Neural net robot controller with guaranteed tracking performance
Neural net robot controller with guaranteed tracking performance
复制标题
DOI：
10.1109/isic.1993.397709
复制
发表时间：
1993-08
期刊：
影响因子：
--
通讯作者：
F. Lewis;Kai Liu;A. Yesildirek
中科院分区：
文献类型：
--
作者：
F. Lewis;Kai Liu;A. Yesildirek
开发了一种用于通用串联机器人手臂的神经网络（NN）控制器。神经网络有两层，因此参数保持线性，但“净功能重建误差”被视为非零。神经网络控制器的结构是使用过滤误差/无源性方法导出的。结果表明，当用于实时闭环控制时，如果（1）网络无法精确地重建某个所需的控制函数，或者（2）机器人动力学中存在有界的未知扰动，则标准反向传播可以产生无界的神经网络权重。包括反向传播校正项的在线权重调整算法保证了跟踪以及有界权重。介绍了被动神经网络和鲁棒神经网络的概念。>
A neural net (NN) controller for a general serial-link robot arm is developed. The NN has two layers so that linearity in the parameters holds, but the "net functional reconstruction error" is taken as nonzero. The structure of the NN controller is derived using a filtered error/passivity approach. It is shown that standard backpropagation, when used for real time closed-loop control, can yield unbounded NN weights if (1) the net cannot exactly reconstruct a certain required control function, or (2) there are bounded unknown disturbances in the robot dynamics. An online weight tuning algorithm including a correction term to backpropagation guarantees tracking as well as bounded weights. The notions of a passive NN and a robust NN are introduced.>