{"id":"https://openalex.org/W4415968716","doi":"https://doi.org/10.1109/iecon58223.2025.11221516","title":"Autonomous Drifting of Single-Track Two-Wheeled Robot with Deep Reinforcement Learning","display_name":"Autonomous Drifting of Single-Track Two-Wheeled Robot with Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415968716","doi":"https://doi.org/10.1109/iecon58223.2025.11221516"},"language":null,"primary_location":{"id":"doi:10.1109/iecon58223.2025.11221516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon58223.2025.11221516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","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/A5041025969","display_name":"Yifan Sun","orcid":"https://orcid.org/0000-0003-3532-6521"},"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":"Yifan Sun","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063291337","display_name":"Feilong Jing","orcid":"https://orcid.org/0009-0001-2375-9410"},"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":"Feilong Jing","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043111836","display_name":"Yang Deng","orcid":"https://orcid.org/0000-0001-9420-8467"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012871103","display_name":"Jin Gu","orcid":"https://orcid.org/0000-0003-3968-8036"},"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":"Jin Gu","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","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":["BNRist, Tsinghua Univ,Department of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua Univ,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40541922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.2946999967098236,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.2946999967098236,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.18809999525547028,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.09969999641180038,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8043000102043152},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.6525999903678894},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6478999853134155},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6470999717712402},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5135999917984009},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4147000014781952},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4058000147342682},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3853999972343445}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8043000102043152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559000015258789},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.6525999903678894},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6478999853134155},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6470999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5277000069618225},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.38089999556541443},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.33640000224113464},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3061999976634979},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.27619999647140503},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2676999866962433},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iecon58223.2025.11221516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon58223.2025.11221516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2078676277","https://openalex.org/W2106136078","https://openalex.org/W2127251115","https://openalex.org/W2142014508","https://openalex.org/W2147524078","https://openalex.org/W2157402463","https://openalex.org/W2158782408","https://openalex.org/W2767008557","https://openalex.org/W2811282447","https://openalex.org/W2915454777","https://openalex.org/W2981761302","https://openalex.org/W2999762404","https://openalex.org/W3209403137","https://openalex.org/W4210353754","https://openalex.org/W4214717370","https://openalex.org/W4281570340","https://openalex.org/W4285102561","https://openalex.org/W4296838344","https://openalex.org/W4317383053","https://openalex.org/W4317383440","https://openalex.org/W4381746267","https://openalex.org/W4387951962","https://openalex.org/W4388918636","https://openalex.org/W4388947777","https://openalex.org/W4396592718"],"related_works":[],"abstract_inverted_index":{"Single-Track":[0],"two-wheeled":[1],"(STTW)":[2],"robots,":[3,133],"due":[4,31],"to":[5,32,64],"their":[6,138],"unique":[7],"kinematic":[8],"structure,":[9],"offer":[10],"superior":[11],"dynamic":[12,142],"performance,":[13],"making":[14],"them":[15],"highly":[16],"suitable":[17],"for":[18,26,44,87,131],"real-world":[19],"applications.":[20],"However,":[21],"research":[22],"on":[23,81],"drift":[24,66,71,107],"control":[25],"STTW":[27,88,132],"robots":[28],"is":[29],"limited":[30],"complex":[33],"dynamics,":[34],"narrow":[35],"feasible":[36],"region":[37],"and":[38,55,70,102,112,127],"difficulty":[39],"in":[40,141],"collecting":[41],"demonstration":[42,95],"data":[43],"adopting":[45],"data-driven":[46],"solutions.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,98],"explore":[52],"the":[53,121,135],"feasibility":[54],"effectiveness":[56],"of":[57],"applying":[58],"model-free":[59],"deep":[60],"reinforcement":[61,77],"learning":[62,78],"(DRL)":[63],"two":[65],"tasks:":[67],"steady-state":[68],"drifting":[69,89,129],"trajectory":[72],"tracking.":[73],"We":[74],"trained":[75],"a":[76,100],"controller":[79],"based":[80],"novel":[82],"reward":[83],"functions":[84],"particularly":[85],"designed":[86],"control,":[90],"which":[91],"does":[92],"not":[93],"require":[94],"data.":[96],"Furthermore,":[97],"propose":[99],"sampling":[101],"verification":[103],"mechanism":[104],"that":[105,120],"excludes":[106],"targets":[108],"violating":[109],"action":[110],"constraints":[111],"thus":[113],"improve":[114],"training":[115],"performance.":[116],"Simulation":[117],"results":[118],"show":[119],"DRL-based":[122],"solution":[123],"can":[124],"achieve":[125],"consistent":[126],"generalizable":[128],"behaviors":[130],"paving":[134],"way":[136],"toward":[137],"practical":[139],"deployment":[140],"environments.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-06T00:00:00"}