Underwater vehicle trajectory planning in dynamic environments based on Radau Pseudospectral method

Abstract

In this paper, the problem of trajectory planning for underwater vehicle in dynamic environments is discussed. Considering the kinematics model of underwater vehicle, the optimal trajectory planning model is set up with the goal of minimum time consumption and collision avoidance. Based on the local recurrent neural networks, the state equation is constructed for prediction of obstacle trajectory. According to the optimization model and the predicted obstacle trajectory, the trajectory of underwater vehicle is planned by Radau Pseudospectral Method (RPM). Finally, the proposed method is verified by simulation.