摘要
机器人路径规划中,传统蚁群算法收敛速度慢,容易陷入局部最优解的问题。提出一种改进蚁群算法,该算法通过设置动态分级信息素浓度,在迭代过程中逐渐降低信息素浓度,有效地提高了收敛速度;当算法迭代陷入局部最优时,引入了惩罚系数,调整当前最优路径上的信息素浓度,增强算法随机性。仿真实验表明,改进后的蚁群算法加快了收敛速度,解决了局部最优解的问题,提高了全局寻优能力。
In the robot path planning,the traditional ant colony algorithm has slow convergence speed and easy to fall into the local optimal solution.An improved ant colony algorithm is proposed. By setting the dynamic hierarchical pheromone concentration,the algorithm gradually reduces the pheromone concentration in the iterative process,and effectively improves the convergence speed;when the algorithm iterations fall into the local optimum,the penalty coefficient is introduced to adjust the pheromone concentration on the current optimal path to enhance the randomness of the algorithm. Simulation results show that the improved ant colony algorithm speeds up the convergence speed,solves the problem of local optimal solution,and improves the global optimization ability.
作者
沈葭栎
李燕
季建楠
佘宇
SHEN Jiali;LI Yan;JI Jiannan;SHE Yu(College of Automation,Nanjing University of Infomation Science&Technology,Nanjing 210044;College of Computer Internet of Things Engineering,Nanjing University of Information Science&Technology Binjiang College,Wuxi 214105)
出处
《现代计算机》
2021年第22期5-9,共5页
Modern Computer
基金
南京信息工程大学滨江学院校级项目(No.2019bjyng001)。
关键词
蚁群算法
信息素浓度
惩罚系数
路径规划
Ant Colony Algorithm
Pheromone
Penalty Coefficient
Path Planning
