摘要
针对传统蚁群算法在进行无人机三维环境路径规划时存在规划速度慢、容易陷入局部最优等问题,本文提出了用引导函数改变状态转移规则、初始信息素先验分配、时变信息素更新方式3个改进策略,充分挖掘路径规划先验信息。通过增加引导函数进行路径增强,增大最优路径的选择概率;同时根据与先验路径的距离赋予信息素不同的初始浓度,使算法在搜索初期具有明确的方向性,基于优胜劣汰的思想进行信息素更新,并将信息素挥发因子设定为服从Laplace分布的波动因子,避免搜索过程陷入局部最优,最大化提升路径搜索效率,实现三维环境下的无人机路径规划。仿真试验结果表明,改进后的蚁群算法在规划最优路径长度和最优路径搜索效率上明显优于传统蚁群算法。
Aiming at the problems of slow planning speed and easy to fall into local optimization when the traditional ant colony algorithm is used for path planning of UAV 3D environment,this paper proposes three improved strategies:changing the state transition rules with the guidance function,the prior distribution of the initial pheromone,and the time-varying pheromone update method,fully mining the prior information of path planning,enhancing the path by adding the guidance function,and increasing the probability of selecting the optimal path.At the same time,the pheromone is given a different initial concentration according to the distance from the prior path,so that the algorithm has a clear direction in the initial search.The pheromone is updated based on the idea of survival of the fittest,and the pheromone volatilization factor is set as a fluctuation factor that obeys the Laplace distribution,so as to avoid the search process from falling into local optimization,maximize the path search efficiency,and realize the path planning of UAV in the 3D environment.The simulation results show that the improved ant colony algorithm is superior to the traditional ant colony algorithm in planning the optimal path length and searching efficiency.
作者
董志洋
李慧
葛靖宇
程建华
DONG Zhiyang;LI Hui;GE Jingyu;CHENG Jianhua(College of Intelligent Systems Science and Engineering,Harbin Engineering University,Harbin 150001,China)
出处
《测绘通报》
CSCD
北大核心
2023年第5期153-157,共5页
Bulletin of Surveying and Mapping
基金
国家自然科学基金(62073093,62003108)
中国博士后科学基金(2020M681078)。
关键词
路径规划
蚁群算法
无人机
信息素
path planning
ant colony algorithm
UAV
pheromone
