基于改进免疫遗传优化蚁群算法的移动机器人路径寻优研究

针对移动机器人路径规划中使用蚁群算法(ACO)易陷入局部最优和收敛速度慢的问题,提出了一种适用于机器人静态路径寻优的改进免疫遗传优化蚁群算法(IMGAC)。该算法可以根据实际情况自动调整变异概率和变异方式,以及自动调节个体免疫位的长度,将通过改进的变异算子和免疫算子嵌入蚁群算法来提高全局寻优能力与收敛速度。仿真及实验表明:相比于经典ACO算法以及最大最小蚂蚁系统,IMGAC算法收敛速度更快,全局寻优能力更强。利用该算法寻找移动机器人最优路径,提高了静态路径寻优的效果和效率。

Robot Path Optimization Research Based on Improved Immune Genetic Optimization Ant Colony Algorithm

Aiming at the problem that the ant colony algorithm(ACO) is easy to fall into the local optimum and the convergence speed is slow in the path planning of mobile robots, an improved algorithm is proposed for the static path optimization of robots, which is called as improved immune genetic algorithm (IMGAC). The algorithm can automatically adjust the mutation probability and mutation mode according to the actual situation and automatically adjust the length of individual immunization bits. The improved mutation operator and immune operator are embedded in ant colony algorithm to improve the global optimization ability and convergence speed. Simulation and experiment show that compared with the classical ACO algorithm and the maximum and minimum ant system, the IMGAC algorithm can converge faster and have better global search ability. The IMGAC algorithm also improves to the result and efficiency of robot path optimization.