{"id":"https://openalex.org/W4413394597","doi":"https://doi.org/10.23919/acc63710.2025.11107899","title":"When to Localize? A Risk-Constrained Reinforcement Learning Approach","display_name":"When to Localize? A Risk-Constrained Reinforcement Learning Approach","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413394597","doi":"https://doi.org/10.23919/acc63710.2025.11107899"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107899","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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/A5006805271","display_name":"Chak Lam Shek","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chak Lam Shek","raw_affiliation_strings":["University of Maryland,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114657810","display_name":"Kasra Torshizi","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kasra Torshizi","raw_affiliation_strings":["University of Maryland,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082620396","display_name":"Troi Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Troi Williams","raw_affiliation_strings":["University of Maryland,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086188394","display_name":"Pratap Tokekar","orcid":"https://orcid.org/0000-0002-3715-0382"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratap Tokekar","raw_affiliation_strings":["University of Maryland,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006805271"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12476849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.11460000276565552,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.11460000276565552,"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":0.7641838788986206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6734410524368286},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49097898602485657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44757771492004395},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15158343315124512},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07775288820266724}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7641838788986206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734410524368286},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49097898602485657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44757771492004395},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15158343315124512},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07775288820266724}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107899","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.41999998688697815,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1823979212","https://openalex.org/W1982447260","https://openalex.org/W2005647881","https://openalex.org/W2064675550","https://openalex.org/W2113117178","https://openalex.org/W2131655609","https://openalex.org/W2299529128","https://openalex.org/W2769509614","https://openalex.org/W2965621489","https://openalex.org/W2991391803","https://openalex.org/W2993826828","https://openalex.org/W3003697734","https://openalex.org/W3047297564","https://openalex.org/W3108159143","https://openalex.org/W4200140111","https://openalex.org/W4323645916","https://openalex.org/W4327662982","https://openalex.org/W4389665555","https://openalex.org/W4391529055","https://openalex.org/W4404953369"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"In":[0],"robotic":[1],"navigation,":[2],"continuous":[3],"localization":[4,92,96],"can":[5],"be":[6],"inefficient":[7],"in":[8,153,156],"certain":[9],"scenarios,":[10,71],"such":[11,33,70],"as":[12,34],"underwater":[13,18],"searches.":[14],"For":[15],"example,":[16],"an":[17,77],"agent":[19,46,78],"surfacing":[20],"to":[21,52,57,75,81,89],"localize":[22],"too":[23],"often":[24],"hinders":[25],"it":[26,49],"from":[27,37],"searching":[28],"for":[29,138],"critical":[30],"items":[31,55],"underwater,":[32],"black":[35],"boxes":[36],"crashed":[38],"aircraft.":[39],"On":[40],"the":[41,45,54,60,136],"other":[42],"hand,":[43],"if":[44],"never":[47],"localizes,":[48],"may":[50],"fail":[51],"find":[53],"due":[56],"inadvertently":[58],"leaving":[59],"search":[61],"area":[62],"or":[63],"entering":[64],"hazardous,":[65],"restricted":[66],"areas.":[67],"Motivated":[68],"by":[69,130],"we":[72],"explore":[73],"approaches":[74],"help":[76],"determine":[79,90],"\"when":[80],"localize?\".":[82],"We":[83],"propose":[84],"a":[85,105,109,117,150],"bi-criteria":[86],"optimization":[87],"approach":[88,124],"optimal":[91],"timing,":[93],"which":[94,115],"balances":[95],"frequency":[97],"with":[98],"failure":[99],"probability.":[100],"Our":[101],"method,":[102],"RiskRL,":[103],"employs":[104],"Particle":[106],"Filter":[107],"and":[108,134,141],"constrained":[110],"Reinforcement":[111],"Learning":[112],"(RL)":[113],"framework,":[114],"uses":[116],"recurrent":[118],"Soft":[119],"Actor-Critic":[120],"(SAC)":[121],"network.":[122],"This":[123],"improves":[125],"our":[126,160],"previous":[127],"POMDP-based":[128],"solution":[129],"reducing":[131],"computational":[132],"complexity":[133],"eliminating":[135],"need":[137],"complete":[139],"transition":[140],"observation":[142],"models.":[143],"Experimental":[144],"results":[145],"demonstrate":[146],"that":[147],"RiskRL":[148],"showed":[149],"26%":[151],"increase":[152],"success":[154],"rates":[155],"unseen":[157],"environments":[158],"over":[159],"baselines.":[161],"The":[162],"implementation":[163],"is":[164],"available":[165],"on":[166],"GitHub:":[167],"https://github.com/raaslab/when-to-localize-riskrl":[168]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}