中国舰船研究2024，Vol.19Issue(6)：219-227,9.DOI:10.19693/j.issn.1673-3185.03492
基于深度强化学习的双体船姿态控制
Attitude control of catamaran based on deep reinforcement learning
秦雷洪 1张松涛 1南晓峰 1钟齐鸣1
作者信息
- 1. 哈尔滨工程大学 智能科学与工程学院,黑龙江 哈尔滨 150001
- 折叠
摘要
Abstract
[Objective]A longitudinal motion control algorithm based on deep reinforcement learning is pro-posed,focusing on the dependency of traditional control algorithms on precise mathematical models and sys-tem parameters in longitudinal motion control of catamarans.[Methods]By designing reward functions and neural network structures and adjusting relevant hyper-parameters,in combination with the catamaran model,through experiments,the control effect of the deep reinforcement learning DDPG algorithm and the GA-LQR algorithm under three different control modes and the robustness under different operating conditions and ini-tial states were compared.[Results]Under the same operating conditions,the DDPG algorithm has a slight advantage over the GA-LQR algorithm in control effect,but its fin angle output during the control process is more aggressive.In the simulation experiments under different operating conditions and initial states,when the system and the environmental models undergo significant changes,the control effect of the DDPG algorithm is significantly affected.However,when the system and the environment undergo small changes,the DDPG al-gorithm exhibits better adaptability and superiority over the GA-LQR algorithm.The comprehensive analysis shows that the DDPG algorithm demonstrates similarity to the GA-LQR algorithm in terms of performance.[Conclusions]The DDPG algorithm based on deep reinforcement learning has the potential of applications in the longitudinal motion control of catamarans,providing new research directions and methodological sup-port for ship motion control under complex sea conditions in the future.关键词
船舶设计/人工智能/深度强化学习/双体船/运动控制/姿态控制Key words
naval architecture/artificial intelligence/deep reinforcement learning/catamaran/motion control/attitude control分类
交通工程引用本文复制引用
秦雷洪,张松涛,南晓峰,钟齐鸣..基于深度强化学习的双体船姿态控制[J].中国舰船研究,2024,19(6):219-227,9.
