Multi-UAV Autonomous Obstacle Avoidance Based on Reinforcement Learning

Obstacle avoidance is a necessary behaviour to ensure the safety of UAV. In this paper, aiming at the problem of autonomous learning and obstacle avoidance of multiple UAVs in the multi-obstacle map environment, an obstacle avoidance method of UAVs based on an improved reward deep Q learning network...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Chinese Control Conference s. 8657 - 8661
Hlavní autoři: Li, Zheng, Li, Jinna, Wang, Yanhui
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: Technical Committee on Control Theory, Chinese Association of Automation 24.07.2023
Témata:
ISSN:1934-1768
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Obstacle avoidance is a necessary behaviour to ensure the safety of UAV. In this paper, aiming at the problem of autonomous learning and obstacle avoidance of multiple UAVs in the multi-obstacle map environment, an obstacle avoidance method of UAVs based on an improved reward deep Q learning network is proposed. According to the dynamics model of UAV, the three-dimensional dynamic equation is established, and the combination of pitch angle and heading angle constructs the action space of UAV. a new reward evaluation method, which adaptively adjusts the weight of the reward according to the distance between the UAV and the obstacle, is developed thus improving the performance of the UAV. Thus, the obstacle avoidance performance of multiple UAVs in unknown environment can be effectively improved. Finally, by comparing the traditional deep Q learning network, the simulation results show that the algorithm in this paper is reasonable, and UAVs can successfully achieve obstacle avoidance in unknown environment.
AbstractList Obstacle avoidance is a necessary behaviour to ensure the safety of UAV. In this paper, aiming at the problem of autonomous learning and obstacle avoidance of multiple UAVs in the multi-obstacle map environment, an obstacle avoidance method of UAVs based on an improved reward deep Q learning network is proposed. According to the dynamics model of UAV, the three-dimensional dynamic equation is established, and the combination of pitch angle and heading angle constructs the action space of UAV. a new reward evaluation method, which adaptively adjusts the weight of the reward according to the distance between the UAV and the obstacle, is developed thus improving the performance of the UAV. Thus, the obstacle avoidance performance of multiple UAVs in unknown environment can be effectively improved. Finally, by comparing the traditional deep Q learning network, the simulation results show that the algorithm in this paper is reasonable, and UAVs can successfully achieve obstacle avoidance in unknown environment.
Author Li, Jinna
Li, Zheng
Wang, Yanhui
Author_xml – sequence: 1
  givenname: Zheng
  surname: Li
  fullname: Li, Zheng
  email: 386184452@qq.com
  organization: Liaoning Petrochemical University,Fushun,Liaoning,113001
– sequence: 2
  givenname: Jinna
  surname: Li
  fullname: Li, Jinna
  email: lijinna_721@126.comn
  organization: Liaoning Petrochemical University,Fushun,Liaoning,113001
– sequence: 3
  givenname: Yanhui
  surname: Wang
  fullname: Wang, Yanhui
  email: wangyanhui@lnpu.edu.cn
  organization: Liaoning Petrochemical University,Fushun,Liaoning,113001
BookMark eNo1j91KwzAYQKMouM29gWBeoDNf0_x8l7W4KVQG4rwdafZFIlsibSf49g7Uq3N3OGfKLlJOxNgtiEUpEfCuaRplNZpFKUq5AFFWwpjyjM3RWLTWKAuqkudsAiirAoy2V2w6DB9CaIEgJ2z1fNyPsdjUb7w-jjnlQz4OfN0No_N74vVXjjuXPPF7N9CO58RfKKaQe08HSiNvyfUppvdrdhncfqD5H2dss3x4bR6Ldr16auq2iAA4Fgq70oWuQ_RGIQjlTkkGDHpJRkKoCJzvtBOKtAMVrAxaBy9sJUR3OpEzdvPrjUS0_ezjwfXf2_9x-QN5-E5t
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.23919/CCC58697.2023.10240772
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9789887581543
9887581542
EISSN 1934-1768
EndPage 8661
ExternalDocumentID 10240772
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62073158
  funderid: 10.13039/501100001809
GroupedDBID 29B
6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i119t-59b2afbb99c759105a7687179c3e731f4e1acb6a05e6a15f83f66fc08400b5433
IEDL.DBID RIE
IngestDate Wed Aug 27 02:47:22 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i119t-59b2afbb99c759105a7687179c3e731f4e1acb6a05e6a15f83f66fc08400b5433
PageCount 5
ParticipantIDs ieee_primary_10240772
PublicationCentury 2000
PublicationDate 2023-July-24
PublicationDateYYYYMMDD 2023-07-24
PublicationDate_xml – month: 07
  year: 2023
  text: 2023-July-24
  day: 24
PublicationDecade 2020
PublicationTitle Chinese Control Conference
PublicationTitleAbbrev CCC
PublicationYear 2023
Publisher Technical Committee on Control Theory, Chinese Association of Automation
Publisher_xml – name: Technical Committee on Control Theory, Chinese Association of Automation
SSID ssj0060913
Score 2.2262294
Snippet Obstacle avoidance is a necessary behaviour to ensure the safety of UAV. In this paper, aiming at the problem of autonomous learning and obstacle avoidance of...
