Underactuated Unmanned Ship Trajectory Tracking Control Based on LSTM and DDPG Under Environmental Disturbance

To solve the trajectory tracking problem of low-speed small unmanned ships with unknown environmental disturbances, and enhance the computational performance of trajectory tracking. This article is based on LSTM neural network and reinforcement learning DDPG algorithm to establish an unmanned ship trajectory tracking control model considering event triggering mechanism. Firstly, establish a kinematic and dynamic model of three degree of freedom unmanned ships, and design a trajectory tracking controller through feedback linearization method. Secondly, the LSTM network is used as the actor network of the DDPG algorithm, and an LSPG model is established to adapt the control parameters of the trajectory tracking controller. Subsequently, event triggering conditions are set based on trajectory tracking errors. When the event is triggered, the trajectory tracking controller outputs control force to achieve trajectory tracking of unmanned ships. Finally, numerical simulation experiments are conducted, which verified the effectiveness of the trajectory tracking control algorithm and demonstrated that the trajectory tracking model considering event triggering mechanism can effectively enhance computational performance while achieving trajectory tracking objectives.