{"id":"https://openalex.org/W7125943667","doi":"https://doi.org/10.1109/smc58881.2025.11343465","title":"An Improved Reinforcement Learning-Based UAV Obstacle Avoidance Framework Using PPO-CMA","display_name":"An Improved Reinforcement Learning-Based UAV Obstacle Avoidance Framework Using PPO-CMA","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125943667","doi":"https://doi.org/10.1109/smc58881.2025.11343465"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343465","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 Systems, Man, and Cybernetics (SMC)","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/A5124094143","display_name":"Yuqi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuqi Chen","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041700152","display_name":"Junjie Gao","orcid":"https://orcid.org/0000-0001-7087-0886"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junjie Gao","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020778730","display_name":"Yaosheng Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yaosheng Deng","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124061438","display_name":"Mir Feroskhan","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mir Feroskhan","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"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":"5845","last_page":"5850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.8030999898910522,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.8030999898910522,"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/T11133","display_name":"UAV Applications and Optimization","score":0.05889999866485596,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.031199999153614044,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.8436999917030334},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7732999920845032},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6425999999046326},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5781999826431274},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5544999837875366},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5394999980926514},{"id":"https://openalex.org/keywords/cma-es","display_name":"CMA-ES","score":0.5347999930381775},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5339000225067139}],"concepts":[{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.8436999917030334},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7732999920845032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779000163078308},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5781999826431274},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.5347999930381775},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205999970436096},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.3637000024318695},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.25200000405311584},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343465","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 Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1786686177","https://openalex.org/W2112036188","https://openalex.org/W2128990851","https://openalex.org/W2129711966","https://openalex.org/W2329739548","https://openalex.org/W2767999517","https://openalex.org/W3094027362","https://openalex.org/W3104753760","https://openalex.org/W3114626444","https://openalex.org/W3124192137","https://openalex.org/W3159045549","https://openalex.org/W4313270348","https://openalex.org/W4323645819","https://openalex.org/W4388838093","https://openalex.org/W4390871512","https://openalex.org/W4391407237","https://openalex.org/W4400410971","https://openalex.org/W4413925210"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,13,82,137,161],"widespread":[4],"adoption":[5],"of":[6,167],"unmanned":[7],"aerial":[8],"vehicles":[9],"(UAVs)":[10],"has":[11],"increased":[12],"demand":[14],"for":[15,34,55,97,169],"advanced":[16],"obstacle":[17,154],"avoidance":[18],"capabilities.":[19],"Traditional":[20],"path":[21,100],"planning":[22,174],"algorithms":[23],"often":[24],"exhibit":[25],"low":[26],"efficiency":[27],"and":[28,60,91,108,128,153,164,172],"poor":[29],"adaptability,":[30],"making":[31],"them":[32],"unsuitable":[33],"dynamic":[35],"environments.":[36],"To":[37,75],"address":[38],"these":[39],"limitations,":[40],"researchers":[41],"have":[42],"explored":[43],"reinforcement":[44],"learning":[45,129],"(RL)-based":[46],"approaches,":[47],"with":[48,120],"Proximal":[49],"Policy":[50],"Optimization":[51],"(PPO)":[52],"widely":[53],"used":[54],"its":[56,72],"stable":[57],"policy":[58,122],"updates":[59],"improved":[61],"sample":[62],"efficiency.":[63,130],"However,":[64],"PPO":[65,90,121,148],"suffers":[66],"from":[67],"slow":[68],"convergence,":[69],"which":[70],"limits":[71],"real-time":[73],"applicability.":[74],"overcome":[76],"this":[77,79],"issue,":[78],"paper":[80],"integrates":[81],"Covariance":[83],"Matrix":[84],"Adaptation":[85],"Evolution":[86],"Strategy":[87],"(CMA-ES)":[88],"into":[89],"proposes":[92],"PPO-CMA,":[93],"an":[94],"enhanced":[95],"algorithm":[96],"end-to-end":[98],"UAV":[99,109,170],"planning.":[101],"The":[102,131,156],"PPO-CMA":[103,168],"network,":[104],"leveraging":[105],"depth":[106],"images":[107],"pose":[110],"feedback,":[111],"generates":[112],"continuous":[113],"control":[114],"actions,":[115],"combining":[116],"CMA-ES":[117],"adaptive":[118],"search":[119],"optimization":[123],"to":[124,146],"improve":[125],"convergence":[126,144],"speed":[127],"proposed":[132],"method":[133],"is":[134],"evaluated":[135],"in":[136,175],"VisFly":[138],"simulation":[139],"environment,":[140],"demonstrating":[141],"significantly":[142],"faster":[143],"compared":[145],"traditional":[147],"while":[149],"ensuring":[150],"accurate":[151],"target-reaching":[152],"avoidance.":[155],"real-world":[157,176],"experimental":[158],"results":[159],"validate":[160],"effectiveness,":[162],"robustness,":[163],"practical":[165],"applicability":[166],"navigation":[171],"motion":[173],"scenarios.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}