An improved adaptive particle swarm optimization algorithm with interactions between particles for path planning of underwater vehicles

Path planning for underwater vehicles in complex underwater environments has become one of the key research areas. However, there are many drawbacks, such as slow convergence rates, poor real-time performance, and local optima, which lead to not being able to find the optimal path. Based on the particle swarm optimization (PSO) algorithm, a new adaptive PSO algorithm with interaction evidence (IEAPSO) is proposed. Firstly, we design the control strategy with a dynamic inertia weight and adaptive learning factor to update the velocity and position of particles. Secondly, considering the influence of neighboring particles on their own velocity and position during the spatial search process, we put forward an improved strategy with interaction evidence between particles to adjust their own velocity and position. Finally, the IEAPSO algorithm is applied to path planning for underwater vehicles and corresponding simulation experiments are accomplished. Simulation results show that the IEAPSO algorithm on three-dimensional trajectories in complex environments has better performances than other algorithms.