{"id":"https://openalex.org/W2151472180","doi":"https://doi.org/10.1109/robot.2009.5152335","title":"A novel method for learning policies from constrained motion","display_name":"A novel method for learning policies from constrained motion","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2151472180","doi":"https://doi.org/10.1109/robot.2009.5152335","mag":"2151472180"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2009.5152335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2009.5152335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Robotics and Automation","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/A5050881123","display_name":"Matthew Howard","orcid":"https://orcid.org/0000-0003-2534-4865"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Matthew Howard","raw_affiliation_strings":["Institute of Perception Action and Behaviour, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Institute of Perception Action and Behaviour, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049236982","display_name":"Stefan Klanke","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Klanke","raw_affiliation_strings":["Institute of Perception Action and Behaviour, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Institute of Perception Action and Behaviour, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025560073","display_name":"Michael Gienger","orcid":"https://orcid.org/0000-0001-8036-2519"},"institutions":[{"id":"https://openalex.org/I4210112253","display_name":"Honda (Germany)","ror":"https://ror.org/022c1xk47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210112253"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Gienger","raw_affiliation_strings":["Honda Research Institute Europe GmBH, Offenbach, Germany"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Europe GmBH, Offenbach, Germany","institution_ids":["https://openalex.org/I4210112253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053974584","display_name":"Christian Goerick","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112253","display_name":"Honda (Germany)","ror":"https://ror.org/022c1xk47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210112253"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Goerick","raw_affiliation_strings":["Honda Research Institute Europe GmBH, Offenbach, Germany"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Europe GmBH, Offenbach, Germany","institution_ids":["https://openalex.org/I4210112253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069715982","display_name":"Sethu Vijayakumar","orcid":"https://orcid.org/0000-0003-0649-7241"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sethu Vijayakumar","raw_affiliation_strings":["Institute of Perception Action and Behaviour, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Institute of Perception Action and Behaviour, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050881123"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":3.076,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92296842,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1717","last_page":"1723"},"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9886000156402588,"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/unobservable","display_name":"Unobservable","score":0.8820831775665283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7264500856399536},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7130225300788879},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.6844265460968018},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6058555245399475},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.578009307384491},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5511271357536316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5179859399795532},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5054569244384766},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45631349086761475},{"id":"https://openalex.org/keywords/degrees-of-freedom","display_name":"Degrees of freedom (physics and chemistry)","score":0.4197620153427124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4147800803184509},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12317207455635071},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11411824822425842},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08972534537315369},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.08219647407531738}],"concepts":[{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.8820831775665283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264500856399536},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7130225300788879},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.6844265460968018},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6058555245399475},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.578009307384491},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5511271357536316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5179859399795532},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5054569244384766},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45631349086761475},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.4197620153427124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4147800803184509},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12317207455635071},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11411824822425842},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08972534537315369},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.08219647407531738},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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":5,"locations":[{"id":"doi:10.1109/robot.2009.5152335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2009.5152335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.318.9325","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.318.9325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ipab.informatics.ed.ac.uk/slmc/SLMCpeople/Howard_M_files/icra09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.505.2452","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.505.2452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://stiff-project.org/uploads/tx_sibibtex/HowKlaGieGoeVij2009.pdf","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/3654","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/3654","pdf_url":null,"source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/ed474a8b-ef1d-4de9-93de-2d2fe57726ee","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/ed474a8b-ef1d-4de9-93de-2d2fe57726ee","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Howard, M, Klanke, S, Gienger, M, Goerick, C & Vijayakumar, S 2009, A Novel Method for Learning Policies from Constrained Motion. in ICRA '09. IEEE International Conference on Robotics and Automation, 2009. pp. 1717-1723. https://doi.org/10.1109/ROBOT.2009.5152335","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323389","display_name":"Universit\u00e4t Bielefeld","ror":"https://ror.org/02hpadn98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1684361744","https://openalex.org/W1963726847","https://openalex.org/W2049617391","https://openalex.org/W2092604609","https://openalex.org/W2112474089","https://openalex.org/W2114006755","https://openalex.org/W2119088038","https://openalex.org/W2122364547","https://openalex.org/W2123967136","https://openalex.org/W2130726249","https://openalex.org/W2150297144","https://openalex.org/W2167804690","https://openalex.org/W2168921921","https://openalex.org/W2543071036","https://openalex.org/W3088063282","https://openalex.org/W4211008118","https://openalex.org/W6677616476","https://openalex.org/W6678157427","https://openalex.org/W6682452441","https://openalex.org/W6808409006"],"related_works":["https://openalex.org/W2614563012","https://openalex.org/W4293337373","https://openalex.org/W1968533609","https://openalex.org/W1984270607","https://openalex.org/W2151842462","https://openalex.org/W2349333549","https://openalex.org/W2116445905","https://openalex.org/W2486803649","https://openalex.org/W3140685204","https://openalex.org/W3016354044"],"abstract_inverted_index":{"Many":[0],"everyday":[1],"human":[2],"skills":[3],"can":[4],"be":[5],"framed":[6],"in":[7],"terms":[8],"of":[9,90,104],"performing":[10],"some":[11],"task":[12],"subject":[13],"to":[14,65,72],"constraints":[15],"imposed":[16],"by":[17],"the":[18,66,78,97],"environment.":[19],"Constraints":[20],"are":[21],"usually":[22],"unobservable":[23],"and":[24,81],"frequently":[25],"change":[26],"between":[27,77],"contexts.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,57],"present":[33],"a":[34,54,59,74],"novel":[35],"approach":[36,87],"for":[37],"learning":[38],"(unconstrained)":[39],"control":[40],"policies":[41],"from":[42,48,96],"movement":[43],"data,":[44],"where":[45],"observations":[46],"come":[47],"movements":[49],"under":[50],"different":[51],"constraints.":[52],"As":[53],"key":[55],"ingredient,":[56],"introduce":[58],"small":[60],"but":[61],"highly":[62],"effective":[63],"modification":[64],"standard":[67],"risk":[68],"functional,":[69],"allowing":[70],"us":[71],"make":[73],"meaningful":[75],"comparison":[76],"estimated":[79],"policy":[80],"constrained":[82],"observations.":[83],"We":[84],"demonstrate":[85],"our":[86],"on":[88],"systems":[89],"varying":[91],"complexity,":[92],"including":[93],"kinematic":[94],"data":[95],"ASIMO":[98],"humanoid":[99],"robot":[100],"with":[101],"27":[102],"degrees":[103],"freedom.":[105]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}