{"id":"https://openalex.org/W4415048837","doi":"https://doi.org/10.23919/ccc64809.2025.11178866","title":"Improvement of Basic Behaviors for Bipedal Robot Based on PPO Algorithm","display_name":"Improvement of Basic Behaviors for Bipedal Robot Based on PPO Algorithm","publication_year":2025,"publication_date":"2025-07-28","ids":{"openalex":"https://openalex.org/W4415048837","doi":"https://doi.org/10.23919/ccc64809.2025.11178866"},"language":"en","primary_location":{"id":"doi:10.23919/ccc64809.2025.11178866","doi":"https://doi.org/10.23919/ccc64809.2025.11178866","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ccc64809.2025.11178866","pdf_url":null,"source":{"id":"https://openalex.org/S4363607703","display_name":"Chinese Control Conference (CCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2025 44th Chinese Control Conference (CCC)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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":null,"display_name":"Xiangrui Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangrui Jiang","raw_affiliation_strings":["College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087394806","display_name":"Bowen Hu","orcid":"https://orcid.org/0000-0003-0730-3648","observed_orcids":["https://orcid.org/0000-0003-0730-3648","https://orcid.org/0009-0000-6729-6019"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Hu","raw_affiliation_strings":["College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505105","display_name":"Yifan Jiang","orcid":"https://orcid.org/0009-0007-5334-9627","observed_orcids":["https://orcid.org/0009-0007-5334-9627","https://orcid.org/0009-0002-4310-2069"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Jiang","raw_affiliation_strings":["College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675404","display_name":"Chu Li","orcid":"https://orcid.org/0000-0002-0591-4771","observed_orcids":["https://orcid.org/0000-0002-0591-4771"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu Li","raw_affiliation_strings":["College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091449095","display_name":"Kuihan Chen","orcid":"https://orcid.org/0009-0006-5831-5277","observed_orcids":["https://orcid.org/0009-0006-5831-5277"]},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuihan Chen","raw_affiliation_strings":["School of Future Science and Engineering, Soochow University,Suzhou,P. R. China,215006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Future Science and Engineering, Soochow University,Suzhou,P. R. China,215006","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101619211","display_name":"Zhiwei Liang","orcid":"https://orcid.org/0009-0003-6349-575X","observed_orcids":["https://orcid.org/0009-0003-6349-575X"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Liang","raw_affiliation_strings":["College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and College of Aritifical Intelligence, Nanjing University of Posts and Telecommunications,Nanjing,P. R. China,210023","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1027,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82204766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4920","last_page":"4925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.6279000043869019,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.6279000043869019,"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":0.3711000084877014,"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":0.0003000000142492354,"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/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.9350000023841858},{"id":"https://openalex.org/keywords/movement-primitives","display_name":"motion primitives","score":0.6100000143051147},{"id":"https://openalex.org/keywords/multi-objective-reward-function","display_name":"multi-objective reward function","score":0.8100000023841858},{"id":"https://openalex.org/keywords/walking-and-running","display_name":"walking and running","score":0.6520000100135803},{"id":"https://openalex.org/keywords/gait-stability","display_name":"gait stability","score":0.7379999756813049},{"id":"https://openalex.org/keywords/robocup","display_name":"RoboCup","score":0.8510000109672546}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6610999703407288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.642300009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6069999933242798},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5254999995231628},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C2780465443","wikidata":"https://www.wikidata.org/wiki/Q852061","display_name":"Champion","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3950999975204468},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2615000009536743},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/ccc64809.2025.11178866","doi":"https://doi.org/10.23919/ccc64809.2025.11178866","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ccc64809.2025.11178866","pdf_url":null,"source":{"id":"https://openalex.org/S4363607703","display_name":"Chinese Control Conference (CCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2025 44th Chinese Control Conference (CCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2125621103","https://openalex.org/W2145339207","https://openalex.org/W2730539781","https://openalex.org/W2766408330","https://openalex.org/W2919616510","https://openalex.org/W3164631379","https://openalex.org/W4377102358","https://openalex.org/W4389924455","https://openalex.org/W4390976912","https://openalex.org/W4402568850"],"related_works":["https://openalex.org/W4385660897","https://openalex.org/W4403741606","https://openalex.org/W3168511769","https://openalex.org/W7090875381","https://openalex.org/W4416598187","https://openalex.org/W4415222839","https://openalex.org/W7214667947","https://openalex.org/W7160413969","https://openalex.org/W4410503067","https://openalex.org/W4412756792"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"makes":[4],"a":[5,47,70,88],"big":[6],"improvement":[7],"for":[8],"robotic":[9],"control.":[10],"However,":[11],"training":[12],"stable":[13],"and":[14,20,31,42,81,112,115,143],"efficient":[15],"bipedal":[16],"gaits":[17],"like":[18],"walking":[19,111],"running":[21,113],"still":[22],"remains":[23],"challenging.":[24],"Current":[25],"DRL":[26],"approaches":[27],"can":[28],"be":[29],"sample-inefficient":[30],"struggle":[32],"with":[33,55],"stability,":[34],"while":[35],"traditional":[36],"methods":[37],"may":[38],"lack":[39],"peak":[40],"performance":[41,80],"adaptability.":[43],"This":[44],"paper":[45],"proposes":[46],"novel":[48],"approach":[49,126],"integrating":[50],"Proximal":[51],"Policy":[52],"Optimization":[53],"(PPO)":[54],"Skill-Set-Primitives":[56],"(SS-primitives),":[57],"which":[58],"predefined":[59],"biomechanically-inspired":[60],"motion":[61],"patterns":[62],"capturing":[63],"commonalities":[64],"across":[65],"locomotion":[66,96],"tasks.":[67],"By":[68],"providing":[69],"structured":[71],"baseline,":[72],"SS-primitives":[73],"allow":[74],"PPO":[75,120],"to":[76,83,93,118],"focus":[77],"on":[78],"refining":[79],"adapting":[82],"specific":[84],"goals.":[85],"We":[86],"introduce":[87],"multi-objective":[89],"reward":[90],"function":[91],"designed":[92],"prioritize":[94],"key":[95],"metrics.":[97],"Experiments":[98],"conducted":[99],"in":[100],"the":[101,131,138],"SimSpark":[102],"simulation":[103],"environment":[104],"demon-strate":[105],"that":[106],"our":[107],"method":[108],"significantly":[109],"improves":[110],"speed":[114],"stability":[116],"compared":[117],"standard":[119],"training.":[121],"The":[122],"effectiveness":[123],"of":[124],"this":[125,150],"was":[127],"further":[128],"validated":[129],"by":[130],"Apollo3D":[132],"team's":[133],"success,":[134],"achieving":[135],"Champion":[136],"at":[137,146],"RoboCup":[139,147],"China":[140],"Open":[141],"2024":[142,148],"third":[144],"place":[145],"using":[149],"framework.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-11T00:00:00"}