{"id":"https://openalex.org/W4416749761","doi":"https://doi.org/10.1109/iros60139.2025.11245927","title":"VMTS: Vision-Assisted Teacher-Student Reinforcement Learning for Multi-Terrain Locomotion in Bipedal Robots","display_name":"VMTS: Vision-Assisted Teacher-Student Reinforcement Learning for Multi-Terrain Locomotion in Bipedal Robots","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749761","doi":"https://doi.org/10.1109/iros60139.2025.11245927"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5039118363","display_name":"Chen Fu","orcid":"https://orcid.org/0000-0001-6554-1770"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Chen","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103241430","display_name":"Rui Wan","orcid":"https://orcid.org/0000-0003-1958-1784"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wan","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103244934","display_name":"Peidong Liu","orcid":"https://orcid.org/0000-0003-1261-6120"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peidong Liu","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102988701","display_name":"Nanxing Zheng","orcid":"https://orcid.org/0009-0007-7705-2641"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanxing Zheng","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463402","display_name":"Bingyi Wang","orcid":"https://orcid.org/0000-0002-9401-9145"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingyi Wang","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101808587","display_name":"Bo Zhou","orcid":"https://orcid.org/0000-0002-3908-7575"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhou","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4759","last_page":"4766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9664999842643738,"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":0.9664999842643738,"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/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.004999999888241291,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/terrain","display_name":"Terrain","score":0.7628999948501587},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7281000018119812},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6502000093460083},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6378999948501587},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43639999628067017},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41510000824928284},{"id":"https://openalex.org/keywords/bipedalism","display_name":"Bipedalism","score":0.3476000130176544},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.335999995470047},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.32989999651908875}],"concepts":[{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.7628999948501587},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7281000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6784999966621399},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6502000093460083},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6378999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590999722480774},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C143733281","wikidata":"https://www.wikidata.org/wiki/Q372949","display_name":"Bipedalism","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C2780527621","wikidata":"https://www.wikidata.org/wiki/Q7936593","display_name":"Visual control","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2939999997615814},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C6101204","wikidata":"https://www.wikidata.org/wiki/Q7353391","display_name":"Robot locomotion","level":5,"score":0.2694000005722046},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.25099998712539673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2036604449","https://openalex.org/W2052011296","https://openalex.org/W2890831342","https://openalex.org/W2951360122","https://openalex.org/W3093922502","https://openalex.org/W3175254947","https://openalex.org/W4205430897","https://openalex.org/W4312423130","https://openalex.org/W4313562995","https://openalex.org/W4383108274","https://openalex.org/W4390481019","https://openalex.org/W4390481283","https://openalex.org/W4392763392","https://openalex.org/W4401415792","https://openalex.org/W4402401628","https://openalex.org/W4402449733","https://openalex.org/W4405786631","https://openalex.org/W4413925793"],"related_works":[],"abstract_inverted_index":{"Bipedal":[0],"robots,":[1,77],"due":[2],"to":[3,35,135,155,160],"their":[4,14,22],"anthropomorphic":[5],"design,":[6],"offer":[7],"substantial":[8],"potential":[9],"across":[10,181],"various":[11],"applications,":[12],"yet":[13,117],"control":[15,52],"is":[16,42],"hindered":[17],"by":[18],"the":[19,33,105,127,145,157,170],"complexity":[20],"of":[21,97,107],"structure.":[23],"Currently,":[24],"most":[25,83],"research":[26,84],"focuses":[27],"on":[28,86,111,169],"proprioception-based":[29,69],"methods,":[30],"which":[31,103],"lack":[32],"capability":[34],"overcome":[36],"complex":[37],"terrain.":[38],"While":[39],"visual":[40,112],"perception":[41],"vital":[43],"for":[44,75],"operation":[45],"in":[46,62,131],"human-centric":[47],"environments,":[48],"its":[49,177],"integration":[50],"complicates":[51],"further.":[53],"Recent":[54],"reinforcement":[55],"learning":[56],"(RL)":[57],"approaches":[58],"have":[59],"shown":[60],"promise":[61],"enhancing":[63],"legged":[64],"robot":[65],"locomotion,":[66],"particularly":[67],"with":[68,82,126],"methods.":[70],"However,":[71],"terrain":[72,123,183],"adaptability,":[73],"especially":[74],"bipedal":[76,174],"remains":[78],"a":[79,94,115],"significant":[80],"challenge,":[81],"focusing":[85],"flat-terrain":[87],"scenarios.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92,139],"introduce":[93,140],"novel":[95],"mixture":[96],"experts":[98],"teacher-student":[99,108],"network":[100],"RL":[101],"strategy,":[102],"enhances":[104],"performance":[106,133],"policies":[109],"based":[110],"inputs":[113],"through":[114],"simple":[116],"effective":[118],"approach.":[119],"Our":[120],"method":[121],"combines":[122],"selection":[124],"strategies":[125],"teacher":[128,146],"policy,":[129],"resulting":[130],"superior":[132],"compared":[134],"traditional":[136],"models.":[137],"Additionally,":[138],"an":[141],"alignment":[142],"loss":[143],"between":[144],"and":[147,179],"student":[148],"networks,":[149],"rather":[150],"than":[151],"enforcing":[152],"strict":[153],"similarity,":[154],"improve":[156],"student\u2019s":[158],"ability":[159],"navigate":[161],"diverse":[162],"terrains.":[163],"We":[164],"validate":[165],"our":[166],"approach":[167],"experimentally":[168],"Limx":[171],"Dynamic":[172],"P1":[173],"robot,":[175],"demonstrating":[176],"feasibility":[178],"robustness":[180],"multiple":[182],"types.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}
