{"id":"https://openalex.org/W4403486891","doi":"https://doi.org/10.3233/faia241014","title":"Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning","display_name":"Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403486891","doi":"https://doi.org/10.3233/faia241014"},"language":"en","primary_location":{"id":"doi:10.3233/faia241014","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia241014","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia241014","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018498977","display_name":"Runhao Zeng","orcid":"https://orcid.org/0000-0001-8694-4245"},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Runhao Zeng","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, China","institution_ids":["https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102486367","display_name":"Dingjie Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingjie Zhou","raw_affiliation_strings":["College of Mechatronics and Control Engineering, Shenzhen University"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Control Engineering, Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101676571","display_name":"Qiwei Liang","orcid":"https://orcid.org/0000-0002-4422-2137"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwei Liang","raw_affiliation_strings":["College of Mechatronics and Control Engineering, Shenzhen University"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Control Engineering, Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101880141","display_name":"Junlin Liu","orcid":"https://orcid.org/0009-0007-5650-4979"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlin Liu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051035661","display_name":"Hui Li","orcid":"https://orcid.org/0000-0002-5555-8920"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["College of Mechatronics and Control Engineering, Shenzhen University"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Control Engineering, Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046865333","display_name":"Changxin Huang","orcid":"https://orcid.org/0000-0002-9588-064X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxin Huang","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393871","display_name":"Jianqiang Li","orcid":"https://orcid.org/0000-0002-2208-962X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Li","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007941489","display_name":"Xiping Hu","orcid":"https://orcid.org/0000-0002-4952-699X"},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiping Hu","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, China","institution_ids":["https://openalex.org/I4388482657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111876340","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0002-9169-951X"},"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":"Fuchun Sun","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5018498977"],"corresponding_institution_ids":["https://openalex.org/I4388482657"],"apc_list":null,"apc_paid":null,"fwci":4.0223,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94304281,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11135","display_name":"Virology and Viral Diseases","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11135","display_name":"Virology and Viral Diseases","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.973800003528595,"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/T11560","display_name":"Animal Disease Management and Epidemiology","score":0.9301999807357788,"subfield":{"id":"https://openalex.org/subfields/1102","display_name":"Agronomy and Crop Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7344310283660889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6934664249420166},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6257921457290649},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5719907283782959},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5369967818260193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5356205701828003},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5160114765167236},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36451685428619385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3215865194797516}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7344310283660889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934664249420166},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6257921457290649},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5719907283782959},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5369967818260193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356205701828003},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5160114765167236},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36451685428619385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3215865194797516},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia241014","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia241014","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2412.05515","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.05515","pdf_url":"https://arxiv.org/pdf/2412.05515","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.3233/faia241014","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia241014","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4860469773","display_name":null,"funder_award_id":"62202311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G657063301","display_name":null,"funder_award_id":"2023A1515011512","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6641422996","display_name":null,"funder_award_id":"22104038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7198236715","display_name":null,"funder_award_id":"20220809180405001","funder_id":"https://openalex.org/F4320316880","funder_display_name":"Natural Science Foundation of Shenzhen City"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7626431573","display_name":null,"funder_award_id":"51501151","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G772798963","display_name":null,"funder_award_id":"104038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316880","display_name":"Natural Science Foundation of Shenzhen City","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320337998","display_name":"HORIZON EUROPE Excellent Science","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Learning":[0],"behavior":[1,64,188],"in":[2,33,108,136,217],"legged":[3],"robots":[4],"presents":[5],"a":[6,24,74,118,154],"significant":[7],"challenge":[8],"due":[9],"to":[10,29,54,59,88,130,140,170,178],"its":[11],"inherent":[12],"instability":[13],"and":[14,62,91,166,196,242],"complex":[15],"constraints.":[16],"Recent":[17],"research":[18],"has":[19],"proposed":[20],"the":[21,38,86,99,103,109,132,142,146,149,163,171,176,181,206],"use":[22],"of":[23,106,148,208,219],"large":[25],"language":[26],"model":[27],"(LLM)":[28],"generate":[30,131],"reward":[31,81,133,150,157,182,211],"functions":[32,82],"reinforcement":[34],"learning,":[35],"thereby":[36],"replacing":[37],"need":[39],"for":[40],"manually":[41],"designed":[42],"rewards":[43],"by":[44,214,225],"experts.":[45],"However,":[46],"this":[47,70],"approach,":[48],"which":[49,78,135],"relies":[50],"on":[51,192],"textual":[52,168],"descriptions":[53],"define":[55],"learning":[56,65],"objectives,":[57],"fails":[58],"achieve":[60],"controllable":[61],"precise":[63],"with":[66],"clear":[67],"directionality.":[68],"In":[69],"paper,":[71],"we":[72,94,152,229],"introduce":[73],"new":[75],"video2reward":[76],"method,":[77],"directly":[79],"generates":[80],"from":[83],"videos":[84,97,110],"depicting":[85],"behaviors":[87,165,238],"be":[89],"mimicked":[90],"learned.":[92],"Specifically,":[93],"first":[95],"process":[96],"containing":[98],"target":[100],"behaviors,":[101],"converting":[102],"motion":[104,199,237],"information":[105],"individuals":[107],"into":[111,127],"keypoint":[112],"trajectories":[113,123],"represented":[114],"as":[115,240],"coordinates":[116],"through":[117],"video2text":[119],"transforming":[120],"module.":[121],"These":[122],"are":[124],"then":[125],"fed":[126],"an":[128],"LLM":[129,177],"function,":[134,151,183],"turn":[137],"is":[138],"used":[139],"train":[141],"policy.":[143],"To":[144],"enhance":[145],"quality":[147],"develop":[153],"video-assisted":[155],"iterative":[156],"refinement":[158],"scheme":[159],"that":[160,202],"visually":[161],"assesses":[162],"learned":[164],"provides":[167],"feedback":[169,174],"LLM.":[172],"This":[173],"guides":[175],"continually":[179],"refine":[180],"ultimately":[184],"facilitating":[185],"more":[186],"efficient":[187],"learning.":[189],"Experimental":[190],"results":[191],"tasks":[193],"involving":[194],"bipedal":[195],"quadrupedal":[197],"robot":[198],"control":[200],"demonstrate":[201],"our":[203,231],"method":[204,232],"surpasses":[205],"performance":[207],"state-of-the-art":[209],"LLM-based":[210],"generation":[212],"methods":[213],"over":[215],"37.6%":[216],"terms":[218],"human":[220],"normalized":[221],"score.":[222],"More":[223],"importantly,":[224],"switching":[226],"video":[227],"inputs,":[228],"find":[230],"can":[233],"rapidly":[234],"learn":[235],"diverse":[236],"such":[239],"walking":[241],"running.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}
