摘要
提出一种新的基于神经网络的机器人模型参考自适应控制方法。采用动态对角回归神经网络作为辨识器和控制器 ,实现了机器人轨迹跟踪的最小误差控制。给出了神经网络的学习算法 ,通过实例仿真证明了控制方法应用于未知模型机器人系统的正确性和有效性。
A new robot model reference adaptive control method based on neural networks is presented. Using dynamic recurrent neural networks as identification and controller, the minimum error control of robot tracking the idea locus is implemented. The learning algorithm of neural networks is given. The correctness and validity that the control method presented is used to unknown model robot system is testified by emulation.
出处
《高技术通讯》
EI
CAS
CSCD
2000年第11期81-83,共3页
Chinese High Technology Letters
基金
86 3计划资助项目!(86 3 5 12 2 0 0 7)