Three-dimensional path planning for autonomous underwater vehicles based on a whale optimization algorithm

Due to the influence of the complex underwater environment, safety, smoothness, real-time requirements and poor integrity, the path of autonomous underwater vehicles is mainly determined by perception, decisionmaking and control systems. These not only achieve object detection and environmental investigation but also ensure the safety and reliability of autonomous navigation systems. This paper proposes a whale optimization algorithm based on forward-looking sonar to tackle the three-dimensional path planning of autonomous underwater vehicles. The purpose of path planning is to effectively avoid threatened regions and obtain the shortest and safest paths with minimal fuel and time. The whale optimization algorithm based upon bubble-net hunting behavior imitates the contraction surrounding mechanism, logarithmic spiral position updating mechanism and stochastic searching mechanism to effectively solve the complex problem in the solution space. The whale optimization algorithm not only avoids premature convergence and avoids falling into the local optimum to achieve the global optimal solution but also utilizes exploration and exploitation to enhance the convergence speed and calculation accuracy. To verify the superiority and overall optimization performance of the whale optimization algorithm, the optimization results of the algorithm are compared with other algorithms by minimizing the fitness value. The experimental results reveal that the whale optimization algorithm has better planning efficiency, shorter execution time, faster convergence speed and higher solution precision, which is effective and efficient for path planning.