数学优化
运动规划
粒子群优化
稳健性(进化)
计算机科学
地形
人口
路径(计算)
多群优化
趋同(经济学)
人工智能
数学
机器人
地理
生物化学
化学
人口学
地图学
社会学
基因
程序设计语言
经济增长
经济
作者
Shuang Xia,Xiangyin Zhang
出处
期刊:Actuators
[Multidisciplinary Digital Publishing Institute]
日期:2021-09-29
卷期号:10 (10): 255-255
被引量:17
摘要
This paper considered the constrained unmanned aerial vehicle (UAV) path planning problem as the multi-objective optimization problem, in which both costs and constraints are treated as the objective functions. A novel multi-objective particle swarm optimization algorithm based on the Gaussian distribution and the Q-Learning technique (GMOPSO-QL) is proposed and applied to determine the feasible and optimal path for UAV. In GMOPSO-QL, the Gaussian distribution based updating operator is adopted to generate new particles, and the exploration and exploitation modes are introduced to enhance population diversity and convergence speed, respectively. Moreover, the Q-Learning based mode selection logic is introduced to balance the global search with the local search in the evolution process. Simulation results indicate that our proposed GMOPSO-QL can deal with the constrained UAV path planning problem and is superior to existing optimization algorithms in terms of efficiency and robustness.
科研通智能强力驱动
Strongly Powered by AbleSci AI