仿蝠鲼航行器游动规律智能控制与优化方法

Intelligent Control and Optimization Method for the Swimming Law of the Biomimetic Manta Vehicle

摘要:

固化的游动策略导致仿生航行器难以在变化的水下环境中保持高效率运动，以仿蝠鲼航行器为研究对象，提出了基于深度强化学习的仿生航行器胸鳍摆动智能控制方法，实现了航行器对高效摆动规律的自适应控制和优化。仿真示例表明：与初始给定的游动策略相比，优化后的游动策略在航行速度上提升了 14.46%，在游动能效上提升了 24.48%，从而验证了该方法在仿生航行器游动规律自适应控制与优化设计中的有效性。

Abstract:

In order to solve the problem of low energy efficiency of biomimetic vehicle with pectoral fins in dynamic underwater environment caused by the solidified swimming law，an intelligent control method based on deep reinforcement learning is proposed to optimize the energy efficiency of the manta-ray like vehicle，which realizes the adaptive control and optimization of the efficient swimming law. The simulation results show that compared with the solidified swimming strategy，the optimized swimming strategy improves the navigation speed by 14.46% and decreases the energy assumption by 24.48%，which validates the effectiveness of the proposed method.