基于元胞遗传算法的机器人路径规划研究

使用基本遗传算法进行移动机器人路径规划时,面临路径进行插入修复无法保证解的可行性,且算法易陷入局部收敛的问题;针对上述问题,通过使用元胞遗传算法增强了路径规划环境建模的通用性,并在算法适应度函数中加入路径平滑因素改善了元胞遗传算法的路径;仿真实验表明,该算法和基本遗传算法相比,机器人行驶路径的长度减少,转角绝对值之和减小,得到了距离短且平滑的路径,提高了移动机器人的行驶效率和平稳性;由于算法良好的隐性迁移机制,因此在局部优化时保持了群体的多样性,一定程度克服了算法的早熟现象,有效解决了移动机器人路径规划问题。

Research on Path Planning Based on Cellular Genetic Algorithm

When using the basic genetic algorithm for path planning of mobile robots, the problem is that the insertion repair of the path cannot guarantee the feasibility of the solution, and the algorithm is easy to fall into local convergence. In response to the above problems, the use of cell genetic algorithm enhances the versatility of path planning environment modeling, and adds a path smoothing factor to the algorithm fitness function, thereby improving the path of the cell genetic algorithm.Simulation experiments show that compared with the basic genetic algorithm, the length of the robot''s driving path is reduced, and the sum of the absolute values of the corners is reduced. A short and smooth path is obtained, and the driving efficiency and stability of the mobile robot are improved. Due to the good implicit migration mechanism of the algorithm, the diversity of the group is maintained during local optimization, which overcomes the premature phenomenon of the algorithm to a certain extent and effectively solves the problem of mobile robot path planning.