Research on Constraining Strategies of Underwater Glider's Trajectory Under the Influence of Ocean Currents Based on DQN Algorithm

This paper presents a novel approach about constraining trajectories of underwater gliders based on Deep Q Network(DQN) and the dynamic model of gliders. In terms of dynamics modeling, we choose the angle of attack and roll angle as the input of the glider' movement simulation, the profile motions in the vertical plane is manipulated by the angle of attack, and the gyratory motion is accomplished by controlling the roll angle. Since different roll angles allow the glider to turn with different radius, it can be used to counteract the influence of current on the motion state of the glider. And the determination of the proper roll angle to make the glider's trajectory consistent with the preset route is a sequential decision problem. We use the glider's motion space discretization and apply the deep reinforcement learning theory to acquire the optimal roll angle, thus finally achieve the goal that improves the accuracy of the glider's trajectory. The simulation results show that the proposed method has better performance and advantage to deploy compared with the conventional PID method.