{"id":"https://openalex.org/W4389665798","doi":"https://doi.org/10.1109/iros55552.2023.10342187","title":"End-to-End Reinforcement Learning for Torque Based Variable Height Hopping","display_name":"End-to-End Reinforcement Learning for Torque Based Variable Height Hopping","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665798","doi":"https://doi.org/10.1109/iros55552.2023.10342187"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5046961999","display_name":"Raghav Soni","orcid":"https://orcid.org/0000-0002-9566-5528"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghav Soni","raw_affiliation_strings":["Indian Institute of Technology (Banaras Hindu University),Department of Electronics Engineering,Varanasi,India","Department of Electronics Engineering, Indian Institute of Technology (Banaras Hindu University), Varanasi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology (Banaras Hindu University),Department of Electronics Engineering,Varanasi,India","institution_ids":["https://openalex.org/I91357014"]},{"raw_affiliation_string":"Department of Electronics Engineering, Indian Institute of Technology (Banaras Hindu University), Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067081068","display_name":"Daniel Harnack","orcid":"https://orcid.org/0000-0001-6255-0321"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Harnack","raw_affiliation_strings":["DFKI GmbH Robotic-s Innovation Center,Bremen,Germany","DFKI GmbH Robotic-s Innovation Center, Bremen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI GmbH Robotic-s Innovation Center,Bremen,Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"DFKI GmbH Robotic-s Innovation Center, Bremen, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040475195","display_name":"Hannah Isermann","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hannah Isermann","raw_affiliation_strings":["DFKI GmbH Robotic-s Innovation Center,Bremen,Germany","DFKI GmbH Robotic-s Innovation Center, Bremen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI GmbH Robotic-s Innovation Center,Bremen,Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"DFKI GmbH Robotic-s Innovation Center, Bremen, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112972262","display_name":"Sotaro Fushimi","orcid":"https://orcid.org/0009-0007-4514-8040"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sotaro Fushimi","raw_affiliation_strings":["Kyoto University,Undergraduate Course Program of Mechanical and Systems Engineering,Kyoto,Japan","Undergraduate Course Program of Mechanical and Systems Engineering, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Undergraduate Course Program of Mechanical and Systems Engineering,Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Undergraduate Course Program of Mechanical and Systems Engineering, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036934435","display_name":"Shivesh Kumar","orcid":"https://orcid.org/0000-0002-6254-3882"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shivesh Kumar","raw_affiliation_strings":["DFKI GmbH Robotic-s Innovation Center,Bremen,Germany","DFKI GmbH Robotic-s Innovation Center, Bremen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI GmbH Robotic-s Innovation Center,Bremen,Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"DFKI GmbH Robotic-s Innovation Center, Bremen, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016436943","display_name":"Frank Kirchner","orcid":"https://orcid.org/0000-0002-1713-9784"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Kirchner","raw_affiliation_strings":["DFKI GmbH Robotic-s Innovation Center,Bremen,Germany","DFKI GmbH Robotic-s Innovation Center, Bremen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI GmbH Robotic-s Innovation Center,Bremen,Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"DFKI GmbH Robotic-s Innovation Center, Bremen, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8201,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.6969078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7531","last_page":"7538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9997000098228455,"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":0.9997000098228455,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9901999831199646,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9843999743461609,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7921789884567261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6969411969184875},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6181962490081787},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5234493613243103},{"id":"https://openalex.org/keywords/jump","display_name":"Jump","score":0.5211658477783203},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5076242685317993},{"id":"https://openalex.org/keywords/torque","display_name":"Torque","score":0.5068288445472717},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.49097564816474915},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4488638639450073