摘要：In this paper, an intelligent control scheme of formation collision avoidance and iterative docking is proposed for full-actuated unmanned surface vehicles (USVs). The artificial potential field method is integrated into the partial differential equation (PDE) formation control approach, which can improve the collision-avoidance performance of the formation. During the docking process of the straight-line formation, the USV agent is expected to track the desired commands accurately. Considering the possibility of docking failure, an iterative learning model predictive control (ILMPC) scheme is introduced. Once the moving USV fails in docking on the stationary USV, the moving agent can return to the origin to re-execute the docking process. The ILMPC method has the advantages of model predictive control and the iterative learning, so it can consider the future process dynamics in the time domain and overcome periodic disturbances. Simulation results show that USVs can avoid collisions with each other in the straight-line-formation mission. Furthermore, the USV agent can dock one-by-one successfully when interference exists.
