{"id":"https://openalex.org/W3197905921","doi":"https://doi.org/10.1177/01423312211037847","title":"Continuous reinforcement learning based ramp jump control for single-track two-wheeled robots","display_name":"Continuous reinforcement learning based ramp jump control for single-track two-wheeled robots","publication_year":2021,"publication_date":"2021-08-28","ids":{"openalex":"https://openalex.org/W3197905921","doi":"https://doi.org/10.1177/01423312211037847","mag":"3197905921"},"language":"en","primary_location":{"id":"doi:10.1177/01423312211037847","is_oa":false,"landing_page_url":"https://doi.org/10.1177/01423312211037847","pdf_url":null,"source":{"id":"https://openalex.org/S24148485","display_name":"Transactions of the Institute of Measurement and Control","issn_l":"0142-3312","issn":["0142-3312","1477-0369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Institute of Measurement and Control","raw_type":"journal-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/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":true,"raw_author_name":"Qingyuan Zheng","raw_affiliation_strings":["Department of Automation, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0002-6743-4327","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334974","display_name":"Duo Wang","orcid":"https://orcid.org/0000-0002-7070-034X"},"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":"Duo Wang","raw_affiliation_strings":["Department of Automation, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452417","display_name":"Zhang Chen","orcid":"https://orcid.org/0000-0003-4317-9373"},"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":["Department of Automation, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101690398","display_name":"Yiyong Sun","orcid":"https://orcid.org/0000-0001-5250-3468"},"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":"Yiyong Sun","raw_affiliation_strings":["Department of Automation, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","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":["Department of Automation, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101520982"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.0817,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87066339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"44","issue":"4","first_page":"892","last_page":"904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12810","display_name":"Real-time simulation and control systems","score":0.989300012588501,"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/T12810","display_name":"Real-time simulation and control systems","score":0.989300012588501,"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":0.9882000088691711,"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/T10524","display_name":"Traffic control and management","score":0.9871000051498413,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9005595445632935},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6740596890449524},{"id":"https://openalex.org/keywords/jump","display_name":"Jump","score":0.6408926844596863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6401614546775818},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.6178504228591919},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5734735727310181},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5430180430412292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4250187575817108},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42475754022598267},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4159565567970276},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4106053411960602},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3452007472515106},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2473280429840088}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9005595445632935},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6740596890449524},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.6408926844596863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6401614546775818},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.6178504228591919},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5734735727310181},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5430180430412292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4250187575817108},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42475754022598267},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4159565567970276},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4106053411960602},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3452007472515106},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2473280429840088},{"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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/01423312211037847","is_oa":false,"landing_page_url":"https://doi.org/10.1177/01423312211037847","pdf_url":null,"source":{"id":"https://openalex.org/S24148485","display_name":"Transactions of the Institute of Measurement and Control","issn_l":"0142-3312","issn":["0142-3312","1477-0369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Institute of Measurement and Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8500000238418579,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4296342713","display_name":null,"funder_award_id":"61703228","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5552769826","display_name":null,"funder_award_id":"61903219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7025346706","display_name":null,"funder_award_id":"2020T130351","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8465316650","display_name":null,"funder_award_id":"62073183","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1496249676","https://openalex.org/W1557517019","https://openalex.org/W2002232590","https://openalex.org/W2073903944","https://openalex.org/W2076192651","https://openalex.org/W2078676277","https://openalex.org/W2097979582","https://openalex.org/W2107136560","https://openalex.org/W2115966471","https://openalex.org/W2119717200","https://openalex.org/W2124149195","https://openalex.org/W2128410439","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2156974162","https://openalex.org/W2157047204","https://openalex.org/W2169681057","https://openalex.org/W2172968643","https://openalex.org/W2291199538","https://openalex.org/W2484754949","https://openalex.org/W2492794003","https://openalex.org/W2915454777","https://openalex.org/W2921793253","https://openalex.org/W2968348607","https://openalex.org/W2973148106","https://openalex.org/W3037720013","https://openalex.org/W3041202696","https://openalex.org/W3048156710","https://openalex.org/W3098733038","https://openalex.org/W3148362830","https://openalex.org/W4254789786","https://openalex.org/W4376502360","https://openalex.org/W6684205842"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"Single-track":[0],"two-wheeled":[1,43,61,104],"robots":[2],"have":[3],"become":[4],"an":[5],"important":[6],"research":[7],"topic":[8],"in":[9],"recent":[10],"years,":[11],"owing":[12],"to":[13,21,39],"their":[14],"simple":[15],"structure,":[16],"energy":[17],"savings":[18],"and":[19,80,99,118,134],"ability":[20],"run":[22],"on":[23],"narrow":[24],"roads.":[25],"However,":[26],"the":[27,74,77,84,93,102,113],"ramp":[28,45,106],"jump":[29,107],"remains":[30],"a":[31,41,49,66],"challenging":[32],"task.":[33,108],"In":[34],"this":[35],"study,":[36],"we":[37,91],"propose":[38],"realize":[40,101],"single-track":[42,60,103],"robot":[44,62,105],"jump.":[46],"We":[47,64],"present":[48],"control":[50,94,114,129],"method":[51,95,115],"that":[52,112],"employs":[53],"continuous":[54],"action":[55,78,124,136],"reinforcement":[56,71,127,137],"learning":[57,128,138],"techniques":[58],"for":[59,70],"control.":[63,139],"design":[65],"novel":[67],"reward":[68,132],"function":[69,133],"learning,":[72],"optimize":[73],"dimensions":[75],"of":[76,130],"space,":[79],"enable":[81],"training":[82],"under":[83],"deep":[85],"deterministic":[86],"policy":[87],"gradient":[88],"algorithm.":[89],"Finally,":[90],"validate":[92,111],"through":[96],"simulation":[97],"experiments":[98],"successfully":[100],"Simulation":[109],"results":[110],"is":[116],"effective":[117],"has":[119],"several":[120],"advantages":[121],"over":[122],"high-dimension":[123],"space":[125],"control,":[126],"sparse":[131],"discrete":[135]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}