摘要
传统的寻路算法通常用在已知地形结构的基础上规划路线,而扫地机器人的工作环境通常是陌生的,传统寻路算法在此失效。该文结合BP神经网络的特性,提出一种基于BP神经网络的扫地机器人寻路算法,目标是使扫地机器人能够在任何陌生的环境中正确地完成寻路任务,通过分析扫地机器人的清扫模式,建立观察模型和运动模型,利用MatLab实现对应的BP神经网络,并对传统BP网络激励函数进行了优化,最后经过训练和仿真验证了算法的有效性和实用性。
The traditional Pathfinding algorithm is usually used in route planning based on the knowned structure of terrain, buttheworking environment of sweeping robot is often unknowned, traditional algorithm failure.Combined with the characteristics ofBP neural network, this paper puts forward a pathfinding algorithm based on BP neural network, the goal is to make the sweepingrobot correctly complete wayfinding tasks in any strange environment, through analysing the sweeping mode of sweeping robotmode, we establish the observation model and motion model, then we apply the BP neural network by MatLab, and optimized thetraditional BP network excitation function. finally we validate the availability and practicability of the algorithm.
作者
杨忠
刘华春
YANG Zhong, LIU Hua-chun （The Engineering ＆ Technical College of Chengdu University of Technology, Leshan 614000, China）
出处
《电脑知识与技术》
2017年第4期156-158,共3页
Computer Knowledge and Technology
基金
乐山市重点科技项目：基于人工神经网络的物联网应用研究（编号：05GZ0014-28）
关键词
寻路算法
扫地机器人
BP神经网络
pathfinding algorithm
sweeping robot
BP neural network
