Robot Global Path Planning Based on Improved Second-Order PSO Algorithm

When using particle swarm optimization (PSO) to realize the global path planning of the robot, premature convergence and falling into the local optimum often occur. Therefore, an improved second-order PSO is used to improve premature convergence and analyze its stability. The logistic function relationship is established between the inertia weight and the learning factors. Using linearly decreasing inertia weight and adaptive learning factors, making the inertia weight change together with the learning factors to change the global or local flight ability to improve the ability to jump out of the local optimum. Through simulation comparison, it is proved that the improved second-order PSO proposed in this paper has the ability to jump out of the local optimum in the global path planning, and at the same time avoids premature convergence, and can also improve the convergence speed of the algorithm, which verifies the effectiveness of the algorithm.