.":[125],"These":[126],"result":[128],"success":[130],"comparable":[132],"initialized":[136],"simplified":[139],"task.":[140],"could":[142],"successfully":[143],"these":[145],"robot":[150],"only":[152],"minor":[153],"modifications":[154],"image":[158],"filtering.":[159],"found":[161],"heuristic":[165],"training":[169],"was":[170],"useful":[171],"enforce":[173],"desired":[174],"behavior,":[175],"while":[176],"from":[180],"scratch":[181],"better":[186],"cope":[188],"unseen":[190],"scenarios":[191],"where":[192],"are":[194],"removed.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}