Improved Swarm Optimization and Path Planning Intelligent Robot

Abstract

This research provides an improved particle swarm optimization technique including features of differential evolution in response to the shortcomings of particle swarm optimization in mobile robot path planning, such as poor convergence accuracy and susceptibility to premature convergence. The method, which incorporates adaptive adjustment weights and acceleration coefficients to improve conventional particle swarm optimization, introduces the idea of corporate governance. This change speeds up algorithm convergence. Additionally, adaptive parameters are included to control the magnitude of the mutations in order to improve the performance of the differential evolution process. Additionally, a "high-intensity training" mode is created to precisely refine the search accuracy of the algorithm by intensely training the global ideal position of the particle swarm optimization using the improved differential evolution algorithm.A mathematical model for robot path planning is presented in the paper as a two-objective optimization problem that takes into account both the length of the path and the level of hazard. For path planning, the suggested method is put through a number of experiments and simulated tests. The outcomes demonstrate the algorithm's viability and efficiency in resolving path planning issues for mobile robots.