摘要
针对标准粒子群算法在移动机器人路径规划问题上存在的收敛速度慢、易陷入“早熟”现象以及路径不平滑等缺点,对粒子群优化算法进行改进,该方法在粒子陷入局部最优值时,对全局最优粒子的速度进行了轻微的干扰,从而提高收敛速度。为了平衡局部和全局搜索能力,提出了非线性惯性权重。最后提出一个考虑路径最短和平滑性的适应度函数。仿真结果表明,在一个动态环境中,改进之后的粒子群优化算法收敛快,并能避开障碍物,寻找到符合要求的最优路径。
Aiming at the shortcomings of the standard particle swarm algorithm in the path planning of mobile robots, such as slow convergence, easy to fall into the "premature" phenomenon, and unsmooth path, the particle swarm optimization algorithm is improved in this paper. When the particles fall into the local optimal value, this improved method can slightly perturb the speed of the global optimal particle to increase the convergence speed. In order to balance the local and global search capabilities, nonlinear inertia weights are proposed. Finally, a fitness function considering the shortest path and smoothness is also proposed. The simulation results show that in a dynamic environment, the improved particle swarm optimization algorithm converges quickly,avoids obstacles, and finds the optimal path that meets the requirements.
作者
巫光福
万路萍
WU Guangfu;WAN Luping(School of Information Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,Jiangxi,China)
出处
《机械科学与技术》
CSCD
北大核心
2022年第11期1759-1764,共6页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金项目(11461031)
江西省自然科学基金项目(20181BBE58018)
江西省教育厅科技计划项目(GJJ180442)
江西省教育厅科技重点项目(GJJ170492)。
关键词
粒子群算法
非线性惯性权重
平滑性
路径规划
particle swarm algorithm
nonlinear inertia weights
smoothness
path planning
