{"id":"https://openalex.org/W4410614007","doi":"https://doi.org/10.1109/lra.2025.3572427","title":"ALARM: Safe Reinforcement Learning With Reliable Mimicry for Robust Legged Locomotion","display_name":"ALARM: Safe Reinforcement Learning With Reliable Mimicry for Robust Legged Locomotion","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4410614007","doi":"https://doi.org/10.1109/lra.2025.3572427"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3572427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3572427","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5101221591","display_name":"Qiqi Zhou","orcid":"https://orcid.org/0009-0003-3261-9844"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiqi Zhou","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0003-3261-9844","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104098480","display_name":"Hui Ding","orcid":"https://orcid.org/0009-0006-5470-4056"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Ding","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0006-5470-4056","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637772","display_name":"Teng Chen","orcid":"https://orcid.org/0000-0002-7905-564X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Chen","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-7905-564X","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Luxin Man","orcid":"https://orcid.org/0009-0005-8382-6223"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luxin Man","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0005-8382-6223","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891512","display_name":"Han Jiang","orcid":"https://orcid.org/0000-0001-7242-3369"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Jiang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-7242-3369","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070648653","display_name":"Guoteng Zhang","orcid":"https://orcid.org/0000-0001-7705-2819"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoteng Zhang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-7705-2819","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100744772","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-4028-0938"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-4028-0938","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025820722","display_name":"Xuewen Rong","orcid":"https://orcid.org/0000-0003-3283-5347"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewen Rong","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-3283-5347","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724411","display_name":"Yibin Li","orcid":"https://orcid.org/0000-0002-5906-5074"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Li","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5906-5074","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0254,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85944591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"10","issue":"7","first_page":"6768","last_page":"6775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9972000122070312,"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/mimicry","display_name":"Mimicry","score":0.9336050748825073},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6937554478645325},{"id":"https://openalex.org/keywords/alarm","display_name":"ALARM","score":0.692081093788147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49816298484802246},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44836658239364624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4177485704421997},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24610719084739685},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2262367308139801},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1844419240951538},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.16398319602012634},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07646271586418152},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.06007122993469238}],"concepts":[{"id":"https://openalex.org/C7863114","wikidata":"https://www.wikidata.org/wiki/Q192627","display_name":"Mimicry","level":2,"score":0.9336050748825073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6937554478645325},{"id":"https://openalex.org/C2779119184","wikidata":"https://www.wikidata.org/wiki/Q294350","display_name":"ALARM","level":2,"score":0.692081093788147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49816298484802246},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44836658239364624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4177485704421997},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24610719084739685},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2262367308139801},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1844419240951538},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.16398319602012634},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07646271586418152},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.06007122993469238}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3572427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3572427","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1194196734","display_name":null,"funder_award_id":"62203268","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7467507350","display_name":null,"funder_award_id":"62373217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2901286613","https://openalex.org/W2911087563","https://openalex.org/W2964198579","https://openalex.org/W3011016396","https://openalex.org/W3093922502","https://openalex.org/W3104876774","https://openalex.org/W3113616534","https://openalex.org/W3175254947","https://openalex.org/W4206497039","https://openalex.org/W4221155471","https://openalex.org/W4226143977","https://openalex.org/W4283787029","https://openalex.org/W4285600796","https://openalex.org/W4382365373","https://openalex.org/W4383108274","https://openalex.org/W4387158111","https://openalex.org/W4387351182","https://openalex.org/W4390938336","https://openalex.org/W4396910086","https://openalex.org/W4400680090","https://openalex.org/W4401415792","https://openalex.org/W4402354142","https://openalex.org/W4405778675","https://openalex.org/W4405786631","https://openalex.org/W6640174482","https://openalex.org/W6772033386","https://openalex.org/W6788240645","https://openalex.org/W6801964084","https://openalex.org/W6846358943","https://openalex.org/W6846664724","https://openalex.org/W6857483907","https://openalex.org/W6859578310"],"related_works":["https://openalex.org/W2566749067","https://openalex.org/W2332959588","https://openalex.org/W2159218316","https://openalex.org/W2379994817","https://openalex.org/W2373086291","https://openalex.org/W3158429762","https://openalex.org/W1980659691","https://openalex.org/W2132785383","https://openalex.org/W2146352487","https://openalex.org/W4385683480"],"abstract_inverted_index":{"Legged":[0],"robots":[1,32,66],"are":[2],"supposed":[3],"to":[4,12,18,27],"traverse":[5],"complicated":[6],"environments,":[7],"which":[8,84,103],"makes":[9],"it":[10],"challenging":[11],"design":[13],"a":[14,38,54,73,118],"model-based":[15],"controller":[16],"due":[17],"their":[19],"functional":[20],"complexity.":[21],"Currently,":[22],"using":[23,67],"deep":[24],"reinforcement":[25,55,92],"learning":[26,56,90,93],"improve":[28],"the":[29,86],"adaptability":[30],"of":[31,88],"in":[33,64],"complex":[34],"scenarios":[35],"has":[36],"been":[37],"major":[39],"research":[40],"trend.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"Adaptive":[47],"Latent":[48],"Aggregation":[49],"for":[50,121],"Reliable":[51],"Mimicry":[52],"(ALARM),":[53],"framework":[57,96],"that":[58],"enables":[59],"safe":[60],"and":[61,91],"robust":[62],"locomotion":[63,109],"legged":[65,123],"only":[68],"proprioception.":[69],"This":[70],"work":[71],"features":[72],"one-step":[74],"teacher-student":[75],"training":[76],"paradigm":[77],"by":[78],"constructing":[79],"an":[80],"adaptive":[81],"aggregation":[82],"strategy,":[83],"integrates":[85,97],"merits":[87],"imitation":[89],"effectively.":[94],"The":[95],"normalized":[98],"penalized":[99],"proximal":[100],"policy":[101],"optimization,":[102],"penalizes":[104],"constraint-violating":[105],"behaviors":[106],"while":[107],"optimizing":[108],"policy.":[110],"Our":[111],"method":[112],"facilitates":[113],"efficient":[114],"sim-to-real":[115],"transfer,":[116],"offering":[117],"promising":[119],"approach":[120],"real-world":[122],"robot":[124],"applications.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}
