Unmanned ship path following system and method based on deep reinforcement learning

The invention discloses an unmanned ship path following system based on deep reinforcement learning. A simulation platform construction module of the unmanned ship path following system is used for constructing an unmanned ship motion interaction simulation platform; the Markov decision modeling module is used for performing Markov decision process modeling by using an unmanned ship motion control task; the neural network construction module is used for designing a deep neural network based on a DDPG algorithm architecture according to a state space, an action space and a reward function in a Markov decision process; the strategy model construction module uses a DDPG algorithm on a simulation platform to train the deep neural network to obtain an unmanned ship path following control strategy model; and the path following control module is used for realizing the path following control of the unmanned ship by combining the path following control strategy model of the unmanned ship with a sight guidance algorith