{"id":"https://openalex.org/W4312293813","doi":"https://doi.org/10.1109/iros47612.2022.9982061","title":"Active Exploration for Robotic Manipulation","display_name":"Active Exploration for Robotic Manipulation","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312293813","doi":"https://doi.org/10.1109/iros47612.2022.9982061"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9982061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982061","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5101815718","display_name":"Tim Schneider","orcid":"https://orcid.org/0000-0001-6605-9257"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tim Schneider","raw_affiliation_strings":["Technical University of Darmstadt,Intelligent Autonomous Systems Lab,Darmstadt,Germany,64289"],"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt,Intelligent Autonomous Systems Lab,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088706700","display_name":"Boris Belousov","orcid":"https://orcid.org/0000-0001-7172-9104"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Boris Belousov","raw_affiliation_strings":["Technical University of Darmstadt,Intelligent Autonomous Systems Lab,Darmstadt,Germany,64289"],"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt,Intelligent Autonomous Systems Lab,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026055366","display_name":"Georgia Chalvatzaki","orcid":"https://orcid.org/0000-0002-5055-199X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georgia Chalvatzaki","raw_affiliation_strings":["Technical University of Darmstadt,Intelligent Autonomous Systems Lab,Darmstadt,Germany,64289"],"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt,Intelligent Autonomous Systems Lab,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062272788","display_name":"Diego Romeres","orcid":"https://orcid.org/0000-0002-8603-2438"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Romeres","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010530960","display_name":"Devesh K. Jha","orcid":"https://orcid.org/0000-0002-7843-9545"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devesh K. Jha","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063321196","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0001-9328-3078"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Technical University of Darmstadt,Intelligent Autonomous Systems Lab,Darmstadt,Germany,64289"],"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt,Intelligent Autonomous Systems Lab,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101815718"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.4185,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.59331107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9355","last_page":"9362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9954000115394592,"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/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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7428866624832153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7350872755050659},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6605980396270752},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5759311318397522},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5530616641044617},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.543679416179657},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5295770168304443},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5060099959373474},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4757758677005768},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41502201557159424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40180861949920654},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3418307304382324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14993071556091309}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7428866624832153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350872755050659},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6605980396270752},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5759311318397522},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5530616641044617},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.543679416179657},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5295770168304443},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5060099959373474},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4757758677005768},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41502201557159424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40180861949920654},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3418307304382324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14993071556091309},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9982061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982061","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308022","display_name":"California Department of Fish and Game","ror":"https://ror.org/02v6w2r95"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W326419249","https://openalex.org/W1691093543","https://openalex.org/W1980928215","https://openalex.org/W2040355924","https://openalex.org/W2048621063","https://openalex.org/W2059320470","https://openalex.org/W2076580309","https://openalex.org/W2100805904","https://openalex.org/W2130195834","https://openalex.org/W2160589914","https://openalex.org/W2164424353","https://openalex.org/W2294642219","https://openalex.org/W2334239033","https://openalex.org/W2560674852","https://openalex.org/W2914261249","https://openalex.org/W2937555108","https://openalex.org/W2947682490","https://openalex.org/W2963017537","https://openalex.org/W2963523627","https://openalex.org/W2964036701","https://openalex.org/W2976205474","https://openalex.org/W2995298643","https://openalex.org/W3008513355","https://openalex.org/W3012211643","https://openalex.org/W3023727388","https://openalex.org/W3036619998","https://openalex.org/W3043426275","https://openalex.org/W3127352841","https://openalex.org/W3189092450","https://openalex.org/W3205868665","https://openalex.org/W4226400653","https://openalex.org/W4287017924","https://openalex.org/W4288319859","https://openalex.org/W4298206671","https://openalex.org/W6680657880","https://openalex.org/W6683436435","https://openalex.org/W6736742618","https://openalex.org/W6747473740","https://openalex.org/W6747837047","https://openalex.org/W6748012927","https://openalex.org/W6751494529","https://openalex.org/W6756192075","https://openalex.org/W6756256016","https://openalex.org/W6758978475","https://openalex.org/W6761392374","https://openalex.org/W6762796984","https://openalex.org/W6762863188","https://openalex.org/W6763407230","https://openalex.org/W6764053384","https://openalex.org/W6764969207","https://openalex.org/W6771217966","https://openalex.org/W6774996162","https://openalex.org/W6778000925","https://openalex.org/W6780559895","https://openalex.org/W6800089562"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W1586572182"],"abstract_inverted_index":{"Robotic":[0],"manipulation":[1,25,60,154],"stands":[2],"as":[3,140],"a":[4,48,105,115,141],"largely":[5],"unsolved":[6],"problem":[7],"despite":[8],"significant":[9],"advances":[10],"in":[11,16,24,57,101,147],"robotics":[12],"and":[13,76,103],"machine":[14],"learning":[15,56,150],"recent":[17],"years.":[18],"One":[19],"of":[20,29,32,73,144,151],"the":[21,27,30,33,41,88,124,132],"key":[22],"challenges":[23],"is":[26,37,128],"exploration":[28,51,146],"dynamics":[31],"environment":[34],"when":[35],"there":[36],"continuous":[38],"contact":[39],"between":[40],"objects":[42],"being":[43],"manipulated.":[44],"This":[45],"paper":[46],"proposes":[47],"model-based":[49,148],"active":[50,145],"approach":[52],"that":[53,86],"enables":[54],"efficient":[55],"sparse-reward":[58],"robotic":[59,153],"tasks.":[61,155],"The":[62],"proposed":[63,99],"method":[64],"estimates":[65],"an":[66,71],"information":[67],"gain":[68],"objective":[69],"using":[70],"ensemble":[72],"probabilistic":[74],"models":[75],"deploys":[77],"model":[78],"predictive":[79],"control":[80],"(MPC)":[81],"to":[82,131],"plan":[83],"actions":[84],"online":[85],"maximize":[87],"expected":[89],"reward":[90],"while":[91],"also":[92],"performing":[93],"directed":[94],"exploration.":[95],"We":[96],"evaluate":[97],"our":[98,112],"algorithm":[100],"simulation":[102],"on":[104,114,120],"real":[106],"robot,":[107],"trained":[108],"from":[109],"scratch":[110],"with":[111],"method,":[113],"challenging":[116],"ball":[117,126],"pushing":[118],"task":[119],"tilted":[121],"tables,":[122],"where":[123],"target":[125],"position":[127],"not":[129],"known":[130],"agent":[133],"a-priori.":[134],"Our":[135],"real-world":[136],"robot":[137],"experiment":[138],"serves":[139],"fundamental":[142],"application":[143],"reinforcement":[149],"complex":[152],"Project":[156],"page":[157],"https://sites.google.com/view/aerm.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}