【摘要】 针对传统粒子群算法(Particle Swarm Optimization, PSO)在全局路径规划过程中存在搜索路径不合理、容易陷入局部最优解等问题，提出了一种PSO-ABC(Particle Swarm Optimization-Artificial Bee Colony Algorithm)融合搜索算法。首先，提出惯性权重自适应更新与动态学习因子策略，使得粒子能够随着迭代次数的变化而更新惯性权重与学习因子，提高算法的寻优能力和收敛速率；其次，提出粒子拥挤度因子的概念，增强算法跳出局部极小值的能力；最后，引入人工蜂群算法中的跟随蜂和侦察蜂思想，提高融合算法的全局搜索能力。设置4种不同的障碍物环境进行仿真实验，实验结果表明，改进的融合算法相较于3种对比算法路径规划速度快且路径短，提高了算法搜索路径的成功率，其综合性能显著优于传统的粒子群算法。更多还原

【Abstract】 Aiming at the problems of unreasonable search path and easy to fall into local optimal solution in the process of global path planning in the traditional Particle Swarm Optimization(PSO) algorithm, a PSO-ABC(Particle Swarm Optimization-Artificial Bee Colony Algorithm) fusion search algorithm is proposed.Firstly, the strategy of adaptive updating of inertia weight and dynamic learning factor is proposed to enable particles to update inertia weight and learning factor with the change of iteration times, so as to improve the optimization ability and convergence rate of the algorithm; Secondly, the concept of particle crowding degree factor is proposed to enhance the ability of the algorithm to jump out of local minima; Finally, the idea of Onlooker bees and Scouter bees in the Artificial Bee Colony Algorithm is introduced to improve the global search ability of the fusion algorithm.Four different obstacle environments are set up for simulation experiments.The experimental results show that the improved fusion algorithm is faster and shorter than the three comparison algorithms in path planning, improves the success rate of the algorithm search path, and its comprehensive performance is significantly better than the traditional Particle Swarm Optimization Algorithm.更多还原