A Weights and Improved Adaptive Artificial Fish Swarm Algorithm for Path Planning

Abstract

A weight and improved adaptive artificial fish swarm algorithm(WIA-AFSA) is proposed to deal with the problem of mobile robots path planning have low optimization accuracy and premature convergence under real environment. Firstly, introduced an improved aggregation degree factor to obtain an adaptive step and visual strategy, which can reflect the actual changes in the optimal state of the artificial fish swarm search, and better balance the global and local search capabilities. At the same time, the weight evaluation factor is introduced in the pray, swarm and follow behavior of the artificial fish, which effectively avoids the algorithm falling into the local optimum and premature. The benchmark function is used to test the performance of the algorithm. The results show that the algorithm has good searching ability and convergence. Simulation experiments of path planning based on raster model were carried out to verify the superiority of wia-afsa algorithm in robot navigation. Finally, the path planning experiment of the robot in real environment proves the effectiveness and practicability of the proposed algorithm.