OPTION-DQN algorithm flowchart.
<div><p>In response to the inefficiencies in offshore wind farm inspections caused by path redundancy and mission omissions, this study proposes a novel path planning method for Unmanned Aerial Vehicle (UAV) inspections, integrating multi-constraint optimization and intelligent schedulin...
Wedi'i Gadw mewn:
| Prif Awdur: | |
|---|---|
| Awduron Eraill: | , , , , |
| Cyhoeddwyd: |
2025
|
| Pynciau: | |
| Tagiau: |
Ychwanegu Tag
Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!
|
| _version_ | 1849927642401210368 |
|---|---|
| author | Meiqing Xu (8502255) |
| author2 | Chao Deng (329151) Xiangyu Hu (4326106) Yuxin Lu (225932) Wenyan Xue (22676549) Bin Zhu (182882) |
| author2_role | author author author author author |
| author_facet | Meiqing Xu (8502255) Chao Deng (329151) Xiangyu Hu (4326106) Yuxin Lu (225932) Wenyan Xue (22676549) Bin Zhu (182882) |
| author_role | author |
| dc.creator.none.fl_str_mv | Meiqing Xu (8502255) Chao Deng (329151) Xiangyu Hu (4326106) Yuxin Lu (225932) Wenyan Xue (22676549) Bin Zhu (182882) |
| dc.date.none.fl_str_mv | 2025-11-24T18:30:00Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0336935.g005 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/OPTION-DQN_algorithm_flowchart_/30697196 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Microbiology Neuroscience Evolutionary Biology Inorganic Chemistry Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified unmanned aerial vehicle faster simulation time encompassing wind speed dynamic obstacle avoidance deep reinforcement learning balance global navigation dimensional constraint model conventional heuristic methods heuristic search constraint optimization xlink "> study proposes simulated annealing path redundancy path distance mission omissions means algorithm local optimization intelligent scheduling improved k comparative evaluations |
| dc.title.none.fl_str_mv | OPTION-DQN algorithm flowchart. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>In response to the inefficiencies in offshore wind farm inspections caused by path redundancy and mission omissions, this study proposes a novel path planning method for Unmanned Aerial Vehicle (UAV) inspections, integrating multi-constraint optimization and intelligent scheduling. First, a four-dimensional constraint model is established, encompassing wind speed, charging, minimum UAV fleet size, and dynamic obstacle avoidance. Second, the OPTION-A*-DQN hybrid algorithm is developed by synergizing A* heuristic search with deep reinforcement learning (DRL) to balance global navigation and local optimization. An improved K-Means algorithm further enables efficient topological partitioning for multi-UAV collaboration. Comparative evaluations against original OPTION-DQN and conventional heuristic methods (Dijkstra and Simulated Annealing) demonstrate that the proposed method achieves three key improvements: (1) a 10% higher task completion rate, (2) a 14.9% reduction in path distance, and (3) a 20% faster simulation time. This work significantly advances intelligent path planning for offshore wind farm inspections.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_d99da165407580938c5c0967fd9b36f4 |
| identifier_str_mv | 10.1371/journal.pone.0336935.g005 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30697196 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | OPTION-DQN algorithm flowchart.Meiqing Xu (8502255)Chao Deng (329151)Xiangyu Hu (4326106)Yuxin Lu (225932)Wenyan Xue (22676549)Bin Zhu (182882)MicrobiologyNeuroscienceEvolutionary BiologyInorganic ChemistryScience PolicySpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedunmanned aerial vehiclefaster simulation timeencompassing wind speeddynamic obstacle avoidancedeep reinforcement learningbalance global navigationdimensional constraint modelconventional heuristic methodsheuristic searchconstraint optimizationxlink ">study proposessimulated annealingpath redundancypath distancemission omissionsmeans algorithmlocal optimizationintelligent schedulingimproved kcomparative evaluations<div><p>In response to the inefficiencies in offshore wind farm inspections caused by path redundancy and mission omissions, this study proposes a novel path planning method for Unmanned Aerial Vehicle (UAV) inspections, integrating multi-constraint optimization and intelligent scheduling. First, a four-dimensional constraint model is established, encompassing wind speed, charging, minimum UAV fleet size, and dynamic obstacle avoidance. Second, the OPTION-A*-DQN hybrid algorithm is developed by synergizing A* heuristic search with deep reinforcement learning (DRL) to balance global navigation and local optimization. An improved K-Means algorithm further enables efficient topological partitioning for multi-UAV collaboration. Comparative evaluations against original OPTION-DQN and conventional heuristic methods (Dijkstra and Simulated Annealing) demonstrate that the proposed method achieves three key improvements: (1) a 10% higher task completion rate, (2) a 14.9% reduction in path distance, and (3) a 20% faster simulation time. This work significantly advances intelligent path planning for offshore wind farm inspections.</p></div>2025-11-24T18:30:00ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0336935.g005https://figshare.com/articles/figure/OPTION-DQN_algorithm_flowchart_/30697196CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306971962025-11-24T18:30:00Z |
| spellingShingle | OPTION-DQN algorithm flowchart. Meiqing Xu (8502255) Microbiology Neuroscience Evolutionary Biology Inorganic Chemistry Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified unmanned aerial vehicle faster simulation time encompassing wind speed dynamic obstacle avoidance deep reinforcement learning balance global navigation dimensional constraint model conventional heuristic methods heuristic search constraint optimization xlink "> study proposes simulated annealing path redundancy path distance mission omissions means algorithm local optimization intelligent scheduling improved k comparative evaluations |
| status_str | publishedVersion |
| title | OPTION-DQN algorithm flowchart. |
| title_full | OPTION-DQN algorithm flowchart. |
| title_fullStr | OPTION-DQN algorithm flowchart. |
| title_full_unstemmed | OPTION-DQN algorithm flowchart. |
| title_short | OPTION-DQN algorithm flowchart. |
| title_sort | OPTION-DQN algorithm flowchart. |
| topic | Microbiology Neuroscience Evolutionary Biology Inorganic Chemistry Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified unmanned aerial vehicle faster simulation time encompassing wind speed dynamic obstacle avoidance deep reinforcement learning balance global navigation dimensional constraint model conventional heuristic methods heuristic search constraint optimization xlink "> study proposes simulated annealing path redundancy path distance mission omissions means algorithm local optimization intelligent scheduling improved k comparative evaluations |