何永强, 张启先. 基于分散神经网络的多指灵巧手位置控制[J]. 机器人, 2002, 24(1): 26-30.
引用本文: 何永强, 张启先. 基于分散神经网络的多指灵巧手位置控制[J]. 机器人, 2002, 24(1): 26-30.
HE Yong-qiang, ZHANG Qi-xian. DECENTRALIZED NEURAL NETWORK BASED POSITION CONTROL OF MULTI-FINGERED DEXTEROUS HAND[J]. ROBOT, 2002, 24(1): 26-30.
Citation: HE Yong-qiang, ZHANG Qi-xian. DECENTRALIZED NEURAL NETWORK BASED POSITION CONTROL OF MULTI-FINGERED DEXTEROUS HAND[J]. ROBOT, 2002, 24(1): 26-30.

基于分散神经网络的多指灵巧手位置控制

DECENTRALIZED NEURAL NETWORK BASED POSITION CONTROL OF MULTI-FINGERED DEXTEROUS HAND

  • 摘要: 针对多指灵巧手钢缆传动系统的非线性,提出一种基于分散神经网络的位置控制方法.通过对复杂的钢缆传动系统施加不同的输入可以得到特定的相对简单的输入输出数据,利用这种特定的输入输出数据学习传动系统的非线性关系得到多个分散的神经网络,再根据传动系统的结构特性用分散的神经网络求取钢缆传动系统的逆模型,用于直接逆控制,从而达到补偿非线性误差的目的.同时应用在线神经网络的适时补偿使系统长时间保持良好的运行状态.实验证明这种方法可大大提高位置跟踪精度.取得比较满意的结果.

     

    Abstract: A decentralized neural network based position control method is presented for multi-fingered dexterous hand with nonlinear tendon-drive system. Multiple decentralized neural network is acquired via learning nonlinear relationship of tendon-driving system using the simple input output data that obtained by applying different input to the complex drive system. Then the inverse model of the tendon-drive system can be established using the decentralized neural networks according to the characteristics of the tendon-drive system. In the meantime, an online neural network is used to keep well running state for a long time. Experiment illustrates the proposed method can improve greatly the tracking accuracy.

     

/

返回文章
返回