{"id":"https://openalex.org/W4401416328","doi":"https://doi.org/10.1109/icra57147.2024.10610137","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","display_name":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416328","doi":"https://doi.org/10.1109/icra57147.2024.10610137"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5024315223","display_name":"Lukas Schneider","orcid":"https://orcid.org/0000-0001-9708-9248"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Lukas Schneider","raw_affiliation_strings":["ETH Zurich,Robotic Systems Lab,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Robotic Systems Lab,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016683949","display_name":"Jonas Frey","orcid":"https://orcid.org/0000-0002-7401-2173"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jonas Frey","raw_affiliation_strings":["ETH Zurich,Robotic Systems Lab,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Robotic Systems Lab,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016407319","display_name":"Takahiro Miki","orcid":"https://orcid.org/0000-0001-8556-2819"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Takahiro Miki","raw_affiliation_strings":["ETH Zurich,Robotic Systems Lab,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Robotic Systems Lab,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044258783","display_name":"Marco Hutter","orcid":"https://orcid.org/0000-0002-4285-4990"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marco Hutter","raw_affiliation_strings":["ETH Zurich,Robotic Systems Lab,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Robotic Systems Lab,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024315223"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":3.192,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92379396,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11451","last_page":"11458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9988999962806702,"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":0.9988999962806702,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9861999750137329,"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/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/quadrupedalism","display_name":"Quadrupedalism","score":0.8963563442230225},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8190537691116333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6982719898223877},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4757891893386841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4043129086494446},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37644627690315247},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18108579516410828}],"concepts":[{"id":"https://openalex.org/C134181672","wikidata":"https://www.wikidata.org/wiki/Q21907045","display_name":"Quadrupedalism","level":2,"score":0.8963563442230225},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8190537691116333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6982719898223877},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4757891893386841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4043129086494446},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37644627690315247},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18108579516410828},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320326765","display_name":"National Centre of Competence in Research Robotics","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1647779468","https://openalex.org/W1845972764","https://openalex.org/W2053984877","https://openalex.org/W2560418171","https://openalex.org/W2619903301","https://openalex.org/W2736601468","https://openalex.org/W2909553221","https://openalex.org/W2911087563","https://openalex.org/W2951191893","https://openalex.org/W2963184939","https://openalex.org/W2970857152","https://openalex.org/W2977518448","https://openalex.org/W2978134924","https://openalex.org/W3023210489","https://openalex.org/W3093922502","https://openalex.org/W3104876774","https://openalex.org/W3107153805","https://openalex.org/W3123216837","https://openalex.org/W3129049248","https://openalex.org/W3131341185","https://openalex.org/W3204973825","https://openalex.org/W3207033168","https://openalex.org/W4205430897","https://openalex.org/W4210870706","https://openalex.org/W4250058668","https://openalex.org/W4281479885","https://openalex.org/W4287120583","https://openalex.org/W4296561979","https://openalex.org/W4302010773","https://openalex.org/W4312441173","https://openalex.org/W4312749288","https://openalex.org/W4315881846","https://openalex.org/W4382981485","https://openalex.org/W4385430650","https://openalex.org/W4394674699","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6744927671","https://openalex.org/W6745500190","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6750645735","https://openalex.org/W6751629939","https://openalex.org/W6759679099","https://openalex.org/W6760854571","https://openalex.org/W6762639926","https://openalex.org/W6767112054","https://openalex.org/W6770012831","https://openalex.org/W6773161478","https://openalex.org/W6776730770","https://openalex.org/W6788575936","https://openalex.org/W6796923828","https://openalex.org/W6801964084","https://openalex.org/W6843725745","https://openalex.org/W6846664724","https://openalex.org/W6848925757","https://openalex.org/W6852263707"],"related_works":["https://openalex.org/W4388251424","https://openalex.org/W2008498579","https://openalex.org/W2923272690","https://openalex.org/W2559825912","https://openalex.org/W2064963663","https://openalex.org/W1966935220","https://openalex.org/W3100731831","https://openalex.org/W2806616984","https://openalex.org/W4323670354","https://openalex.org/W2139075120"],"abstract_inverted_index":{"Deployment":[0],"in":[1,72,156],"hazardous":[2],"environments":[3],"requires":[4],"robots":[5],"to":[6,16,51,68,88,102,117,128,145],"understand":[7],"the":[8,64,73,77,130,138,160,166],"risks":[9,23],"associated":[10],"with":[11,76],"their":[12],"actions":[13],"and":[14,158,168],"movements":[15],"prevent":[17],"accidents.":[18],"Despite":[19],"its":[20],"importance,":[21],"these":[22],"are":[24,95,170],"not":[25],"explicitly":[26],"modeled":[27],"by":[28,84,122],"currently":[29],"deployed":[30],"locomotion":[31,44,154],"controllers":[32],"for":[33,70,140],"legged":[34],"robots.":[35],"In":[36],"this":[37],"work,":[38],"we":[39,62],"propose":[40],"a":[41,59,85,123],"risk":[42,86,90,112,147,152],"sensitive":[43,91,153],"training":[45],"method":[46],"employing":[47],"distributional":[48],"reinforcement":[49],"learning":[50],"consider":[52],"safety":[53],"explicitly.":[54],"Instead":[55],"of":[56,165],"relying":[57],"on":[58,159],"value":[60,66,80,92],"expectation,":[61],"estimate":[63],"complete":[65],"distribution":[67,81],"account":[69],"uncertainty":[71],"robot\u2019s":[74,131],"interaction":[75],"environment.":[78],"The":[79,111],"is":[82],"consumed":[83],"metric":[87],"extract":[89],"estimates.":[93],"These":[94],"integrated":[96],"into":[97],"Proximal":[98,107],"Policy":[99,108],"Optimization":[100,109],"(PPO)":[101],"derive":[103],"our":[104,135],"method,":[105],"Distributional":[106],"(DPPO).":[110],"preference,":[113],"ranging":[114],"from":[115],"risk-averse":[116],"risk-seeking,":[118],"can":[119],"be":[120],"controlled":[121],"single":[124],"parameter,":[125],"which":[126],"enables":[127],"adjust":[129],"behavior":[132,155],"dynamically.":[133],"Importantly,":[134],"approach":[136],"removes":[137],"need":[139],"additional":[141],"reward":[142],"function":[143],"tuning":[144],"achieve":[146],"sensitivity.":[148],"We":[149],"show":[150],"emergent":[151],"simulation":[157],"quadrupedal":[161],"robot":[162],"ANYmal.":[163],"Videos":[164],"experiments":[167],"code":[169],"available":[171],"at":[172],"https://sites.google.com/leggedrobotics.com/risk-aware-locomotion.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}