Zobrazit v EDS

Unmanned Aerial Vehicle Path Planning in Complex Dynamic Environments Based on Deep Reinforcement Learning

Uloženo v:
Podrobná bibliografie
Název: Unmanned Aerial Vehicle Path Planning in Complex Dynamic Environments Based on Deep Reinforcement Learning
Autoři: Jiandong Liu, Wei Luo, Guoqing Zhang, Ruihao Li
Zdroj: Machines ; Volume 13 ; Issue 2 ; Pages: 162
Informace o vydavateli: Multidisciplinary Digital Publishing Institute
Rok vydání: 2025
Sbírka: MDPI Open Access Publishing
Témata: UAV obstacle avoidance, artificial potential field, dynamic environment, DQN algorithm, Yolov8
Popis: In this paper, an enhanced deep reinforcement learning approach is presented for unmanned aerial vehicles (UAVs) operating in dynamic and potentially hazardous environments. Initially, the capability to discern obstacles from visual data is achieved through the application of the Yolov8-StrongSort technique. Concurrently, a novel data storage system for deep Q-networks (DQN), named dynamic data memory (DDM), is introduced to hasten the learning process and convergence for UAVs. Furthermore, addressing the issue of UAVs’ paths veering too close to obstacles, a novel strategy employing an artificial potential field to adjust the reward function is introduced, which effectively guides the UAVs away from proximate obstacles. Rigorous simulation tests in an AirSim-based environment confirm the effectiveness of these methods. Compared to DQN, dueling DQN, M-DQN, improved Q-learning, DDM-DQN, EPF (enhanced potential field), APF-DQN, and L1-MBRL, our algorithm achieves the highest success rate of 77.67%, while also having the lowest average number of moving steps. Additionally, we conducted obstacle avoidance experiments with UAVs with different densities of obstacles. These tests highlight fast learning convergence and real-time obstacle detection and avoidance, ensuring successful achievement of the target.
Druh dokumentu: text
Popis souboru: application/pdf
Jazyk: English
Relation: Automation and Control Systems; https://dx.doi.org/10.3390/machines13020162
DOI: 10.3390/machines13020162
Dostupnost: https://doi.org/10.3390/machines13020162
Rights: https://creativecommons.org/licenses/by/4.0/
Přístupové číslo: edsbas.5BBA5E48
Databáze: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://doi.org/10.3390/machines13020162#
    Name: EDS - BASE (s4221598)
    Category: fullText
    Text: View record from BASE
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Liu%20J
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsbas
DbLabel: BASE
An: edsbas.5BBA5E48
RelevancyScore: 997
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 996.707214355469
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Unmanned Aerial Vehicle Path Planning in Complex Dynamic Environments Based on Deep Reinforcement Learning
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Jiandong+Liu%22">Jiandong Liu</searchLink><br /><searchLink fieldCode="AR" term="%22Wei+Luo%22">Wei Luo</searchLink><br /><searchLink fieldCode="AR" term="%22Guoqing+Zhang%22">Guoqing Zhang</searchLink><br /><searchLink fieldCode="AR" term="%22Ruihao+Li%22">Ruihao Li</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Machines ; Volume 13 ; Issue 2 ; Pages: 162
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Multidisciplinary Digital Publishing Institute
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: MDPI Open Access Publishing
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22UAV+obstacle+avoidance%22">UAV obstacle avoidance</searchLink><br /><searchLink fieldCode="DE" term="%22artificial+potential+field%22">artificial potential field</searchLink><br /><searchLink fieldCode="DE" term="%22dynamic+environment%22">dynamic environment</searchLink><br /><searchLink fieldCode="DE" term="%22DQN+algorithm%22">DQN algorithm</searchLink><br /><searchLink fieldCode="DE" term="%22Yolov8%22">Yolov8</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: In this paper, an enhanced deep reinforcement learning approach is presented for unmanned aerial vehicles (UAVs) operating in dynamic and potentially hazardous environments. Initially, the capability to discern obstacles from visual data is achieved through the application of the Yolov8-StrongSort technique. Concurrently, a novel data storage system for deep Q-networks (DQN), named dynamic data memory (DDM), is introduced to hasten the learning process and convergence for UAVs. Furthermore, addressing the issue of UAVs’ paths veering too close to obstacles, a novel strategy employing an artificial potential field to adjust the reward function is introduced, which effectively guides the UAVs away from proximate obstacles. Rigorous simulation tests in an AirSim-based environment confirm the effectiveness of these methods. Compared to DQN, dueling DQN, M-DQN, improved Q-learning, DDM-DQN, EPF (enhanced potential field), APF-DQN, and L1-MBRL, our algorithm achieves the highest success rate of 77.67%, while also having the lowest average number of moving steps. Additionally, we conducted obstacle avoidance experiments with UAVs with different densities of obstacles. These tests highlight fast learning convergence and real-time obstacle detection and avoidance, ensuring successful achievement of the target.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: text
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: application/pdf
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: Automation and Control Systems; https://dx.doi.org/10.3390/machines13020162
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3390/machines13020162
– Name: URL
  Label: Availability
  Group: URL
  Data: https://doi.org/10.3390/machines13020162
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: https://creativecommons.org/licenses/by/4.0/
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.5BBA5E48
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.5BBA5E48
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/machines13020162
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: UAV obstacle avoidance
        Type: general
      – SubjectFull: artificial potential field
        Type: general
      – SubjectFull: dynamic environment
        Type: general
      – SubjectFull: DQN algorithm
        Type: general
      – SubjectFull: Yolov8
        Type: general
    Titles:
      – TitleFull: Unmanned Aerial Vehicle Path Planning in Complex Dynamic Environments Based on Deep Reinforcement Learning
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Jiandong Liu
      – PersonEntity:
          Name:
            NameFull: Wei Luo
      – PersonEntity:
          Name:
            NameFull: Guoqing Zhang
      – PersonEntity:
          Name:
            NameFull: Ruihao Li
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
          Titles:
            – TitleFull: Machines ; Volume 13 ; Issue 2 ; Pages: 162
              Type: main
ResultId 1