{"id":"https://openalex.org/W4391308089","doi":"https://doi.org/10.1109/smc53992.2023.10394052","title":"EPO-S: A Constrained RL Method to Enhance UAV Safety with Spatial Representation","display_name":"EPO-S: A Constrained RL Method to Enhance UAV Safety with Spatial Representation","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391308089","doi":"https://doi.org/10.1109/smc53992.2023.10394052"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10394052","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5100629869","display_name":"Qin Zhang","orcid":"https://orcid.org/0000-0003-1214-9657"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045272072","display_name":"Linrui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linrui Zhang","raw_affiliation_strings":["Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112333633","display_name":"Zaihui Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaihui Yang","raw_affiliation_strings":["Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034166666","display_name":"Haoyu Wang","orcid":"https://orcid.org/0009-0000-9167-2459"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737125","display_name":"Xueqian Wang","orcid":"https://orcid.org/0000-0003-3542-0593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Wang","raw_affiliation_strings":["Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026500154","display_name":"Yongzhe Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongzhe Chang","raw_affiliation_strings":["Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100629869"],"corresponding_institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19705965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":null,"first_page":"3835","last_page":"3841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998000264167786,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7747024297714233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7508301138877869},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.6411819458007812},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6097881197929382},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5916163325309753},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.555499255657196},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5408182144165039},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5140582323074341},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4534483253955841},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4507281482219696},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.406418114900589},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3254474997520447},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3239113986492157},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.29763263463974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28709495067596436},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.24949511885643005},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.16402104496955872},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13455164432525635},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1321958601474762},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10163488984107971}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7747024297714233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508301138877869},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.6411819458007812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6097881197929382},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5916163325309753},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.555499255657196},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5408182144165039},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5140582323074341},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4534483253955841},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4507281482219696},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.406418114900589},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3254474997520447},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3239113986492157},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.29763263463974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28709495067596436},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.24949511885643005},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.16402104496955872},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13455164432525635},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1321958601474762},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10163488984107971},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10394052","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2005073772","https://openalex.org/W2074464158","https://openalex.org/W2343616166","https://openalex.org/W2347603147","https://openalex.org/W2462906003","https://openalex.org/W2540486912","https://openalex.org/W2736057540","https://openalex.org/W2784465508","https://openalex.org/W2792734461","https://openalex.org/W2962890638","https://openalex.org/W2996195849","https://openalex.org/W3094224934","https://openalex.org/W3150718622","https://openalex.org/W3151306683","https://openalex.org/W3162902207","https://openalex.org/W3164473225","https://openalex.org/W3179181747","https://openalex.org/W4206497039","https://openalex.org/W4214717370","https://openalex.org/W4285600796","https://openalex.org/W4293370597","https://openalex.org/W4313196885","https://openalex.org/W4385447794","https://openalex.org/W6687063787","https://openalex.org/W6718836005","https://openalex.org/W6729062945","https://openalex.org/W6737893269","https://openalex.org/W6747790125","https://openalex.org/W6747984218","https://openalex.org/W6748839928","https://openalex.org/W6785187516","https://openalex.org/W6795857475","https://openalex.org/W6800776581"],"related_works":["https://openalex.org/W2889566344","https://openalex.org/W2742483371","https://openalex.org/W4381746183","https://openalex.org/W2359600231","https://openalex.org/W2380019117","https://openalex.org/W3138952546","https://openalex.org/W1987886368","https://openalex.org/W1660309994","https://openalex.org/W2369187583","https://openalex.org/W3197207153"],"abstract_inverted_index":{"Path":[0],"planning":[1,113],"and":[2,58,76,114,140,182],"collision":[3,115],"avoidance":[4,116],"are":[5],"critical":[6],"components":[7],"of":[8,179,205],"UAV":[9,19,80,138,164],"control":[10,28,44],"algorithms":[11],"that":[12,46],"play":[13],"a":[14,83,93,119,156,191,199],"crucial":[15],"role":[16],"in":[17,78,118,136,187,194,202],"executing":[18],"missions.":[20],"As":[21],"scenarios":[22],"become":[23],"increasingly":[24],"complex,":[25],"the":[26,36,111,124,137,163,177,180,203,207],"traditional":[27,56],"methods":[29,57],"just":[30],"ain't":[31],"cutting":[32],"it":[33],"to":[34,48,55,69,92,97,104,148,166],"meet":[35],"requirements.":[37],"Reinforcement":[38],"learning":[39],"is":[40],"an":[41,53,142],"emerging":[42],"decision-making":[43],"algorithm":[45,147],"attempts":[47],"address":[49,105],"these":[50,86],"issues":[51],"as":[52,196,198],"alternative":[54],"has":[59],"made":[60],"significant":[61,192],"advances.":[62],"Unfortunately,":[63],"standard":[64],"RL":[65,121],"approaches":[66],"only":[67],"aim":[68],"maximize":[70],"rewards,":[71],"however":[72],"balancing":[73],"task":[74],"performance":[75],"safety":[77],"completing":[79],"tasks":[81],"poses":[82],"challenge":[84],"since":[85],"two":[87],"objectives":[88],"sometimes":[89],"conflict,":[90],"leading":[91],"trade-off":[94],"often":[95],"difficult":[96],"manage.":[98],"This":[99],"paper":[100],"proposes":[101],"three":[102],"techniques":[103],"this":[106,188],"problem.":[107],"First,":[108],"we":[109,131],"model":[110],"path":[112],"issue":[117],"constrained":[120],"framework,":[122],"eliminating":[123],"need":[125],"for":[126,162],"complex":[127],"reward":[128],"engineering.":[129],"Second,":[130],"expand":[132],"our":[133],"previous":[134],"work":[135],"setting":[139],"introduce":[141],"exact":[143],"penalty":[144],"optimization":[145],"(EPO)":[146],"provide":[149],"stricter":[150],"constraint":[151],"guarantees.":[152],"We":[153],"also":[154],"propose":[155],"novel":[157],"spatial":[158,183],"information":[159],"representation":[160,184],"method":[161],"scenario":[165],"help":[167],"UAVs":[168],"better":[169],"understand":[170],"environmental":[171],"information.":[172],"The":[173],"experimental":[174],"results":[175],"demonstrate":[176],"effectiveness":[178],"EPO":[181],"modules":[185],"proposed":[186],"paper,":[189],"through":[190],"reduction":[193],"collisions":[195],"well":[197],"strong":[200],"improvement":[201],"rate":[204],"reaching":[206],"destination.":[208]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