SourceID ieee
SourceType Publisher
StartPage 8657
SubjectTerms Adaptation models
Autonomous aerial vehicles
Decision making
DQN
Improved reward evaluation strategy
Multi-UAV obstacle avoidance algorithm
Neural networks
Q-learning
Simulation
Solid modeling
Title Multi-UAV Autonomous Obstacle Avoidance Based on Reinforcement Learning
URI https://ieeexplore.ieee.org/document/10240772
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV27TsMwFLWgYoCFVxFveWB1iePYjscQURhQqRCtulW2c426JKik_X5st-UxMLBFkaJIx497z7XPuQjdJLmljoXyUmYd8XzDEJ-GWJJxy8C5PNXRUmj8JAeDfDJRw7VYPWphACBePoNeeIxn-VVjF6FU5ld44B_S77jbUoqVWGuz7YpgcLm6wJUyRdVtWZY8F0r2QoPw3ubTX01UYgzp7__z7weo-63Gw8OvOHOItqA-Qns_jASP0UPU0ZJRMcbFog06BU_o8bPxqZ-fFrhYNrMqDC--80Grwk2NXyBaptpYHcRrl9W3Lhr171_LR7JukUBmlKqWcGVS7Yzx8EruIz_Xnj54hqY80pJRlwHV1gidcBCacpczJ4Sziad1ieEZYyeoUzc1nCLMBROQV6zSYIKjjQKpNEsro0KSJuAMdQMm0_eVC8Z0A8f5H-8v0G5APtRB0-wSddr5Aq7Qjl22s4_5dRy7T8XemVE
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZQQQIWXkW88cDqksSxE48lohRRSoXaqltlO2fUJUEl7e_HdlMeAwObFcmKdBff3Xfx9x1CN0GqQ0NdeynWhli8oYgtQzSJmaZgTBpJLyk07iX9fjqZiEFNVvdcGADwl8-g5Zb-X35e6oVrldkT7vBHYiPuphudVdO11oGXO4nL1RWuiIpQ3GZZxlIukpYbEd5ab_41RsVnkc7eP9-_j5rffDw8-Mo0B2gDikO0-0NK8Ag9eCYtGbXHuL2oHFPBQnr8omzxZz8M3F6Ws9w5GN_ZtJXjssCv4EVTte8P4lpn9a2JRp37YdYl9ZAEMgtDUREmVCSNUtbACbO5n0kLICxGE9bWCQ1NDKHUisuAAZchMyk1nBsdWGAXKBZTeowaRVnACcKMUw5pTnMJymnaCEiEpFGuhCvTOJyiprPJ9H2lgzFdm-Psj-fXaLs7fO5Ne4_9p3O047zguqJRfIEa1XwBl2hLL6vZx_zK-_ET9Secmg
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Chinese+Control+Conference&rft.atitle=Multi-UAV+Autonomous+Obstacle+Avoidance+Based+on+Reinforcement+Learning&rft.au=Li%2C+Zheng&rft.au=Li%2C+Jinna&rft.au=Wang%2C+Yanhui&rft.date=2023-07-24&rft.pub=Technical+Committee+on+Control+Theory%2C+Chinese+Association+of+Automation&rft.eissn=1934-1768&rft.spage=8657&rft.epage=8661&rft_id=info:doi/10.23919%2FCCC58697.2023.10240772&rft.externalDocID=10240772