We present a look-ahead based trajectory planning algorithm for computation of dynamically feasible trajectories for Unmanned Sea Surface Vehicles (USSV) operating in high seas states. The algorithm combines A* based heuristic search and locally bounded optimal planning under motion uncertainty using a variation of the minimax game-tree search. This allows the algorithm to compute trajectories that explicitly consider the possibility of the vehicle safely deviating from its original course due to the ocean waves within a specified look-ahead region. The algorithm can adapt its search based on the user-specified risk thresholds. Moreover, the algorithm produces a contingency plan as a part of the computed trajectory. We demonstrate the capabilities of the algorithm using simulations.
展开▼
