摘要
为了解决传统路径规划算法缺少自主学习,以及不适用于局部路径规划的问题。本文提出了一种基于神经网络的AGV智能车(Automated Guided Vehicle)路径规划算法,目的是在未知环境中为AGV提供无碰撞规划路线。这种算法是在神经网络算法的基础上,采用一种四层的网络结构,设计能量函数作为网络的评价函数,通过求能量函数极值,使得AGV智能车根据路径点集运动趋向来调节小车移动,完成路径规划任务。通过计算机仿真实验,证明了方法的有效性。
In order to solve the problem that traditional path planning algorithm lacks autonomous learning and it is not suitable for local path planning,this paper puts forward an algorithm of AGV intelligent vehicle path planning based on neural network to provide collision-free planning route for AGV in unknown environment.Based on the neural network algorithm,this algorithm uses a four-layer network structure and designs the energy function as the evaluation function of the network.Through calculating the extreme value of the energy function,the AGV intelligent vehicle control the car moving according to the path point set movement trend,and finish the path planning task.Through the computer simulation experiment,the effectiveness of the method is proved.
作者
项宏峰
曹少中
徐长波
李新佩
Xiang Hongfeng;Cao Shaozhong;Xu Changbo;Li Xinpei(The high-end printing equipment signal and Information Processing Laboratory of Beijing Beijing Institute of Graphic Communication, Beijing 102600, China)
出处
《北京印刷学院学报》
2017年第7期128-130,共3页
Journal of Beijing Institute of Graphic Communication
基金
国家自然基金(编号:61472461)
国家重大科学仪器设备开发专项(编号:2013YQ140517)
