Path Planning of Underwater Vehicles Based on Improved Whale Optimization Algorithm

Abstract

In order to better solve path planning problems of underwater vehicles on complicated seabed terrains under ocean currents, a global path planning method based on whale optimization algorithm (WOA) is proposed. We focus on the fixed-depth navigation, and the underwater environment is modeled based on the MAKLINK graph. Three criteria of the length, smoothness and energy cost are used to evaluate a path. Considering that the original WOA algorithm lacks of balance in the exploration and exploitation at different positions in the search space and is easy to fall into local optima, the improved whale optimization algorithm (IWOA) is presented. The proposed algorithm creates an adaptive elite set by selecting best individuals from the population, and the members of the set will be randomly selected to be combined into new individuals to guide the searching process of the proposed algorithm. The corresponding guidance strategy is that the search agents update the position directionally based on the locations and orientations of the new individuals, replacing the encircling update centered on the position of prey in the original algorithm. Dijkstra algorithm is utilized for “coarse-grained planning” of path planning, and an approach to augment the waypoints is developed to cooperate with the proposed IWOA to complete the “fine-grained planning”. Above two-step planning forms the global path planning method proposed in this paper. The simulation results show that the proposed method is feasible and effective through testing under different circumstances. Compared with original WOA, paths planned by proposed method and IWOA have higher qualities, with shorter lengths, smoother paths and more energy saving.