PSO-QGA在移动机器人复杂路径规划中的应用

量子遗传算法具有适应性强、收敛速度快、适合于全局搜索的特点,粒子群优化算法的优点是具有记忆能力,在智能搜索的实现上可以结合个体和全局的最佳位置实现位置定位,但粒子群优化算法在搜索速度和择优能力方面还有待提升.因此提出了一种改进的路径规划算法,即利用量子遗传算法结合粒子群优化算法的记忆功能和最佳定位能力,实现对移动机器人路径规划算法的改进.通过仿真实验已经证明,改进后的移动机器人路径规划算法在稳定性和路径优化选择上都优于单纯的粒子群优化算法和量子遗传算法,并且改进后的算法更适合于复杂路径中实现优化.

The Application of PSO-QGA in Path Planning of Mobile Robot

The quantum genetic algorithm has strong adaptability,fast convergence speed,and is suitable for global search. The advantages of particle swarm optimization algorithm are the memory capacity,and the fixed position with individual and global best location which can be implemented in the intelligent search. However,the search speed and preferred ability of the particle swarm optimization algorithm still need to be improved. Therefore,we put forward a kind of path planning algorithms,namely the quantum genetic algorithm combined with memory function and the best orientation ability of particle swarm optimization algorithm,are used to improve the path planning algorithm of mobile robot. The simulation experiment has proved that the improved path planning algorithm of mobile robot is better than simple particle swarm optimization algorithm and quantum genetic algorithm in the stability and choice of path optimization,and the improved algorithm is more suitable for implementation in complex path optimization.