论文部分内容阅读
针对经典蚁群算法在复杂环境下的机器人路径规划问题中表现出的收敛速度慢,容易陷入局部最优等问题,提出一种改进算法.依据方向指导信息来优化初始信息素的分布,加快搜索速度,缩减搜索初期的时间消耗;通过优化信息素的挥发与更新规则,保留局部与全局优秀路径的优势信息,改善收敛速度慢的问题;基于区域安全因素对转移概率进行改进,从而避免陷入局部最优和死锁等问题.最后,通过栅格法对仿真环境建模,在不同复杂度与规模的多张地图上进行仿真实验,对比验证了该算法在复杂环境下路径规划问题上的有效性和对不同规模地图的适应性.
Aiming at the problems that the classical ant colony algorithm is slow in convergence and easy to fall into the local optimum in the robot path planning problem under complex environment, an improved algorithm is proposed to optimize the distribution of the initial pheromone and speed up the search according to the directional guidance information , And reduce the time consumption during the initial search. By optimizing the rule of pheromone volatilization and updating, the advantages of local and global excellent path are retained and the convergence speed is slowed down. The transition probabilities are improved based on the regional security factors so as to avoid being trapped locally Optimization and deadlock etc.Finally, through the gridding method, the simulation environment is modeled and simulated on multiple maps with different complexity and scale, and the comparison verifies the effectiveness of the algorithm in the path planning of complex environment And adaptability to maps of different sizes.