{"id":"https://openalex.org/W4317383440","doi":"https://doi.org/10.1109/robio55434.2022.10011757","title":"Ramp Jump Control of Single-track Two-wheeled Robot using Reinforcement Learning with Demonstration Data","display_name":"Ramp Jump Control of Single-track Two-wheeled Robot using Reinforcement Learning with Demonstration Data","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317383440","doi":"https://doi.org/10.1109/robio55434.2022.10011757"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011757","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 International Conference on Robotics and Biomimetics (ROBIO)","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/A5101520982","display_name":"Qingyuan Zheng","orcid":"https://orcid.org/0000-0002-6743-4327"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyuan Zheng","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059444883","display_name":"Xianjin Zhu","orcid":"https://orcid.org/0000-0001-8894-5700"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianjin Zhu","raw_affiliation_strings":["School of Mechatronics Engineering, Harbin Institute of Technology,Harbin,China,150006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechatronics Engineering, Harbin Institute of Technology,Harbin,China,150006","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048881121","display_name":"Boyi Wang","orcid":"https://orcid.org/0000-0001-9120-4583"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyi Wang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101627282","display_name":"Yang Deng","orcid":"https://orcid.org/0000-0002-7318-1899"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Deng","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374141","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0002-8293-0601"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Chen","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644629","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0002-7163-345X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4457,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90515335,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1769","last_page":"1774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9980999827384949,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9818000197410583,"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":0.7909954786300659},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.7741422653198242},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7422728538513184},{"id":"https://openalex.org/keywords/jump","display_name":"Jump","score":0.7407994866371155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694304883480072},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6427154541015625},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5736944675445557},{"id":"https://openalex.org/keywords/jumping","display_name":"Jumping","score":0.5226366519927979},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5130873918533325},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5074560046195984},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.46826058626174927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44774797558784485},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43394869565963745},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.42011627554893494},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3155835270881653},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1689102053642273},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09625640511512756}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7909954786300659},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.7741422653198242},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7422728538513184},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.7407994866371155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694304883480072},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6427154541015625},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5736944675445557},{"id":"https://openalex.org/C2779897013","wikidata":"https://www.wikidata.org/wiki/Q1151752","display_name":"Jumping","level":2,"score":0.5226366519927979},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5130873918533325},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5074560046195984},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.46826058626174927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44774797558784485},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43394869565963745},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.42011627554893494},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3155835270881653},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1689102053642273},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09625640511512756},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio55434.2022.10011757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011757","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6016665242","display_name":null,"funder_award_id":"62073183","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2073903944","https://openalex.org/W2076192651","https://openalex.org/W2078676277","https://openalex.org/W2155027007","https://openalex.org/W2163008031","https://openalex.org/W2172968643","https://openalex.org/W2484754949","https://openalex.org/W2736601468","https://openalex.org/W2740104662","https://openalex.org/W2741122588","https://openalex.org/W2788862220","https://openalex.org/W2915454777","https://openalex.org/W2921793253","https://openalex.org/W2963864421","https://openalex.org/W2973148106","https://openalex.org/W3197522818","https://openalex.org/W3197905921","https://openalex.org/W4251229830","https://openalex.org/W6638018090","https://openalex.org/W6638959657","https://openalex.org/W6677067356","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6741949246","https://openalex.org/W6742461812","https://openalex.org/W6748839928"],"related_works":["https://openalex.org/W3124676748","https://openalex.org/W2334192603","https://openalex.org/W2382466266","https://openalex.org/W2385281849","https://openalex.org/W1591560775","https://openalex.org/W2562824280","https://openalex.org/W4229024545","https://openalex.org/W2512066353","https://openalex.org/W2581854855","https://openalex.org/W2310118952"],"abstract_inverted_index":{"The":[0],"single-track":[1],"two-wheeled":[2],"(STTW)":[3],"robot":[4,18,57,138],"ramp":[5,40,61,79,142],"jump":[6,29,62,143],"is":[7,86,119],"a":[8,45,52,122],"challenging":[9],"task.":[10,63],"This":[11,42],"task":[12,144],"not":[13],"only":[14],"requires":[15,32],"the":[16,24,28,55,60,65,76,91,94,100,115,130,136,141,146],"STTW":[17,56,137],"to":[19,34,50,58,88,109,139],"maintain":[20],"its":[21],"balance":[22],"during":[23],"various":[25],"phases":[26],"of":[27,78],"but":[30],"also":[31],"it":[33],"use":[35],"different":[36,39],"speeds":[37],"for":[38,54],"terrains.":[41,154],"article":[43],"proposes":[44],"deep":[46],"reinforcement":[47],"learning":[48],"method":[49,118,133],"generate":[51],"controller":[53],"complete":[59,140],"First,":[64],"corresponding":[66],"state":[67],"space":[68,71],"and":[69,149],"action":[70],"are":[72,97],"designed":[73],"based":[74],"on":[75,145,150],"characteristics":[77],"jumping.":[80],"Second,":[81],"an":[82],"effective":[83],"reward":[84],"function":[85],"developed":[87],"help":[89],"train":[90],"agent.":[92],"Then,":[93],"demonstration":[95],"data":[96],"introduced":[98],"into":[99],"Twin":[101],"Delayed":[102],"Deep":[103],"Deterministic":[104],"Policy":[105],"Gradient":[106],"(TD3)":[107],"algorithm":[108],"obtain":[110],"better":[111],"training":[112,147],"results.":[113],"Finally,":[114],"proposed":[116,131],"control":[117,132],"verified":[120],"in":[121],"dynamic":[123],"simulation":[124],"environment.":[125],"Simulation":[126],"results":[127],"show":[128],"that":[129],"can":[134],"enable":[135],"terrain":[148],"some":[151],"other":[152],"test":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}