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44740158319473267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3753126263618469},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.36723461747169495},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.19903269410133362},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19577810168266296},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1224367618560791}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7921789884567261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969411969184875},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6181962490081787},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5234493613243103},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.5211658477783203},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5076242685317993},{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.5068288445472717},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.49097564816474915},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4488638639450073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44740158319473267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3753126263618469},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.36723461747169495},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.19903269410133362},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19577810168266296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1224367618560791},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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":43,"referenced_works":["https://openalex.org/W1530083085","https://openalex.org/W1970890515","https://openalex.org/W2002853107","https://openalex.org/W2061063863","https://openalex.org/W2100615611","https://openalex.org/W2107180483","https://openalex.org/W2112036188","https://openalex.org/W2114036586","https://openalex.org/W2133236858","https://openalex.org/W2138046132","https://openalex.org/W2158581396","https://openalex.org/W2158782408","https://openalex.org/W2413990562","https://openalex.org/W2767050701","https://openalex.org/W2781726626","https://openalex.org/W2907537824","https://openalex.org/W2911087563","https://openalex.org/W2937683675","https://openalex.org/W2963097630","https://openalex.org/W3002258670","https://openalex.org/W3003817470","https://openalex.org/W3024597329","https://openalex.org/W3099547539","https://openalex.org/W3101442004","https://openalex.org/W3132082252","https://openalex.org/W3136347463","https://openalex.org/W3155009074","https://openalex.org/W3183038449","https://openalex.org/W3206620955","https://openalex.org/W4225004582","https://openalex.org/W4281717224","https://openalex.org/W4283787029","https://openalex.org/W4287630799","https://openalex.org/W4366724849","https://openalex.org/W4390357269","https://openalex.org/W4390481291","https://openalex.org/W6743923790","https://openalex.org/W6777295057","https://openalex.org/W6778428183","https://openalex.org/W6784706691","https://openalex.org/W6785466209","https://openalex.org/W6798795566","https://openalex.org/W6809847274"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775","https://openalex.org/W2952904874"],"abstract_inverted_index":{"Legged":[0],"locomotion":[1],"is":[2,41],"arguably":[3],"the":[4,32,52,56,104,109,129,142],"most":[5],"suited":[6],"and":[7,22,35,50,81],"versatile":[8],"mode":[9],"to":[10,54,101,111,125,132],"deal":[11],"with":[12],"natural":[13],"or":[14,78],"unstructured":[15],"terrains.":[16],"Intensive":[17],"research":[18],"into":[19],"dynamic":[20,44,135],"walking":[21],"running":[23],"controllers":[24,84],"has":[25,51],"recently":[26],"yielded":[27],"great":[28],"advances,":[29],"both":[30],"in":[31,138],"optimal":[33],"control":[34,63],"reinforcement":[36],"learning":[37],"(RL)":[38],"literature.":[39],"Hopping":[40],"a":[42,47,93,121],"challenging":[43],"task":[45],"involving":[46],"flight":[48],"phase":[49],"potential":[53],"increase":[55],"traversability":[57],"of":[58,71,128],"legged":[59],"robots.":[60],"Model":[61],"based":[62,96],"for":[64,85,115,123],"hopping":[65],"typically":[66],"relies":[67],"on":[68,141],"accurate":[69],"detection":[70],"different":[72,83],"jump":[73,106],"phases,":[74,107],"such":[75],"as":[76],"lift-off":[77],"touch":[79],"down,":[80],"using":[82],"each":[86],"phase.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91],"present":[92],"end-to-end":[94],"RL":[95],"torque":[97],"controller":[98,131],"that":[99],"learns":[100],"implicitly":[102],"detect":[103],"relevant":[105],"removing":[108],"need":[110],"provide":[112],"manual":[113],"heuristics":[114],"state":[116],"detection.":[117],"We":[118],"also":[119],"extend":[120],"method":[122],"simulation":[124],"reality":[126],"transfer":[127],"learned":[130],"contact":[133],"rich":[134],"tasks,":[136],"resulting":[137],"successful":[139],"deployment":[140],"robot":[143],"after":[144],"training":[145],"without":[146],"parameter":[147],"tuning.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-12-14T00:00:00"}