The purpose of this paper is to study the control method of the Robotic Manta and complete its depth control using a T-S fuzzy neural network controller.
The Robotic Manta adopts Median and/or Paired Fin propulsion mode, which has good stability. By adjusting the caudal fin angle, the Robotic Manta can swim upward or downward. Due to the complex hydrodynamics and the uncertainty existing in the environment, it is difficult to establish an accurate mathematical model. In this paper, data acquisition is carried out for the depth control of the Robotic Manta and a T-S fuzzy neural network is designed and trained. Finally, this paper implements the automatic depth control of the Robotic Manta with the T-S fuzzy neural network controller.
The experimental results show that the depth error of the Robotic Manta is less than 60 mm, with good rapidity and small overshoot, which verifies the effectiveness of the T-S fuzzy neural network controller in design and implementation.
Control of Robotic Manta Based on T-S Fuzzy Neural Network
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 276 ; 2813-2822
2022-03-18
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Artificial manta ray robotic fish with passive deformation structure
Europäisches Patentamt | 2023
|Intelligent Control Strategy for Robotic Manta via CPG and Deep Reinforcement Learning
DOAJ | 2024
|