{"id":"https://openalex.org/W4200413037","doi":"https://doi.org/10.1109/iros51168.2021.9635865","title":"ORCHID: Optimisation of Robotic Control and Hardware In Design using Reinforcement Learning","display_name":"ORCHID: Optimisation of Robotic Control and Hardware In Design using Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W4200413037","doi":"https://doi.org/10.1109/iros51168.2021.9635865"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9635865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635865","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5113972647","display_name":"Lucy Jackson","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lucy Jackson","raw_affiliation_strings":["GU2, University of Surrey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GU2, University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054989551","display_name":"Celyn Walters","orcid":"https://orcid.org/0000-0001-6108-4517"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Celyn Walters","raw_affiliation_strings":["GU2, University of Surrey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GU2, University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010795038","display_name":"Steve Eckersley","orcid":"https://orcid.org/0000-0002-9491-4385"},"institutions":[{"id":"https://openalex.org/I1283197605","display_name":"Surrey Satellite Technology (United Kingdom)","ror":"https://ror.org/01s5rx042","country_code":"GB","type":"company","lineage":["https://openalex.org/I1283197605"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Eckersley","raw_affiliation_strings":["Tycho House, GU2, Surrey Satellite Technology Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tycho House, GU2, Surrey Satellite Technology Limited","institution_ids":["https://openalex.org/I1283197605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044201538","display_name":"Pete Senior","orcid":null},"institutions":[{"id":"https://openalex.org/I1283197605","display_name":"Surrey Satellite Technology (United Kingdom)","ror":"https://ror.org/01s5rx042","country_code":"GB","type":"company","lineage":["https://openalex.org/I1283197605"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pete Senior","raw_affiliation_strings":["Tycho House, GU2, Surrey Satellite Technology Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tycho House, GU2, Surrey Satellite Technology Limited","institution_ids":["https://openalex.org/I1283197605"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091184063","display_name":"Simon Hadfield","orcid":"https://orcid.org/0000-0001-8637-5054"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Hadfield","raw_affiliation_strings":["GU2, University of Surrey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GU2, University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8792,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77822395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4911","last_page":"4917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7342900037765503},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7235758304595947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7110589742660522},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6082020998001099},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5503645539283752},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4538976848125458},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.43730902671813965},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43249964714050293},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3414342999458313},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34021347761154175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31713002920150757},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12296715378761292}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7342900037765503},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7235758304595947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110589742660522},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6082020998001099},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5503645539283752},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4538976848125458},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.43730902671813965},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43249964714050293},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3414342999458313},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34021347761154175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31713002920150757},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12296715378761292},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros51168.2021.9635865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635865","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 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":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11151429500002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1211393779","display_name":null,"funder_award_id":"2116510","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G918011532","display_name":null,"funder_award_id":"EP/S035761/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1970233012","https://openalex.org/W2022340880","https://openalex.org/W2098083760","https://openalex.org/W2104705732","https://openalex.org/W2165944157","https://openalex.org/W2257979135","https://openalex.org/W2344075909","https://openalex.org/W2556096037","https://openalex.org/W2581883256","https://openalex.org/W2607735137","https://openalex.org/W2719100828","https://openalex.org/W2737943148","https://openalex.org/W2891122218","https://openalex.org/W2909770505","https://openalex.org/W2949676527","https://openalex.org/W2962696179","https://openalex.org/W2963534270","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2968042644","https://openalex.org/W3038978943","https://openalex.org/W3106528330","https://openalex.org/W3209089215","https://openalex.org/W4297825603","https://openalex.org/W6684157047","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6704744639","https://openalex.org/W6736516544","https://openalex.org/W6757895305","https://openalex.org/W6770029086","https://openalex.org/W6780193278","https://openalex.org/W6780559895","https://openalex.org/W6781780510","https://openalex.org/W6786688792"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W4323768008","https://openalex.org/W3131574667","https://openalex.org/W2586732548","https://openalex.org/W2768698792","https://openalex.org/W2362018761"],"abstract_inverted_index":{"The":[0,115],"successful":[1],"performance":[2,140,157,192],"of":[3,11,28,41,69,193],"any":[4],"system":[5,73,131],"is":[6,15,117,161],"dependant":[7],"on":[8],"the":[9,12,72,79,109,129,155,171,191],"hardware":[10,42],"agent,":[13],"which":[14,35],"typically":[16],"immutable":[17],"during":[18,92],"RL":[19,48],"training.":[20],"In":[21,33],"this":[22,83],"work,":[23],"we":[24,63],"present":[25],"ORCHID":[26,160,182],"(Optimisation":[27],"Robotic":[29],"Control":[30],"and":[31,43,94,111,120],"Hardware":[32],"Design)":[34],"allows":[36,101],"for":[37,102],"truly":[38],"simultaneous":[39],"optimisation":[40],"control":[44,112,149],"parameters":[45,113],"in":[46,78,139,152,183,190],"an":[47,118],"pipeline.":[49],"We":[50,136,174],"show":[51,137,176],"that":[52,74,127],"by":[53],"forming":[54],"a":[55,60,66,85,179,187,194],"complex":[56],"differential":[57],"path":[58],"through":[59],"trajectory":[61],"rollout":[62],"can":[64],"leverage":[65],"vast":[67,188],"amount":[68],"information":[70],"from":[71],"was":[75],"previously":[76],"lost":[77],"\u2018black-box\u2019":[80],"environment.":[81],"Combining":[82],"with":[84,146,159,170],"novel":[86],"hardware-conditioned":[87],"critic":[88],"network":[89],"minimises":[90],"variance":[91],"training":[93],"ensures":[95],"stable":[96],"updates":[97,169],"are":[98],"made.":[99],"This":[100],"refinements":[103],"to":[104,107,123,133,163,186],"be":[105,164],"made":[106],"both":[108],"morphology":[110],"simultaneously.":[114],"result":[116],"efficient":[119],"versatile":[121],"approach":[122],"holistic":[124],"robot":[125,180],"design,":[126],"brings":[128],"final":[130],"nearer":[132],"true":[134],"optimality.":[135],"improvements":[138],"across":[141],"4":[142],"different":[143,148],"test":[144],"environments":[145],"two":[147],"algorithms":[150],"-":[151],"all":[153],"experiments":[154],"maximum":[156],"achieved":[158],"shown":[162],"unattainable":[165],"using":[166,181],"only":[167],"policy":[168],"default":[172],"design.":[173],"also":[175],"how":[177],"re-designing":[178],"simulation,":[184],"transfers":[185],"improvement":[189],"real-world":[195],"robot.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}