Robot Path Planning Based on Improved Pelican Optimization Algorithm

Abstract

To address more complex robot path planning problem, an improved Pelican optimization algorithm was proposed. Aiming at the problem of the weak local search ability of the Pelican optimization algorithm, firstly, a chaotic initialization strategy was introduced to improve the diversity of the initial population. Secondly, the golden sine algorithm was introduced to improve the local search ability of the algorithm. Finally, in order to prevent the algorithm from falling into the local optimum, the optimal individual chaotic search strategy was introduced to help the algorithm jump out of the local optimum. Four scale raster maps of 20x20, 30x30, 40x40 and 50x50 is used to test the proposed algorithm and comparison algorithms. In the path planning test, the path lengths found by the proposed algorithm are 40, and 102, respectively, which are shorter than those of the comparison algorithms, indicating that the proposed algorithm has good search performance for the robot path planning problem.