{"id":"https://openalex.org/W4416750959","doi":"https://doi.org/10.1109/iros60139.2025.11247653","title":"A Safety-Adjusted Policy Optimization Algorithm and Application for Obstacle Avoidance in the Quadcopter","display_name":"A Safety-Adjusted Policy Optimization Algorithm and Application for Obstacle Avoidance in the Quadcopter","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750959","doi":"https://doi.org/10.1109/iros60139.2025.11247653"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5103237673","display_name":"Gang Xia","orcid":"https://orcid.org/0000-0002-5177-1054"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Xia","raw_affiliation_strings":["Sichuan University,College of Electronics and Information Engineering,Chengdu,China,610065"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Electronics and Information Engineering,Chengdu,China,610065","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108711802","display_name":"Xinsong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsong Yang","raw_affiliation_strings":["Sichuan University,College of Electronics and Information Engineering,Chengdu,China,610065"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Electronics and Information Engineering,Chengdu,China,610065","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058603562","display_name":"Qihan Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihan Qi","raw_affiliation_strings":["Sichuan University,College of Electronics and Information Engineering,Chengdu,China,610065"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Electronics and Information Engineering,Chengdu,China,610065","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035171257","display_name":"Yaping Sun","orcid":"https://orcid.org/0000-0002-8733-2467"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaping Sun","raw_affiliation_strings":["Sichuan University,College of Electronics and Information Engineering,Chengdu,China,610065"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Electronics and Information Engineering,Chengdu,China,610065","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078316510","display_name":"Xiwang Dong","orcid":"https://orcid.org/0000-0002-4778-248X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiwang Dong","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University,Beijing,China,100191"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103237673"],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44009858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2360","last_page":"2367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11489","display_name":"Air Traffic Management and Optimization","score":0.25200000405311584,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11489","display_name":"Air Traffic Management and Optimization","score":0.25200000405311584,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.13840000331401825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.11429999768733978,"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/quadcopter","display_name":"Quadcopter","score":0.8701000213623047},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5511999726295471},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5497999787330627},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.548799991607666},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4433000087738037},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42289999127388},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4169999957084656},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4153999984264374}],"concepts":[{"id":"https://openalex.org/C2779199153","wikidata":"https://www.wikidata.org/wiki/Q43965","display_name":"Quadcopter","level":2,"score":0.8701000213623047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377000212669373},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5511999726295471},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313620","display_name":"Hubei Provincial Department of Education","ror":"https://ror.org/05yaa9j15"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2600080636","https://openalex.org/W2902907165","https://openalex.org/W2951360122","https://openalex.org/W2963293747","https://openalex.org/W2990747716","https://openalex.org/W2998619042","https://openalex.org/W3010256639","https://openalex.org/W3091691175","https://openalex.org/W3134645133","https://openalex.org/W3150718622","https://openalex.org/W3185083385","https://openalex.org/W3186708588","https://openalex.org/W3207657697","https://openalex.org/W4206497039","https://openalex.org/W4285600796","https://openalex.org/W4391019623","https://openalex.org/W4402262118","https://openalex.org/W4402402057"],"related_works":[],"abstract_inverted_index":{"Ensuring":[0],"the":[1,49,57,103,107,122,133,138,149,174,177,183,188],"safety":[2,52,87,110],"of":[3,60,151,176],"various":[4],"real-world":[5],"applications":[6],"based":[7],"on":[8,154,185],"reinforcement":[9],"learning":[10],"(RL),":[11],"such":[12],"as":[13],"quadcopter":[14],"control,":[15],"robotic":[16],"manipulators,":[17],"and":[18,53,111,126,199],"autonomous":[19],"robots,":[20],"remains":[21],"a":[22,44,69,81,94,100,127,142],"critical":[23],"challenge,":[24],"despite":[25],"RL\u2019s":[26],"remarkable":[27],"success":[28],"in":[29,39,90,117,132],"solving":[30],"complex":[31],"decision-making":[32],"tasks.":[33],"Existing":[34],"on-policy":[35,71],"Lagrangian":[36],"optimization":[37],"methods":[38],"safe":[40,202],"RL":[41,157,203],"typically":[42],"use":[43],"single":[45],"policy":[46,96],"to":[47,85,97,114,136,147,162,193],"balance":[48],"trade-off":[50,108],"between":[51,109],"return":[54],"without":[55,166],"taking":[56],"potential":[58],"benefits":[59],"adopting":[61],"multiple":[62],"policies":[63],"into":[64],"account.":[65],"In":[66,140],"this":[67],"paper,":[68],"new":[70],"method":[72],"is":[73,80,145,191],"proposed,":[74],"named":[75],"Safe-Adjusted":[76],"Policy":[77],"Optimization(SAPO),":[78],"which":[79],"dual-policy":[82],"framework":[83],"designed":[84,146,178],"address":[86],"constraint":[88],"violations":[89],"RL.":[91],"By":[92],"incorporating":[93],"cost-oriented":[95],"dynamically":[98],"adjust":[99],"reward-oriented":[101],"policy,":[102],"SAPO":[104],"effectively":[105],"resolves":[106],"return.":[112],"Moreover,":[113],"enhance":[115],"performance":[116,197],"carrying":[118],"out":[119],"high-dimensional":[120],"tasks,":[121],"Kullback-Leibler":[123],"(KL)":[124],"divergence":[125],"Gaussian":[128],"kernel":[129],"are":[130],"employed":[131],"distance":[134],"functions":[135],"facilitate":[137],"training.":[139],"addition,":[141],"quadcopter-safe-navigation":[143,155],"task":[144],"overcome":[148],"drawback":[150],"previous":[152],"research":[153],"with":[156],"that":[158],"only":[159],"pays":[160],"attention":[161],"reward":[163],"function":[164],"design":[165],"considering":[167],"policy-level":[168],"optimization.":[169],"Finally,":[170],"experimental":[171],"results":[172],"verify":[173],"feasibility":[175],"task.":[179],"Meanwhile,":[180],"indicated":[181],"by":[182],"test":[184],"real":[186],"device,":[187],"proposed":[189],"algorithm":[190],"easy":[192],"be":[194],"implemented,":[195],"offers":[196],"guarantees,":[198],"outperforms":[200],"existing":[201],"baselines.":[204]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}