AUV 3D docking control using deep reinforcement learning

Abstract

Autonomous docking can enable AUV to have long endurance, so it is necessary to consider the issue of robust docking control under current and wave disturbances. In this work, based on the proximal policy optimization (PPO) algorithm, we developed a model-free docking controller to complete three-dimensional docking tasks under disturbances. To improve the performance of PPO, two mechanisms are proposed, including adaptive rollback clipping and self-generated demonstration replay. A simulation environment is constructed, including fuzzy hydrodynamic parameters, ocean current and wave disturbance model. Simulation results demonstrate that our proposed method has faster learning speed, higher robustness, and can control AUV to achieve 3D docking tasks in complex environments with a high success rate.