Research on Path Planning Optimization Based on Genetic Algorithm

Abstract

In real life, robots are subject to multiple constraints when moving in complex scenes, which can lead to problems such as poor optimization ability, unsmooth path planning, and slow convergence speed of search algorithms. A robot path planning method based on improved genetic algorithm is proposed to address the above issues. Firstly, a grid method is used to construct the mobile environment of the robot, and a model is constructed under constraints such as path smoothness, path length, and path difficulty; Then, the traditional genetic algorithm was improved through smoothing operators and its performance was verified through experiments. The simulation results show that the algorithm proposed in this paper can effectively handle path planning problems under multiple constraint conditions and find the most suitable smooth path for robot motion. Through comparative experiments, this method has relative advantages in path length, smoothness, and runtime.