Intelligent obstacle avoidance algorithms for autonomous underwater vehicle

Real-time obstacle avoidance is the basis to ensure the safe operation of the autonomous underwater vehicle (AUV), and it also represents the intelligent level of AUV. The main factors that affect AUV obstacle avoidance are environment perception ability, obstacle avoidance decision-making ability,...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of physics. Conference series Ročník 1693; číslo 1; s. 12223 - 12230
Hlavní autoři: Liu, Hui, Guo, Yinjing
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bristol IOP Publishing 01.12.2020
Témata:
Algorithms
Artificial neural networks
Autonomous underwater vehicles
Decision making
Fuzzy logic
Machine learning
Neural networks
Obstacle avoidance
Ocean currents
Physics
Tracking control
Trajectory control
ISSN:1742-6588, 1742-6596
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Real-time obstacle avoidance is the basis to ensure the safe operation of the autonomous underwater vehicle (AUV), and it also represents the intelligent level of AUV. The main factors that affect AUV obstacle avoidance are environment perception ability, obstacle avoidance decision-making ability, and trajectory tracking control ability. This paper starts from the perspective of obstacle avoidance decision-making ability, that is, obstacle avoidance algorithm. Firstly, we summarized the structure and influencing factors of AUV real-time obstacle avoidance. Then, we introduced in detail the research progress of AUV intelligent obstacle avoidance algorithms, including fuzzy logic algorithms, neural network algorithms, and reinforcement learning algorithms. And we analysed the improvement methods of each algorithm from three-dimensional underwater environment, ocean current, AUV motion characteristics, and dynamic obstacles. Finally, we prospected the development of the AUV intelligent obstacle avoidance algorithm.
Bibliografie:ObjectType-Conference Proceeding-1
SourceType-Scholarly Journals-1
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1693/1/012223