{"id":"https://openalex.org/W4413925996","doi":"https://doi.org/10.1109/icra55743.2025.11127287","title":"Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances","display_name":"Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925996","doi":"https://doi.org/10.1109/icra55743.2025.11127287"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5034239627","display_name":"Hanyang Hu","orcid":"https://orcid.org/0000-0002-2625-5939"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hanyang Hu","raw_affiliation_strings":["Simon Fraser University,Burnaby,BC,Canada,V5A 1S6"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University,Burnaby,BC,Canada,V5A 1S6","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044446295","display_name":"Xilun Zhang","orcid":"https://orcid.org/0000-0001-5351-3115"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xilun Zhang","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045948472","display_name":"Xubo Lyu","orcid":"https://orcid.org/0000-0003-2110-9075"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xubo Lyu","raw_affiliation_strings":["Simon Fraser University,Burnaby,BC,Canada,V5A 1S6"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University,Burnaby,BC,Canada,V5A 1S6","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100387253","display_name":"Mo Chen","orcid":"https://orcid.org/0000-0003-1841-7608"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mo Chen","raw_affiliation_strings":["Simon Fraser University,Burnaby,BC,Canada,V5A 1S6"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University,Burnaby,BC,Canada,V5A 1S6","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034239627"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35085951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2304","last_page":"2310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9244999885559082,"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"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9244999885559082,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9126999974250793,"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/reachability","display_name":"Reachability","score":0.8390698432922363},{"id":"https://openalex.org/keywords/hamilton\u2013jacobi-equation","display_name":"Hamilton\u2013Jacobi equation","score":0.7369718551635742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5288439989089966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49354827404022217},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3294256329536438},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3261869549751282},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24029967188835144},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.22613462805747986},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.15305453538894653}],"concepts":[{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.8390698432922363},{"id":"https://openalex.org/C2778860007","wikidata":"https://www.wikidata.org/wiki/Q1060137","display_name":"Hamilton\u2013Jacobi equation","level":2,"score":0.7369718551635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5288439989089966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49354827404022217},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3294256329536438},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3261869549751282},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24029967188835144},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22613462805747986},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.15305453538894653},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1003609772","https://openalex.org/W1968315580","https://openalex.org/W1975236902","https://openalex.org/W2009318488","https://openalex.org/W2105078254","https://openalex.org/W2109640889","https://openalex.org/W2110073061","https://openalex.org/W2113350382","https://openalex.org/W2173261491","https://openalex.org/W2209913494","https://openalex.org/W2492629073","https://openalex.org/W2749408143","https://openalex.org/W2807455070","https://openalex.org/W2967292964","https://openalex.org/W2968547875","https://openalex.org/W3003669699","https://openalex.org/W3131822805","https://openalex.org/W3195968524","https://openalex.org/W3206190169","https://openalex.org/W4200438872","https://openalex.org/W4231979851","https://openalex.org/W4285603252","https://openalex.org/W4293370597","https://openalex.org/W4389961034","https://openalex.org/W4391022103","https://openalex.org/W4399205818","https://openalex.org/W4401415792","https://openalex.org/W4401807714","https://openalex.org/W4406736214"],"related_works":["https://openalex.org/W2127267268","https://openalex.org/W2136512912","https://openalex.org/W2067910792","https://openalex.org/W2156446763","https://openalex.org/W2143461633","https://openalex.org/W2150194458","https://openalex.org/W4321471459","https://openalex.org/W2889071233","https://openalex.org/W2380814829","https://openalex.org/W2387511021"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"has":[4],"shown":[5],"remarkable":[6],"success":[7],"in":[8,94,107],"robotics":[9],"with":[10,43,118,131],"complex":[11],"and":[12,21,97,100],"heterogeneous":[13],"dynamics.":[14],"However,":[15],"its":[16,85],"vulnerability":[17],"to":[18,47],"unknown":[19],"disturbances":[20,76],"adversarial":[22,44,66],"attacks":[23],"remains":[24],"a":[25,33,60,91,101],"significant":[26],"challenge.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,70],"propose":[32],"robust":[34,81],"policy":[35,126],"training":[36,46],"framework":[37],"that":[38,111],"integrates":[39],"model-based":[40],"control":[41],"principles":[42],"RL":[45,67],"improve":[48],"robustness":[49],"without":[50],"the":[51,80,119,125],"need":[52],"for":[53,65],"external":[54],"black-box":[55],"adversaries.":[56],"Our":[57],"approach":[58],"introduces":[59],"novel":[61],"Hamilton-Jacobi":[62],"reachability-guided":[63],"disturbance":[64],"training,":[68],"where":[69],"use":[71],"interpretable":[72],"worst-case":[73],"or":[74],"near-worst-case":[75],"as":[77],"adversaries":[78],"against":[79],"policy.":[82],"We":[83,109],"evaluated":[84],"effectiveness":[86],"across":[87],"three":[88],"distinct":[89],"tasks:":[90],"reach-avoid":[92],"game":[93],"both":[95],"simulation":[96],"real-world":[98],"settings,":[99],"highly":[102],"dynamic":[103],"quadrotor":[104],"stabilization":[105],"task":[106],"simulation.":[108],"validate":[110],"our":[112],"learned":[113],"critic":[114],"network":[115,127],"is":[116],"consistent":[117],"ground-truth":[120],"HJ":[121],"value":[122],"function,":[123],"while":[124],"shows":[128],"comparable":[129],"performance":[130],"other":[132],"learning-based":[133],"methods.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}