Research on Robot Path Planning Based on Improved Genetic Algorithm

摘要

Aiming at the disadvantages of genetic algorithm in robot path planning, such as blindness and randomness of initial population, too many path turning points and easy to fall into local optimization, an improved genetic algorithm is proposed. The prior knowledge is used to initialize the path in the direction of the target point, and the continuous and obstruction-free collision path is further obtained to enhance convergence rate. A new fitness function is designed combining the path length and the number of turning points to improve the efficiency of path planning. Simulation results show that compared with the traditional genetic algorithm, the shortest path of the improved genetic algorithm can be shortened by 9.97%, and it is better than the traditional genetic algorithm in convergence rate and the number of turning points.