{"id":"https://openalex.org/W7140374213","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443777","title":"Safe Policy Learning in Online Reinforcement Learning Using Augmented PPO and CMDPs for Robot Navigation","display_name":"Safe Policy Learning in Online Reinforcement Learning Using Augmented PPO and CMDPs for Robot Navigation","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7140374213","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443777"},"language":null,"primary_location":{"id":"doi:10.1109/ieeeconf67917.2025.11443777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080516185","display_name":"Zhen Zhou","orcid":"https://orcid.org/0000-0003-0706-9089"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongna Zhou","raw_affiliation_strings":["University of Missouri,Electrical Engineering and Computer Science Department,Columbia,MO,USA,65211"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Missouri,Electrical Engineering and Computer Science Department,Columbia,MO,USA,65211","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130707252","display_name":"K.C. Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K.C. Ho","raw_affiliation_strings":["University of Missouri,Electrical Engineering and Computer Science Department,Columbia,MO,USA,65211"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Missouri,Electrical Engineering and Computer Science Department,Columbia,MO,USA,65211","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101729122","display_name":"Z. Sun","orcid":"https://orcid.org/0000-0002-0770-732X"},"institutions":[{"id":"https://openalex.org/I151328261","display_name":"Hampton University","ror":"https://ror.org/05fde5z47","country_code":"US","type":"education","lineage":["https://openalex.org/I151328261"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao Sun","raw_affiliation_strings":["Hampton University,Electrical and Computer Engineering Department,Hampton,VA,USA,23669"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hampton University,Electrical and Computer Engineering Department,Hampton,VA,USA,23669","institution_ids":["https://openalex.org/I151328261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117852070","display_name":"Trevor Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I151328261","display_name":"Hampton University","ror":"https://ror.org/05fde5z47","country_code":"US","type":"education","lineage":["https://openalex.org/I151328261"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Tran","raw_affiliation_strings":["Hampton University,Electrical and Computer Engineering Department,Hampton,VA,USA,23669"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hampton University,Electrical and Computer Engineering Department,Hampton,VA,USA,23669","institution_ids":["https://openalex.org/I151328261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1408","last_page":"1412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.880299985408783,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.880299985408783,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0210999995470047,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.008700000122189522,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.5708000063896179},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5088000297546387},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.43230000138282776},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33000001311302185},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3133000135421753},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3100999891757965},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.30079999566078186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5879999995231628},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.43230000138282776},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3165999948978424},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf67917.2025.11443777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2968945909","https://openalex.org/W3112335585","https://openalex.org/W4321020553","https://openalex.org/W4392705148","https://openalex.org/W4409347226","https://openalex.org/W4416750477"],"related_works":[],"abstract_inverted_index":{"We":[0,33],"study":[1],"online":[2],"reinforcement":[3],"learning":[4],"(RL)":[5],"with":[6,17],"environmental":[7],"safety":[8,31],"constraints":[9],"for":[10,52],"a":[11,15,38,65,71],"mobile":[12],"robot":[13],"navigating":[14],"maze":[16],"obstacles":[18],"and":[19,44],"unsafe":[20],"zones,":[21],"where":[22],"the":[23,35,46,62,77],"agent":[24],"must":[25],"maximize":[26],"task":[27],"return":[28],"while":[29,89],"respecting":[30],"budgets.":[32],"model":[34],"problem":[36],"as":[37],"Constrained":[39],"Markov":[40],"Decision":[41],"Process":[42],"(CMDP)":[43],"propose":[45],"Augmented":[47],"Proximal":[48],"Policy":[49],"Optimization":[50],"(APPO)":[51],"policy":[53],"updates.":[54],"A":[55],"variational":[56],"autoencoder":[57],"(VAE)":[58],"estimates":[59],"from":[60],"data":[61],"probability":[63],"that":[64,81],"location":[66],"is":[67],"unsafe,":[68],"which":[69],"yields":[70],"calibrated":[72],"cost":[73],"signal":[74],"to":[75],"regularize":[76],"reward.":[78],"Experiments":[79],"indicate":[80],"APPO":[82],"enables":[83],"reliable":[84],"navigation":[85],"within":[86],"safety-constrained":[87],"regions":[88],"maintaining":[90],"competitive":[91],"returns.":[92]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-27T00:00:00"}